Business General

# Comparison of quantitative methods This section compares various quantitative analysis techniques, focusing on how variable types dictate the choice between linear regression, logistic regression, and ANOVA [2](#page=2). ### 1.1 Key considerations for choosing analysis techniques The selection of appropriate quantitative analysis techniques is critically dependent on the nature of the dependent and independent variables involved. A fundamental distinction is made between metric variables, which represent quantities, and categorical variables, which represent groups [2](#page=2). ### 1.2 Regression analysis: linear vs. logistic #### 1.2.1 Linear regression Linear regression is suitable when the dependent variable is metric. The independent variables in a linear regression can be either metric or categorical. However, if categorical independent variables are used, they must be appropriately coded, typically as dummy variables [2](#page=2). #### 1.2.2 Logistic regression Logistic regression is the preferred method when the dependent variable is categorical [2](#page=2). * **Binary logistic regression:** This is used when the dependent variable is nominal and represents two distinct groups (e.g., a dummy variable coded as 0 or 1) [2](#page=2). * **Multinomial logistic regression:** This is applied when the dependent variable has more than two categories. The course will focus on binary logistic regression, with multinomial logistic regression being beyond its scope [2](#page=2) [3](#page=3). Similar to linear regression, the independent variables in logistic regression can be metric or categorical, provided the categorical variables are encoded as dummy variables [3](#page=3). > **Tip:** Categorical variables must always be converted to dummy (binary: 1/0) variables for use in regression analyses [2](#page=2). #### 1.2.3 Variable types in regression | Analysis Technique | Dependent variable (Y) | Independent variable (X) | | :----------------- | :--------------------- | :----------------------- | | Linear regression | Metric | Metric or categorical* | | Logistic regression (Binary) | Nominal (2 groups) | Metric or categorical* | | Logistic regression (Multinomial) | Nominal (>2 groups) | Metric or categorical* | *Note: Categorical variables must be converted to dummy (binary: 1/0) variables [2](#page=2). ### 1.3 Analysis of Variance (ANOVA) Analysis of Variance (ANOVA) is another technique discussed, which also requires a metric dependent variable. The key distinction for ANOVA lies in its typical independent variable, which is usually categorical. ANOVA is frequently employed in experimental research, where the different experimental groups serve as the independent variable [4](#page=4). > **Tip:** Understanding the measurement level of your variables is paramount for selecting the correct analysis technique, especially in your own research such as a master's thesis [4](#page=4). #### 1.3.1 Variable types in ANOVA | Analysis Technique | Dependent variable (Y) | Independent variable (X) | | :----------------- | :--------------------- | :----------------------- | | ANOVA | Metric | Categorical | ### 1.4 General principle of variable measurement The type of dependent and independent variables is a primary determinant of which analysis techniques can be applied. It is often advantageous to measure variables in ways that result in metric data whenever possible, as this typically offers a wider range of analytical possibilities. Exercises are available to help clarify the relationship between variable measurement and analysis technique selection [4](#page=4). --- # Research example: Pizza restaurant customer satisfaction This section details a research study investigating factors influencing customer satisfaction in a pizza restaurant, defining its dependent, independent, and control variables, and outlining the measurement methodology using a questionnaire [6](#page=6) [9](#page=9). ### 2.1 Study objectives and factors The primary objective of this research is to determine the extent to which various factors influence overall customer satisfaction at a pizza restaurant. Based on discussions with employees, five specific factors were identified as potentially playing a significant role [6](#page=6): * Reception * Service * Waiting time * Food quality * Price It is hypothesized that increased satisfaction with each of these factors will contribute to higher overall satisfaction with the restaurant [6](#page=6). ### 2.2 Measurement of variables Customer satisfaction was measured using a questionnaire [7](#page=7). #### 2.2.1 Overall satisfaction Overall satisfaction with the pizza restaurant was measured using a 7-point Likert scale, where a higher score indicates greater satisfaction [7](#page=7). #### 2.2.2 Factor-specific satisfaction Satisfaction with each of the five identified factors (reception, service, waiting time, food quality, and price) was also assessed using the same 7-point Likert scale. The scale ranges from 1 (very dissatisfied) to 7 (very satisfied), with 4 representing a neutral position (neither dissatisfied nor satisfied) [7](#page=7). #### 2.2.3 Demographic variables In addition to satisfaction measures, demographic variables were collected. These included [8](#page=8): * **Gender:** Collected as a categorical variable (Man or Woman) [8](#page=8). * **Age:** Collected as a categorical variable, with respondents indicating their age range rather than their exact age. The categories were < 20, 20-35, 36-50, and > 50 [8](#page=8). A total of 107 customers completed the questionnaire, resulting in 107 observations for the study. The data is available in a STATA datafile named "Pizza\_incl\_dummies.dta" [8](#page=8). ### 2.3 Variable identification #### 2.3.1 Dependent variable The dependent variable is the primary outcome that the research aims to explain. In this study, the dependent variable is **overall customer satisfaction**, referred to as "satisfaction" in the dataset. Although Likert scale variables are technically categorical, they are often treated as metric variables due to their formulation [9](#page=9). #### 2.3.2 Independent variables Independent variables are those hypothesized to influence the dependent variable. In this research, the independent variables are the five factors being investigated for their effect on overall satisfaction [9](#page=9): * Reception * Service * Waiting time * Food quality * Price These variables were measured using 7-point Likert scales and are thus considered metric variables for analysis [9](#page=9). #### 2.3.3 Control variables Control variables are included in the model because they are known or suspected to influence the dependent variable, but the primary interest of the study is not in their specific effects. Including control variables helps to avoid omitted variable bias, which could distort the estimates of the independent variables' effects [9](#page=9). In this study, the control variables are: * Age * Gender Both age and gender are categorical variables [9](#page=9). > **Tip:** The distinction between independent and control variables is primarily conceptual. While theoretical hypotheses are typically formulated for independent variables, this is not usually the case for control variables. However, both types are entered as independent variables in the statistical analysis [10](#page=10). ### 2.4 Analytical approach Since the dependent variable (overall satisfaction) is metric, linear regression analysis is deemed appropriate for this study. As age and gender are categorical variables, they must first be encoded into dummy variables before being included as independent variables in the linear regression model [10](#page=10). --- # Dummy variable creation and usage in STATA This section details the process of transforming categorical variables into dummy (or indicator) variables within STATA for use in statistical analysis, covering manual creation, automatic generation, and the `i.` prefix. ### 3.1 Introduction to dummy variables Dummy variables, also known as indicator variables or 0/1 variables, are essential for representing categorical independent and control variables in regression analyses. These variables take a value of 1 if a specific category is present and 0 otherwise [11](#page=11). ### 3.2 The dummy variable trap A critical principle when creating dummy variables is to include one fewer dummy variable than the total number of categories in the original variable. Including a number of dummy variables equal to the number of categories leads to perfect multicollinearity, known as the "dummy variable trap". This occurs because one dummy variable can be perfectly predicted from the others, rendering the model unestimatable [11](#page=11) [12](#page=12). * **Rule:** Number of dummy variables = Number of categories - 1 [11](#page=11). ### 3.3 Creating dummy variables manually and with `tabulate, generate` STATA offers straightforward methods for creating dummy variables. #### 3.3.1 Manual recoding Categorical variables that are not already in a 0/1 format, such as a 'gender' variable coded as 1 for male and 2 for female, must be recoded. For a binary variable like gender, two dummy variables could conceptually be created: one for 'male' (1 if male, 0 otherwise) and one for 'female' (1 if female, 0 otherwise). However, as per the dummy variable trap rule, only one of these should be included in a regression model [11](#page=11). #### 3.3.2 Using the `tabulate, generate` command The `tabulate` command with the `generate` option provides an automated way to create dummy variables [13](#page=13). * **Functionality:** The `tabulate` command displays the frequencies of categories within a variable. When combined with the `generate` option, it automatically creates a new dummy variable for each category of the specified variable [13](#page=13). * **Example:** For a 'gender' variable with categories 'male' and 'female', `tabulate gender, generate` will create two new variables, typically named `gender1` and `gender2`. `gender1` will be 1 if the respondent is male and 0 otherwise, while `gender2` will be 1 if the respondent is female and 0 otherwise [14](#page=14). * **Example with multiple categories:** If the 'age' variable has four categories, using `tabulate age, generate` will create four dummy variables: `age1`, `age2`, `age3`, and `age4` [15](#page=15). > **Tip:** While `tabulate, generate` is convenient, remember that you will typically need to exclude one of the generated dummy variables from your regression model to avoid the dummy variable trap. ### 3.4 Using the `i.` prefix in STATA STATA provides a more integrated approach to handle categorical variables without explicit dummy variable creation in the dataset using the `i.` prefix [16](#page=16). * **Functionality:** By preceding a variable name with `i.` (e.g., `i.age` or `i.gender`) in almost any STATA command, you instruct STATA to treat that variable as categorical. STATA will then automatically generate and include the correct number of dummy variables in the analysis, inherently handling the dummy variable trap by omitting one category as a reference group [16](#page=16). * **Advantages:** This method simplifies the process as it removes the need to manually create and manage dummy variables in the data editor, streamlining the analysis workflow. > **Tip:** Using the `i.` prefix is generally the preferred method for incorporating categorical variables in STATA regressions, as it is less prone to user error regarding the dummy variable trap. --- # Linear regression assumptions and testing Performing a linear regression analysis requires several key assumptions to be met for the results to be valid and interpretable. This section outlines these nine assumptions, their importance, and methods for testing them [20](#page=20). ### 4.1 The nine assumptions of linear regression The following assumptions are crucial for a robust linear regression analysis [20](#page=20): 1. **Causality:** The independent variables (and control variables) must influence the dependent variable, not the other way around [21](#page=21). 2. **Inclusion of all relevant variables:** All important variables that could affect the dependent variable must be included in the model to avoid omitted variable bias [22](#page=22). 3. **Metric dependent variable:** The dependent variable must be measured on a metric scale [24](#page=24). 4. **Linear relationship:** There should be a linear relationship between each independent variable and the dependent variable [25](#page=25). 5. **Additive relationship:** The relationship between the dependent and independent variables should be additive, meaning the predicted dependent variable is the sum of the weighted independent variables [26](#page=26). 6. **Residual properties:** Residuals must be independent, normally distributed, homoscedastic (constant variance), and without autocorrelation [29](#page=29). 7. **Sufficient observations:** An adequate number of observations must be available relative to the number of estimated parameters [44](#page=44). 8. **No multicollinearity:** There should be no perfect or high linear relationship between independent variables [45](#page=45). 9. **No extreme values:** The dataset should not contain extreme observations or outliers that unduly influence parameter estimates [49](#page=49). ### 4.2 Detailed examination and testing of assumptions #### 4.2.1 Causality The causality assumption posits that independent variables directly influence the dependent variable. This is challenging to prove, especially when data is collected simultaneously for all variables, as reverse causality or consistency bias (respondents aligning answers to appear consistent) may occur. In practice, this assumption is often made based on theoretical grounds or the experimental design of data collection [21](#page=21). #### 4.2.2 Inclusion of all relevant variables Omitted variable bias occurs when crucial independent variables are excluded from the model, potentially leading to biased parameter estimates. While difficult to test directly, systematic patterns in residual plots can indicate the presence of omitted variables. The `rvfplot` command in STATA can be used to visualize these patterns [22](#page=22) [23](#page=23). > **Tip:** Rely on intuition, existing theory, and academic literature to identify potentially relevant variables to include in the model [22](#page=22). #### 4.2.3 Metric dependent variable This assumption requires the dependent variable to be measured on a continuous or interval scale. Likert scales, often treated as metric in practice, satisfy this assumption if the context allows for such an interpretation [24](#page=24). #### 4.2.4 Linear relationship Linear regression models assume a linear association between each independent variable and the dependent variable. Scatter plots can be used to visually inspect these relationships [25](#page=25). #### 4.2.5 Additive relationship The model assumes that the effects of independent variables on the dependent variable are additive. This means the overall predicted outcome is the sum of the weighted contributions of each independent variable, rather than multiplicative interactions, unless interaction terms are explicitly included [26](#page=26). #### 4.2.6 Residual properties This is a composite assumption encompassing four key aspects of the residual terms [29](#page=29): ##### 4.2.6.1 Independence of residuals Residuals should be independent of each other. This is typically met when observations are collected independently. Autocorrelation can be an issue, particularly in time-series data or with clustered cross-sectional data [29](#page=29) [40](#page=40). ##### 4.2.6.2 Normality of residuals Residuals are expected to follow a normal distribution. This can be tested graphically using histograms and kernel density plots, and statistically using tests like the Shapiro-Wilk test and skewness/kurtosis tests [30](#page=30) [31](#page=31). * **Testing in STATA:** 1. Store residuals: `predict res` 2. Visualize distribution: `histogram res` or `kdensity res, normal` 3. Statistical tests: `sktest res` [30](#page=30) [31](#page=31). * **Remedies for non-normality:** * Investigate and fix underlying model problems (e.g., omitted variables, wrong functional form) [32](#page=32). * Transform the dependent variable (e.g., logarithm, square root) to achieve a more normal distribution, keeping in mind this alters interpretation [32](#page=32). * For large sample sizes, violations of normality are often less critical as parameters and standard errors are less affected [33](#page=33). ##### 4.2.6.3 Homoscedasticity (constant variance of residuals) The variance of the residuals should be constant across all levels of the independent variables. Heteroscedasticity occurs when this variance changes, often appearing as a "fanned-out" pattern in residual plots [34](#page=34) [35](#page=35). * **Testing for heteroscedasticity:** * Graphical inspection using `rvfplot` for patterns in residual spread [36](#page=36). * Statistical tests such as the Breusch-Pagan and White tests. The null hypothesis for these tests is homoscedasticity [37](#page=37). * **Remedies for heteroscedasticity:** * Identify and correct underlying model issues (e.g., omitted variables, wrong functional form) [38](#page=38). * Transform the dependent variable, but be mindful of interpretation changes [38](#page=38). * Use robust standard errors, which can account for heteroscedasticity even in small samples [38](#page=38). ##### 4.2.6.4 Absence of autocorrelation Autocorrelation refers to the correlation between residual terms, typically observed in time-series data where observations from one period are correlated with those from previous periods. It can also occur in cross-sectional data with clustered observations [39](#page=39) [40](#page=40). #### 4.2.7 Sufficient observations A general guideline suggests having at least 20 observations per estimated parameter, though a minimum of 5 might suffice in some cases. A larger sample size, such as hundreds or thousands of observations, generally strengthens the reliability of the regression results [33](#page=33) [44](#page=44) [53](#page=53). #### 4.2.8 No multicollinearity Multicollinearity arises when independent variables are highly correlated with each other [44](#page=44). * **Perfect multicollinearity:** Occurs when one independent variable can be perfectly predicted by a linear combination of others. STATA automatically handles this by removing one of the perfectly correlated variables [45](#page=45). * **Imperfect multicollinearity:** Occurs when there is a high, but not perfect, correlation between an independent variable and a combination of others. This doesn't prevent estimation but inflates standard errors, reducing parameter estimate precision [45](#page=45). * **Testing for multicollinearity:** * **Pairwise correlation coefficients:** Examine correlations between all pairs of independent variables; values above 0.8 (or sometimes 0.6-0.7) may indicate a problem [46](#page=46). * **Variance Inflation Factors (VIFs):** For each independent variable, VIF measures how well other independent variables explain it. VIFs above 10 are considered severe, while values between 5 and 10 indicate substantial multicollinearity. Tolerance (1/VIF) below 0.10 (or 0.5) also signals multicollinearity [47](#page=47). * **Remedies for multicollinearity:** * Remove one of the highly correlated independent variables [48](#page=48). * Merge correlated variables (e.g., by calculating an average score if conceptually meaningful) [48](#page=48). * Utilize factor scores from a factor analysis if appropriate [48](#page=48). #### 4.2.9 No extreme values (outliers) Extreme observations, or outliers, are data points that disproportionately influence parameter estimates [49](#page=49). * **Detection methods:** * **Graphical inspection:** The `rvfplot` can reveal observations that deviate significantly from the main cluster of data [50](#page=50). * **Dfbeta:** This statistic measures how much a parameter estimate changes when a specific observation is excluded. Values with an absolute value greater than 1 are often considered influential [51](#page=51). * **Studentized residuals:** These indicate how much a residual term deviates from others. Observations with studentized residuals less than -3 or greater than 3 are flagged as potential outliers [52](#page=52). * **Handling extreme values:** * Investigate the cause of the outlier; if it's a data entry error, it should be corrected or removed. If it's a genuine but extreme measurement, careful consideration and transparent reporting are crucial [53](#page=53). * The impact of outliers is more problematic in small samples. In large samples, their influence is typically diminished [53](#page=53). * Ideally, the regression results should not change drastically if outliers are removed, indicating robustness [53](#page=53). --- # Interpreting linear regression results This section details how to interpret the output of a linear regression analysis, focusing on model fit and the significance and magnitude of independent variable coefficients. ### 5.1 Overview of the interpretation process The interpretation of linear regression results involves a three-step process: first, checking assumptions; second, assessing the overall meaningfulness or "model fit"; and third, interpreting the coefficients of individual independent variables. This guide focuses on steps two and three, assuming assumptions have been met or corrected. The analysis for this section is based on a dataset with 105 observations after excluding two outliers [60](#page=60) [61](#page=61) [65](#page=65). ### 5.2 Checking model meaningfulness (model fit) To determine if the estimated model as a whole is meaningful and explains a substantial portion of the variance in the dependent variable, two key metrics are examined: the F-statistic and R-squared. #### 5.2.1 F-statistic The F-statistic tests the null hypothesis that all regression coefficients (parameters of all independent variables) are not significantly different from zero ($H_0: b_1 = b_2 = \dots = 0$) [62](#page=62). * **Interpretation:** If the p-value associated with the F-statistic is less than 0.05, the null hypothesis is rejected. This indicates that at least one independent variable has a significant influence on the dependent variable, meaning the model is statistically significant [62](#page=62). #### 5.2.2 R-squared ($R^2$) R-squared represents the proportion of the variance in the dependent variable (Y) that is explained by the model. It ranges from 0 to 1, where 0 indicates no variance explained and 1 indicates 100% of the variance explained [63](#page=63). * **Interpretation:** A higher R-squared value indicates a better fit of the model to the data. For instance, an $R^2$ of 0.7556 means that 75.56% of the variance in overall satisfaction is explained by the model [63](#page=63). * **Disadvantage:** R-squared tends to increase (or stay the same) when additional independent variables are added, regardless of their actual contribution. This can lead to overly complex models that violate the KISS (Keep It Simple, Stupid) principle [63](#page=63). #### 5.2.3 Adjusted R-squared (Adj. $R^2$) Adjusted R-squared is a modified version of R-squared that penalizes the addition of unnecessary independent variables, making it useful for comparing models with different numbers of predictors [63](#page=63) [64](#page=64). * **Interpretation:** It is used to compare models: if including a variable increases adjusted R-squared, it suggests the variable adds substantial explanatory power beyond its complexity. If adjusted R-squared decreases, the variable's contribution does not compensate for the added complexity. The adjusted R-squared of a single model cannot be interpreted in isolation [64](#page=64). > **Tip:** The F-statistic and R-squared are crucial for assessing the overall meaningfulness of the model. A significant F-statistic and a sufficiently high R-squared indicate that the model is a good fit and can proceed to coefficient interpretation [65](#page=65). ### 5.3 Interpreting coefficients of independent variables After establishing the model's meaningfulness, the next step is to interpret the coefficients of each independent variable. This involves assessing their statistical significance and their practical meaning. #### 5.3.1 T-statistics and p-values The t-statistic and its associated p-value are used to test the null hypothesis that an individual coefficient is not significantly different from zero ($H_0: b_i = 0$) [66](#page=66). * **Interpretation:** * If the p-value is less than 0.05, the null hypothesis is rejected. This means the independent variable has a statistically significant effect on the dependent variable, and its estimated coefficient is significantly different from zero [66](#page=66). * If the p-value is higher than 0.05, the null hypothesis cannot be rejected. This indicates that the estimated coefficient does not differ significantly from zero, and the independent variable has no statistically significant effect on the dependent variable [66](#page=66). > **Example:** If a p-value for "waiting time" is greater than 0.05, its coefficient should not be interpreted as having a real effect, as it's not significantly different from zero [67](#page=67). #### 5.3.2 Ceteris Paribus interpretation For independent variables with statistically significant coefficients, their estimated coefficients can be interpreted under the "ceteris paribus" assumption [68](#page=68). * **Interpretation:** Ceteris paribus means "all other things being equal." If the independent variable (X) increases by one unit, the dependent variable (Y) increases by the value of its coefficient ($b_i$), assuming all other independent variables in the model remain constant [68](#page=68) [69](#page=69). > **Example:** If the coefficient for "reception" is 0.176 and is significant, it means that a one-unit increase in satisfaction with reception leads to a 0.176 increase in overall satisfaction, assuming other factors do not change [69](#page=69). #### 5.3.3 Interpretation of dummy variables Dummy variables are used to represent categorical independent variables. Their interpretation is always made in relation to a reference or base category, for which no dummy variable is included in the model [70](#page=70). * **Interpretation:** The coefficient of a dummy variable indicates the difference in the dependent variable between that category and the reference category, holding other variables constant [71](#page=71). > **Example:** If "male" is a dummy variable with a coefficient of -0.393 and "women" is the reference category, it means that overall satisfaction for men is 0.393 lower than for women, ceteris paribus [71](#page=71). > **Example:** When interpreting age categories, if "older than 50" is the reference category, a coefficient of 1.198 for the "less than 20" dummy variable means that respondents younger than 20 have 1.198 higher overall satisfaction compared to those over 50, ceteris paribus [72](#page=72). > **Tip:** To compare the satisfaction levels between different subgroups (e.g., comparing different age groups directly), you may need to change the reference category in your model [73](#page=73). #### 5.3.4 Interpretation with transformed variables If dependent or independent variables have been transformed (e.g., using logarithms), the interpretation of coefficients must reflect this transformation. For example, if $\log(Y)$ was used, coefficients are interpreted in relation to $\log(Y)$, not $Y$ [70](#page=70). #### 5.3.5 Beta coefficients (standardized coefficients) Beta coefficients (standardized coefficients) are obtained by standardizing the independent variables before running the regression (subtracting the mean and dividing by the standard deviation) [75](#page=75). * **Purpose:** Beta values are used to compare the relative strength or importance of different independent variables in their impact on the dependent variable, as they are unit-independent [75](#page=75). * **Interpretation:** The independent variable with the largest absolute beta coefficient has the strongest impact on the dependent variable, while the one with the smallest absolute beta coefficient has the weakest impact [75](#page=75). > **Example:** If the beta value for "age" is the highest among all independent variables, it indicates that age has the strongest effect on overall satisfaction. Similarly, if "service" has a higher beta than "reception," service has a greater impact [75](#page=75). --- # Model comparison for non-linear relationships This section details how to test for non-linear relationships, specifically quadratic ones, by comparing a linear model to one that includes a squared term, using statistical tests to assess significant model improvement [78](#page=78). ### 6.1 The rationale for testing non-linear relationships Theoretical considerations can suggest that the relationship between dependent and independent variables is not strictly linear. For instance, the relationship between purchase intention and price might be quadratic. This means that at very low prices, purchase intention could be low due to a lack of perceived quality or trust. As the price increases, purchase intention may rise up to a certain point (a peak). Beyond this peak, if the price continues to rise, purchase intention might decrease as the product becomes perceived as too expensive [78](#page=78). ### 6.2 Model comparison approach To test for such non-linear, specifically quadratic, relationships, a model comparison method is employed. This approach systematically compares two models: a "restricted model" and a "full model" [79](#page=79). #### 6.2.1 Restricted versus full model * **Restricted model:** This is a simpler model where one or more parameters are constrained to be zero. In the context of testing for a quadratic relationship, the restricted model would be a linear model that does not include the squared term of the independent variable [79](#page=79). * **Full model:** This is a more complex model that includes all the parameters of interest, including those potentially constrained in the restricted model. For a quadratic relationship test, the full model would include both the linear and the squared term of the independent variable [79](#page=79). #### 6.2.2 Steps in model comparison The model comparison process involves several key steps: **Step 1: Create new variables** First, create a new variable that represents the non-linear term. In the example of a quadratic relationship with price, this involves calculating "price squared" [79](#page=79) [80](#page=80). **Step 2: Run linear regression models** Perform two separate linear regression analyses: * One regression for the restricted model (without the quadratic term) [80](#page=80). * Another regression for the full model (with the quadratic term) [80](#page=80). > **Tip:** It is crucial to verify that all assumptions of linear regression are met for both models [81](#page=81). #### 6.2.3 Addressing multicollinearity A common issue that arises when adding squared terms is multicollinearity, where the independent variables are highly correlated. The "price" and "price squared" variables, for instance, will inherently have a strong linear relationship. High variance inflation factors (VIFs) are indicators of this problem [81](#page=81). **Solution: Standardization** A common technique to mitigate multicollinearity is to standardize the variables. This involves transforming the original variables into z-scores [82](#page=82). * Calculate the standardized price variable ($z_{\text{price}}$) [82](#page=82). * Then, calculate the square of this standardized price ($z_{\text{price}}^2$) [82](#page=82). * Finally, run the linear regression models using these standardized variables ($z_{\text{price}}$ and $z_{\text{price}}^2$). This standardization often reduces VIFs to acceptable levels (e.g., below 10) [82](#page=82) [83](#page=83). > **Tip:** While standardization helps with multicollinearity, it's still essential to check other regression assumptions for both the restricted and full models [83](#page=83). **Step 3: Assess significant improvement in model fit** The final step is to determine if adding the non-linear term (the squared variable) significantly improves the overall fit of the model [84](#page=84). * **Using F-statistics and p-values:** This is typically done by examining changes in the F-statistic and its associated p-value. A significant improvement in model fit indicates that the non-linear term contributes meaningfully to explaining the dependent variable [84](#page=84). * **Software implementation:** Commands like `nestreg` in statistical software (e.g., Stata) can perform incremental F-tests, showing the change in the F-statistic when a new variable is added to the model. The significance of this change is assessed by the p-value [84](#page=84). > **Procedure to determine whether there is a nonlinear effect:** > If the p-value for the change in the F-statistic is greater than 0.05, there is no significant improvement, and the relationship can be considered linear. If the p-value is less than 0.05, the improvement is significant, suggesting a non-linear relationship [84](#page=84). **Interpreting the results:** * The focus is on the last row of the `nestreg` output, which indicates the change in the F-statistic upon adding the squared term ($z_{\text{price}}^2$) [84](#page=84). * If the change in the F-statistic is small and its p-value is greater than 0.05, adding the squared term is not a significant improvement. This leads to the conclusion that the relationship between the independent and dependent variables is linear [84](#page=84). * The change in $R^2$ also provides insight; a very low change when adding the squared term further supports the conclusion of no significant non-linear effect [84](#page=84). * Additionally, the coefficient table for the full model can be examined. If the p-value for the t-test of the coefficient of the squared term is greater than 0.05, it indicates that the effect of the squared term is not statistically significant [85](#page=85). > **Example:** If, after adding $z_{\text{price}}^2$ to a model, the change in the F-statistic is 0.07 and its p-value is greater than 0.05, then the addition of $z_{\text{price}}^2$ does not significantly improve the model fit, and the relationship is concluded to be linear. Similarly, if the p-value for the $z_{\text{price}}^2$ coefficient in the full model is, for instance, 0.25 (which is > 0.05), then there is no significant indication of a quadratic relationship [84](#page=84) [85](#page=85). --- ## Common mistakes to avoid - Review all topics thoroughly before exams - Pay attention to formulas and key definitions - Practice with examples provided in each section - Don't memorize without understanding the underlying concepts

| Term | Definition | |------|------------| | Metric variables | Variables that represent quantities or numbers that can be used in calculations, such as height, weight, or temperature. | | Categorical variables | Variables that represent groups or categories, such as gender (male/female) or educational attainment (high school, bachelor's, master's). | | Linear regression | A statistical method used to model the relationship between a dependent variable and one or more independent variables, assuming a linear relationship. | | Logistic regression | A statistical method used to model the probability of a binary outcome (e.g., yes/no, success/failure) based on one or more predictor variables. | | Dependent variable | The variable that is being predicted or explained in a statistical model; its value is assumed to depend on the independent variables. | | Independent variable | A variable that is manipulated or measured to observe its effect on the dependent variable; it is used to explain or predict the dependent variable. | | Dummy variable | A binary variable (coded as 0 or 1) used to represent a categorical variable in a regression analysis. Each category of the original variable, except for a reference category, is represented by a separate dummy variable. | | Binary logistic regression | A type of logistic regression used when the dependent variable has only two possible outcomes. | | Multinomial logistic regression | A type of logistic regression used when the dependent variable has more than two possible outcomes that are not ordered. | | Analysis of Variance (ANOVA) | A statistical technique used to compare the means of two or more groups by analyzing the variance within and between groups. | | Likert scale | A psychometric scale commonly used in questionnaires to measure attitudes or opinions. Respondents indicate their level of agreement or disagreement on a scale, typically with a neutral midpoint. | | Control variables | Variables included in a statistical model to account for their potential influence on the dependent variable, even if they are not the primary focus of the research. They help to isolate the effect of the independent variables and avoid omitted variable bias. | | Omitted variable bias | A bias in the estimated coefficients of a regression model that occurs when a relevant variable that influences both an included independent variable and the dependent variable is not included in the model. | | Dummy variable trap | A situation in regression analysis that occurs when a complete set of dummy variables representing a categorical variable is included in the model along with the intercept. This leads to perfect multicollinearity because one dummy variable can be perfectly predicted from the others and the intercept. | | Multicollinearity | A phenomenon in regression analysis where two or more independent variables are highly correlated with each other, making it difficult to determine the independent effect of each variable on the dependent variable. | | Variance Inflation Factor (VIF) | A measure used to detect the degree of multicollinearity in a regression analysis. A high VIF indicates that the variable is highly correlated with other independent variables in the model. | | Residuals | The differences between the observed values of the dependent variable and the values predicted by the regression model. They represent the unexplained variation in the model. | | Homoscedasticity | A statistical assumption in regression analysis where the variance of the residuals is constant across all levels of the independent variables. | | Heteroscedasticity | The opposite of homoscedasticity, where the variance of the residuals is not constant across all levels of the independent variables, often appearing as a fanning-out pattern in residual plots. | | Autocorrelation | A correlation between observations in a time series or clustered data, where an observation at one point in time or in one cluster is correlated with observations at other points in time or in the same cluster. | | Outliers | Observations that are significantly different from other observations in the dataset and can disproportionately influence the results of a statistical analysis. | | Studentized residuals | A type of residual that is standardized by dividing by an estimate of its standard deviation, making it easier to identify potential outliers. | | Dfbeta | A diagnostic statistic in regression analysis that measures the influence of a single observation on the estimated coefficients of the model. | | Model fit | An overall assessment of how well a statistical model represents the data, typically evaluated using metrics like R-squared and the F-statistic. | | R-squared ($R^2$) | A statistical measure that represents the proportion of the variance in the dependent variable that is predictable from the independent variable(s). | | Adjusted R-squared | A modified version of R-squared that adjusts for the number of predictors in the model, providing a more accurate measure of model fit when comparing models with different numbers of independent variables. | | Ceteris paribus | A Latin phrase meaning "other things being equal." In regression analysis, it refers to interpreting the effect of one variable while holding all other variables constant. | | Standardization | The process of transforming variables so that they have a mean of 0 and a standard deviation of 1. This is often done to compare coefficients of variables measured on different scales. | | Quadratic term | A term in a regression model that represents the square of an independent variable, used to model a non-linear (curved) relationship. | | Restricted model | In model comparison, the simpler model that has fewer parameters or constraints, often used as a baseline against which a more complex model is compared. | | Full model | In model comparison, the more complex model that includes additional parameters or terms compared to the restricted model. | | Nestreg command | A STATA command used to perform incremental F-tests for nested models, assessing whether adding a set of variables significantly improves the model's explanatory power. |

# Understanding supply chain definitions and components This topic introduces the fundamental definition of a supply chain, its constituent components, and the intricate flows of materials and information within it, along with models used for describing and managing these processes [4](#page=4). ### 1.1 Defining a supply chain A supply chain encompasses the relationships and flows between a series of operations and processes that collectively deliver value in the form of products and services to the final consumer [4](#page=4). > **Tip:** Think of a supply chain as an extended enterprise, a network of organizations, people, activities, information, and resources involved in moving a product or service from supplier to customer [4](#page=4). ### 1.2 Terminology and flow within a supply chain * **Bidirectional Flow:** Materials and information flow in both directions within a supply chain [5](#page=5). * **Key Terminology:** * **Tiers:** Different levels of suppliers (e.g., Tier 1, Tier 2) [5](#page=5). * **Supply Side:** The side of the chain that provides the product or service [5](#page=5). * **Demand Side:** The side of the chain that consumes the product or service [5](#page=5). * **Upstream:** Refers to the direction towards the origin of the materials or components [5](#page=5). * **Downstream:** Refers to the direction towards the end consumer [5](#page=5). > **Example:** In a bicycle supply chain, the upstream components might include raw material suppliers for metal and rubber, while downstream would be the retail stores selling bicycles to consumers [7](#page=7). ### 1.3 Models for describing supply chain processes #### 1.3.1 The SIPOC model The SIPOC (Suppliers, Inputs, Process, Outputs, Customers) model is a tool used to describe the logistics supply chain by outlining its key elements. It visually represents the flow of information and materials from suppliers through internal processes to customers [8](#page=8). #### 1.3.2 The SCOR model The Supply Chain Operations Reference (SCOR) model is a standardized framework designed to describe, measure, and improve supply chain processes [11](#page=11) [9](#page=9). * **Purpose:** It helps in creating and managing supply chains by linking operational building blocks within and between companies. The management of processes across the entire chain is crucial for efficiency [10](#page=10) [9](#page=9). * **Focus Areas:** The SCOR model traditionally has four key focus areas: * Process [11](#page=11). * Performance [11](#page=11). * People [11](#page=11). * Best Practices [11](#page=11). * **Operational Scope:** * The standard SCOR model includes six primary management processes: Plan, Source, Make, Deliver, Return, and Enable [12](#page=12). * The SCOR digital standard expands on this, including Order and Transform in place of Make [12](#page=12). ### 1.4 Orchestrating the supply chain: synchronizing demand and supply Effective supply chain management involves synchronizing demand and supply across all phases of satisfying customer needs. This synchronization is supported by models like SCOR [12](#page=12). ### 1.5 Supply chain performance objectives Supply chains compete and are measured against several key performance objectives: * Quality [13](#page=13). * Speed [13](#page=13). * Dependability [13](#page=13). * Flexibility [13](#page=13). * Cost [13](#page=13). * Sustainability [13](#page=13). --- # Lean versus agile supply networks This section distinguishes between lean and agile supply networks and explores the risks associated with a mismatch in network strategy. ### 2.1 Understanding supply chain networks A supply chain network refers to the interconnected system of organizations, people, activities, information, and resources involved in moving a product or service from supplier to customer. Understanding the different types of supply chain networks is crucial for effective operations management [3](#page=3). ### 2.2 Differentiating lean and agile supply networks The core distinction between lean and agile supply networks lies in their primary objectives and how they respond to market demands [3](#page=3). #### 2.2.1 Lean supply networks Lean supply networks are designed to eliminate waste and minimize costs by ensuring a smooth and efficient flow of goods. Their focus is on predictability and efficiency, aiming to deliver products at the lowest possible cost through optimized processes and reduced inventory [3](#page=3). > **Tip:** Lean principles are best suited for stable demand environments where product variety is low and predictability is high. #### 2.2.2 Agile supply networks Agile supply networks, conversely, are built to respond rapidly and flexibly to unpredictable market changes and customer demands. Their strength lies in their ability to adapt quickly to shifts in demand, product variety, and customization requirements [3](#page=3). > **Tip:** Agile networks excel in volatile markets with high product differentiation and fluctuating customer needs. #### 2.2.3 Risks of mismatch in network strategy A significant risk in supply chain management arises from a mismatch between the chosen network strategy (lean or agile) and the actual market conditions or product characteristics. Implementing a lean strategy in a highly volatile market, or an agile strategy in a predictable, cost-sensitive market, can lead to inefficiencies and increased risks [14](#page=14). * **Lean strategy in a volatile market:** May result in stockouts, lost sales, and an inability to meet changing customer preferences due to rigid processes and low inventory [14](#page=14). * **Agile strategy in a stable market:** Can lead to higher operational costs due to excess capacity, frequent small batches, and complex coordination, failing to achieve the cost efficiencies that a lean approach would offer [14](#page=14). Effectively aligning the supply network's capabilities with market demands is therefore a critical strategic decision [14](#page=14). --- # Supplier relationships and sourcing strategies This topic explores the intricacies of managing relationships with suppliers and the strategic approaches to sourcing goods and services. ### 3.1 Understanding supplier networks and partnerships Supplier networks focus on the entities involved in supplying a business and the nature of the relationships established with them. This is distinct from supply chain networks, which are concerned with the infrastructure setup. Within these networks, various forms of partnerships can be developed with suppliers [15](#page=15) [16](#page=16). ### 3.2 Sourcing strategies Sourcing strategies determine how an organization obtains the goods and services it needs. There are four key approaches to sourcing [17](#page=17): * **Inbound logistics:** This strategy focuses on the processes and relationships involved in receiving and managing raw materials, components, and finished goods from suppliers [17](#page=17). * **Operations:** This approach deals with sourcing strategies related to the transformation of inputs into outputs within the organization [17](#page=17). * **Outbound logistics:** This strategy concerns the sourcing of services and processes related to distributing finished goods to customers [17](#page=17). * **Aftermarket:** This strategy involves sourcing services and parts related to the support and maintenance of products after they have been sold to customers [17](#page=17). ### 3.3 Strategic sourcing using the Kraljic matrix Strategic sourcing involves analyzing sourcing categories, rather than individual suppliers, to develop appropriate strategies. The Kraljic matrix, referred to in the document as "supply risk vs. criticality to business," is a tool used for this purpose. It classifies sourcing items based on two dimensions [18](#page=18): * **Supply risk:** This refers to the potential for disruption in the supply of an item, including factors like scarcity, supplier dependency, and logistical challenges [18](#page=18). * **Business criticality:** This dimension assesses the impact of an item on the organization's profitability and its ability to operate effectively [18](#page=18). The matrix typically results in four categories, each requiring a distinct sourcing strategy: * **Non-critical items:** Low supply risk, low business criticality. These items are often standardized and readily available. The strategy is typically to simplify and automate the purchasing process, often through e-procurement [18](#page=18). * **Leverage items:** Low supply risk, high business criticality. These items offer significant spending power. The strategy is to exploit purchasing power through competitive bidding and negotiate favorable terms [18](#page=18). * **Bottleneck items:** High supply risk, low business criticality. These items are important for operations but do not represent a large portion of spending. The strategy is to ensure supply security by securing contracts and potentially holding buffer stock [18](#page=18). * **Strategic items:** High supply risk, high business criticality. These items are crucial for the business and face significant supply challenges. The strategy is to build long-term partnerships and collaboration with suppliers to ensure supply and foster innovation [18](#page=18). > **Tip:** Understanding the Kraljic matrix is fundamental for aligning sourcing efforts with overall business objectives and managing supply chain risks effectively. ### 3.4 Supplier selection and management The supplier selection process is a critical component of the broader sourcing process, which typically begins with defining demand specifications, followed by an overview of the supply market, the development of a sourcing strategy, and then the actual supplier selection. The final step in the sourcing process is contracting the supplier [19](#page=19). Procurement encompasses both sourcing and purchasing. The purchasing process follows sourcing and includes activities such as [19](#page=19): * Phasing in new suppliers [19](#page=19). * Ordering and receiving deliveries [19](#page=19). * Measuring supplier performance [19](#page=19). * Improving or developing a supplier's capabilities [19](#page=19). * Phasing out suppliers when necessary [19](#page=19). Managing suppliers involves identifying and addressing gaps in the supply side of the business. Similarly, managing customers involves identifying and addressing gaps on the demand side [20](#page=20) [21](#page=21). > **Example:** A manufacturing company identifies that a critical component has a high supply risk due to limited suppliers and is highly critical to their final product's functionality. Using the Kraljic matrix, this component would fall into the "Strategic items" quadrant, necessitating a close, collaborative partnership with the supplier to ensure consistent supply and explore joint development opportunities. --- # Supply chain dynamics and the bullwhip effect This topic explores the dynamic behavior within supply chains, specifically focusing on the amplification of demand variability known as the bullwhip effect [22](#page=22). ### 7.1 Understanding supply chain dynamics Supply chain dynamics refers to the study of how demand and order information changes as it moves through a supply chain. In an ideal scenario, demand at each stage of the supply chain would mirror the actual end-customer demand. However, in reality, variations in demand tend to amplify as they propagate upstream from the retailer to the manufacturer and then to the raw material supplier. This amplification is often described as the bullwhip effect [22](#page=22) [23](#page=23). ### 7.2 The bullwhip effect The bullwhip effect is a phenomenon in supply chain management where demand variability increases as one moves upstream in the supply chain from the customer to the supplier. This means that small fluctuations in customer demand can lead to much larger fluctuations in orders placed by retailers to wholesalers, by wholesalers to distributors, and by distributors to manufacturers [22](#page=22) [23](#page=23). **Causes of the bullwhip effect:** * **Demand forecast updating:** Each member of the supply chain forecasts demand based on the orders they receive from their downstream partner, not on the actual end-customer demand. When demand increases, each stage forecasts a further increase, leading to over-ordering. Conversely, when demand decreases, they forecast further decreases, leading to under-ordering [23](#page=23). * **Order batching:** Companies often order in batches to reduce ordering costs or take advantage of discounts. This can create artificial demand spikes and troughs that do not reflect actual customer demand. For example, a retailer might order a month's supply at once, creating a large order that then gets batched with previous orders by the distributor for forecasting purposes [23](#page=23). * **Price fluctuations:** Promotions and discounts can lead customers to buy more than they immediately need, creating "forward buying." This distorts the true demand pattern and leads to an amplified demand signal upstream [23](#page=23). * **Rationing and shortage gaming:** When a supplier faces a shortage, they may ration products to their customers based on past orders. Customers, anticipating future shortages, may inflate their orders to secure a larger allocation, further distorting demand signals [23](#page=23). **Consequences of the bullwhip effect:** The bullwhip effect leads to several negative outcomes for supply chains: * **Excess inventory:** Over-ordering due to inflated forecasts can result in excessive inventory levels at various stages of the supply chain, leading to increased holding costs, obsolescence, and waste [23](#page=23). * **Stockouts:** Conversely, under-ordering or misinterpreting demand can lead to stockouts, resulting in lost sales, customer dissatisfaction, and damage to the company's reputation [23](#page=23). * **Inefficient production:** Fluctuating order sizes make production scheduling difficult, leading to inefficient use of capacity, higher manufacturing costs, and increased lead times [23](#page=23). * **Increased transportation costs:** Batching orders and dealing with unpredictable demand can lead to less efficient transportation planning and higher costs [23](#page=23). > **Tip:** The bullwhip effect is a fundamental concept in supply chain management that highlights the importance of information sharing and demand signal accuracy throughout the chain. ### 7.3 Mitigating the bullwhip effect Several strategies can be employed to mitigate the bullwhip effect: * **Information sharing:** Sharing actual point-of-sale (POS) data across the supply chain allows all partners to base their decisions on real customer demand rather than on distorted order signals [23](#page=23). * **Reducing lead times:** Shorter lead times reduce the need for long-term forecasts, making them more accurate and less susceptible to amplification [23](#page=23). * **Stabilizing prices:** Implementing everyday low pricing (EDLP) strategies rather than frequent promotions can reduce forward buying and smooth out demand [23](#page=23). * **Eliminating order batching:** Encouraging smaller, more frequent orders can lead to a smoother flow of goods and information [23](#page=23). * **Vendor-managed inventory (VMI):** In a VMI system, the supplier takes responsibility for managing the customer's inventory, using actual POS data to replenish stock. This aligns the supplier's incentives with the customer's actual needs [23](#page=23). --- ## Common mistakes to avoid - Review all topics thoroughly before exams - Pay attention to formulas and key definitions - Practice with examples provided in each section - Don't memorize without understanding the underlying concepts

| Term | Definition | |------|------------| | Supply Chain | The network of organizations, people, activities, information, and resources involved in moving a product or service from supplier to customer. | | Lean Network | A supply network designed for efficiency and minimal waste, typically characterized by low inventory and fast throughput. | | Agile Network | A supply network designed for responsiveness and flexibility, capable of adapting quickly to changes in demand or market conditions. | | Supplier Network | Focuses on the relationships and connections between an organization and its direct suppliers, detailing who provides what and the nature of those interactions. | | Supply Chain Network | Refers to the overall infrastructure and setup of how materials and products flow from origin to consumption across multiple entities. | | Partnership (in supply chains) | A close, collaborative relationship between two or more organizations in a supply chain, built on trust and mutual benefit to achieve shared goals. | | Sourcing Approaches | The distinct strategies or methods employed by an organization to acquire goods and services from external providers. | | Kraljic Matrix | A strategic tool used to categorize purchased items or suppliers based on their supply risk and impact on business profitability, guiding sourcing strategies. | | Supplier Selection | The process of identifying, evaluating, and choosing the most suitable suppliers based on predefined criteria to meet an organization's needs. | | Procurement | The comprehensive process of acquiring goods or services, which includes sourcing strategies, supplier selection, purchasing, and supplier relationship management. | | Purchasing | The operational process of buying goods or services, typically following the strategic sourcing and supplier selection phases. | | Bullwhip Effect | A phenomenon in supply chains where demand variability increases as one moves further upstream from the customer to the supplier, leading to inefficiencies. | | SIPOC | A process mapping tool that stands for Suppliers, Inputs, Process, Outputs, and Customers, used to define the scope and elements of a process. | | SCOR Model | The Supply Chain Operations Reference model, a framework used to describe, measure, and improve supply chain processes across different companies. | | Performance Objectives (Supply Chain) | Key metrics used to evaluate the effectiveness of a supply chain, including quality, speed, dependability, flexibility, cost, and sustainability. | | Upstream | The direction in a supply chain moving from the customer back towards the raw material suppliers. | | Downstream | The direction in a supply chain moving from the raw material suppliers towards the ultimate customer. |

# Defining and understanding capacity management Capacity management involves understanding the nature of product or service demand and effectively planning and controlling capacity [3](#page=3). ### 1.1 The capacity management framework The capacity management framework outlines the structured approach to managing an organization's capacity. It encompasses various components and considerations to ensure that capacity aligns with demand and business objectives. While specific levels of the framework are mentioned, the provided content focuses on the fundamental definition and the existence of a framework without detailing its specific hierarchical levels or components [4](#page=4) [5](#page=5). > **Tip:** Understanding capacity management is crucial for ensuring that services can meet user demand without over-provisioning or under-provisioning resources. The core idea of capacity management is to match available capacity with the demand for products or services in an efficient and effective manner. This requires a thorough understanding of the patterns and volume of demand [3](#page=3). --- # Forecasting approaches and calculation methods Forecasting involves predicting future values based on historical data and other relevant information. There are two primary categories of forecasting approaches: qualitative and quantitative [6](#page=6) [7](#page=7). ### 2.1 Qualitative forecasting approaches Qualitative methods rely on subjective opinions and judgment when historical data is scarce or not directly applicable to future predictions. These methods are often used for new products or market entries [8](#page=8). #### 2.1.1 Panel approach This method involves a group of experts who convene to discuss and arrive at a consensus forecast [7](#page=7). #### 2.1.2 Delphi method The Delphi method is a structured technique that involves a panel of experts who are surveyed iteratively. Responses are anonymized, and feedback is provided to the experts to encourage convergence towards a more accurate forecast [7](#page=7). #### 2.1.3 Scenario planning Scenario planning involves developing multiple plausible future scenarios and forecasting outcomes for each. This approach is useful for understanding potential future states and their implications [7](#page=7). ### 2.2 Quantitative forecasting approaches Quantitative methods use historical data and mathematical models to generate forecasts. These methods assume that past patterns will continue into the future. They are broadly divided into time-series analysis and causal methods [8](#page=8). #### 2.2.1 Time-series analysis Time-series analysis uses historical data points ordered by time to forecast future values. Components of a time series can include trend, seasonality, and random fluctuations [12](#page=12) [8](#page=8). ##### 2.2.1.1 Simple moving average The simple moving average (SMA) calculates a forecast by averaging the actual values from a specified number of the most recent periods. Each period considered is given equal weight [9](#page=9). The formula for a simple moving average is: $$ \text{Forecast} = \frac{\sum_{i=1}^{n} \text{Actual Sales in Period } i}{n} $$ Where: - $n$ is the number of periods to average [9](#page=9). **Example:** If actual sales for the last three months were 32, 26, and 20 units, the simple moving average forecast for the next month would be: $$ \text{Forecast} = \frac{32 + 26 + 20}{3} = 26 \text{ units} [11](#page=11). $$ ##### 2.2.1.2 Weighted moving average In a weighted moving average, different weights are assigned to different periods, with more recent periods typically receiving higher weights. The sum of the weights must equal one [10](#page=10) [11](#page=11). The formula for a weighted moving average is: $$ \text{Forecast} = \sum_{i=1}^{n} (\text{Actual Sales in Period } i \times \text{Weight for Period } i) $$ The weights are often determined subjectively or through optimization [11](#page=11). **Example:** Using the same sales data (32, 26, 20) and assigning weights (for example, if $w_1=1/6$, $w_2=2/6$, $w_3=3/6$ for periods 1, 2, and 3 respectively, where period 3 is most recent), the forecast would be calculated as: $$ \text{Forecast} = (32 \times \frac{1}{6}) + (26 \times \frac{2}{6}) + (20 \times \frac{3}{6}) = \frac{32 + 52 + 60}{6} = \frac{144}{6} = 24 \text{ units} [11](#page=11). $$ ##### 2.2.1.3 Simple exponential smoothing Simple exponential smoothing is a time-series forecasting method that assigns exponentially decreasing weights to past observations. It uses a smoothing constant, denoted by alpha ($\alpha$), which ranges between 0 and 1. The most recent forecast and the most recent forecast error are used to calculate the new forecast, giving more weight to recent data [10](#page=10). The formula for simple exponential smoothing is: $$ \text{Forecast}_{t+1} = \alpha \times \text{Actual}_t + (1 - \alpha) \times \text{Forecast}_t $$ Alternatively, it can be expressed in terms of the forecast error: $$ \text{Forecast}_{t+1} = \text{Forecast}_t + \alpha \times (\text{Actual}_t - \text{Forecast}_t) $$ Where: - $\text{Forecast}_{t+1}$ is the forecast for the next period. - $\alpha$ is the smoothing constant (0 $\le \alpha \le$ 1) [10](#page=10). - $\text{Actual}_t$ is the actual demand in the current period ($t$). - $\text{Forecast}_t$ is the forecast for the current period ($t$). **Example:** Using the data where the actual sales in the previous month were 20 units, and the forecast for that month was 23 units, with a smoothing constant ($\alpha$) of 0.3. The forecast for the next month would be: $$ \text{Forecast}_{\text{Apr}} = 0.3 \times 20 + (1 - 0.3) \times 23 = 0.3 \times 20 + 0.7 \times 23 = 6 + 16.1 = 22.1 \text{ units} [11](#page=11) [22](#page=22). $$ > **Tip:** The choice of $\alpha$ is crucial. A higher $\alpha$ gives more weight to recent data, making the forecast more responsive to changes but also more susceptible to random fluctuations. A lower $\alpha$ gives more weight to historical data, resulting in a smoother forecast but one that may lag behind actual trends [10](#page=10). #### 2.2.2 Causal methods Causal methods, such as regression analysis, assume a relationship between the variable being forecasted and other independent variables. These methods are more complex than time-series analysis and are used when underlying causes for demand can be identified [8](#page=8). ### 2.3 Calculating forecast error It is essential to measure the accuracy of a forecast to understand its reliability and to make necessary adjustments. Forecast error is the difference between the actual demand and the forecasted demand. A high deviation indicates a less reliable forecast, while a low deviation suggests a more reliable one [13](#page=13). Common measures of forecast error include: * **Mean Absolute Deviation (MAD):** This measures the average magnitude of the errors in a set of forecasts, without considering their direction. $$ \text{MAD} = \frac{\sum_{t=1}^{n} |\text{Actual}_t - \text{Forecast}_t|}{n} $$ * **Mean Absolute Percentage Error (MAPE):** This expresses the forecast error as a percentage of the actual demand, providing a relative measure of accuracy. $$ \text{MAPE} = \frac{\sum_{t=1}^{n} \frac{|\text{Actual}_t - \text{Forecast}_t|}{\text{Actual}_t}}{n} \times 100\% $$ Where: - $n$ is the number of periods [13](#page=13). > **Tip:** While MAD provides an absolute measure of error, MAPE is useful for comparing forecast accuracy across different products or services with varying demand levels [13](#page=13). --- # Measuring operational capacity and effectiveness This section focuses on calculating key operational metrics, including capacity, utilization, efficiency, and Overall Equipment Effectiveness (OEE), detailing their components and significance. ### 3.1 Understanding operational capacity Capacity is defined as the maximum level of value-added activity that an operation can achieve over a specific period [15](#page=15). ### 3.2 Calculating utilization and efficiency * **Utilization** is a measure that compares the actual output of an operation to its design capacity. The formula is [17](#page=17): $$ \text{Utilization} = \frac{\text{Actual output}}{\text{Design capacity}} $$ * **Efficiency** compares the actual output to the effective capacity of an operation. The formula is [17](#page=17): $$ \text{Efficiency} = \frac{\text{Actual output}}{\text{Effective capacity}} $$ > **Tip:** While utilization indicates how much of the potential capacity is being used, efficiency highlights how well the available capacity is being leveraged. A high utilization rate might not always translate to high efficiency if the effective capacity is also low. ### 3.3 Calculating Overall Equipment Effectiveness (OEE) Overall Equipment Effectiveness (OEE) is a composite metric that measures how well manufacturing equipment is utilized. It is calculated by multiplying three components: availability, performance, and quality [18](#page=18). * **Availability Loss:** This accounts for factors that prevent the equipment from running as scheduled. Examples include staff absence, administrative tasks, and compliance training [18](#page=18). * **Performance Loss:** This considers instances where the equipment runs slower than its theoretical maximum speed. Causes can include learning losses, under-performing staff, and technology-related delays [18](#page=18). * **Quality Loss:** This addresses defects and rework. It includes losses from rework, complaint handling, and inspection activities [18](#page=18). The OEE is calculated as: $$ \text{OEE} = \text{Availability} \times \text{Performance} \times \text{Quality} $$ #### 3.3.1 Example OEE calculation Consider an example where: * Total available hours = 400 hours * Actual operating hours (after availability losses) = 365 hours * Actual output in terms of good parts (after performance losses) = 310 units * Good parts produced (after quality losses) = 285 units The components are calculated as follows: * Availability = $365 \text{ hours} / 400 \text{ hours} = 0.91$ [18](#page=18). * Performance = $310 \text{ units} / 365 \text{ hours} = 0.85$ (This likely represents the proportion of theoretical speed achieved during operating hours) [18](#page=18). * Quality = $285 \text{ good parts} / 310 \text{ total parts} = 0.92$ (This represents the proportion of good parts produced from the output achieved) [18](#page=18). Therefore, the OEE is: $$ \text{OEE} = 0.91 \times 0.85 \times 0.92 = 0.71 $$ This means there is a 29% "capacity leakage," indicating significant potential for improvement in the operational processes [18](#page=18). --- # Strategies for matching capacity and demand Aligning operational capacity with fluctuating customer demand is a critical challenge that organizations must address to optimize efficiency, profitability, and customer satisfaction. This involves employing strategies that either influence demand to better fit available capacity or adjust capacity to meet predicted demand levels [19](#page=19). ### 4.1 Influencing demand One primary approach to managing the capacity-demand imbalance is to actively influence the demand side. This can be achieved through several tactics [20](#page=20): * **Price differentiation:** Varying prices based on demand levels or customer segments can encourage or discourage consumption at specific times [20](#page=20). * **Scheduling promotions:** Offering discounts or special deals during periods of low demand can help stimulate business and smooth out demand peaks and troughs [20](#page=20). * **Constraining customer access:** Implementing reservation systems, appointment scheduling, or limiting entry can help regulate the flow of customers and prevent overwhelming capacity [20](#page=20). * **Service differentiation:** Offering different service levels or product variations can cater to diverse customer needs and preferences, potentially shifting demand towards times when capacity is more readily available [20](#page=20). * **Creating alternative products or services:** Developing complementary offerings that can be produced or delivered during off-peak times can help balance workload and utilize resources more effectively [20](#page=20). #### 4.1.1 Yield management A specialized strategy for influencing demand, particularly relevant for services with inflexible capacities and perishable outputs, is **Yield Management**. This approach is common in industries like hotels and airlines, where the objective is to maximize revenue and resource utilization. Yield management relies heavily on statistical analysis and historical data to forecast demand and adjust pricing dynamically. It allows for variable pricing for the same service across different times or markets, aiming to capture the maximum willingness to pay from customers [21](#page=21). ### 4.2 Matching capacity to demand Alternatively, organizations can focus on directly matching their capacity to the expected demand. Two primary strategies exist for this [28](#page=28): #### 4.2.1 Level capacity plan A **level capacity plan** aims to maintain a stable output rate regardless of demand fluctuations. Under this strategy [28](#page=28): * **Inventory Management:** In times of low demand, the organization produces goods or services and stores any unsold output as inventory. During periods of high demand, they fulfill customer needs by drawing from this accumulated inventory [28](#page=28). * **Stable Operations:** Staff schedules are kept fixed, and the inflow of materials remains constant [28](#page=28). * **Asset Utilization:** This approach typically leads to higher asset utilization due to consistent production levels [28](#page=28). **Example:** Paper mills often utilize a level capacity plan, as paper can be stored in inventory when demand is low [29](#page=29). #### 4.2.2 Chase capacity plan A **chase capacity plan**, conversely, involves adjusting capacity to closely follow the predicted levels of demand. This strategy is best suited for situations where storing the product or service is difficult or impossible. Key characteristics include [28](#page=28): * **Flexibility:** It requires flexibility in staffing and production levels to respond to demand changes [28](#page=28). * **Active Management:** This approach necessitates active management to handle the adjustments in capacity [28](#page=28). * **Potential for Lower Asset Utilization:** Since capacity is scaled to demand, there might be periods of underutilization when demand is low [28](#page=28). **Example:** Beach clubs are a classic example of a business employing a chase capacity plan, as their capacity (e.g., number of loungers, staff) directly fluctuates with daily or seasonal demand [29](#page=29). --- # Factors influencing capacity decisions This section details the critical factors influencing the setting of base capacity levels by examining operational performance objectives, output perishability, and demand/supply variability, using call center examples. ### 5.1 Factors influencing the supply side and setting base capacity levels The supply side of capacity decisions is influenced by several key factors: * **Operational performance objectives:** These are the desired levels of service or output quality that an operation aims to achieve. A common objective is to maintain a certain service level [24](#page=24) [26](#page=26). * **Perishability of the operation’s outputs:** The extent to which an operation's output cannot be stored for future use significantly impacts capacity planning [24](#page=24). * **Degree of variability in demand or supply:** The unpredictability of customer demand or the availability of resources introduces complexity into capacity decisions [24](#page=24). ### 5.2 Factors influencing the demand side and setting base capacity levels Capacity decisions are also heavily influenced by demand-side considerations, particularly performance objectives and the inherent nature of the services provided. #### 5.2.1 Performance objectives and base capacity Performance objectives directly inform the required base capacity. For instance, if a call center's objective is to provide "High Quality Service," this translates into a need for higher base capacity to minimize customer wait times [26](#page=26). > **Example:** A call center aiming for an average customer wait time of 2 minutes will need to implement a higher base capacity compared to one targeting an average wait time of 5 minutes, assuming similar demand patterns [26](#page=26). #### 5.2.2 Cost and flexibility in call centers The trade-offs between fixed costs, flexibility, and operational performance are crucial in capacity decisions, especially in service industries like call centers. * **Traditional Call Center Model:** This model typically involves high fixed costs due to office rent and long-term lease contracts. Staff also often work fixed base shift rosters, making it difficult to upscale capacity quickly [27](#page=27). * **Operators Working From Home Model:** This alternative model can reduce fixed costs by minimizing or eliminating the need for a central workspace. It allows for a smaller minimum shift size and rapid upscaling to meet required capacity without the constraints of travel time. This model can also incorporate small variable compensation for home office use and reserve availability [27](#page=27). > **Result:** The work-from-home model generally leads to lower fixed costs, a lower base staff capacity, higher flexibility, and potentially a higher service level. It can also contribute to sustainability objectives by requiring fewer buildings and reducing travel [27](#page=27). --- ## Common mistakes to avoid - Review all topics thoroughly before exams - Pay attention to formulas and key definitions - Practice with examples provided in each section - Don't memorize without understanding the underlying concepts

| Term | Definition | |------|------------| | Capacity Management | The activity of understanding the nature of product or service demand, and effectively planning and controlling the available capacity to meet that demand. | | Capacity Management Framework | A structured approach that outlines the various components and processes involved in managing an operation's capacity effectively. | | Qualitative Forecasting | Forecasting methods that rely on subjective judgment, opinions, and non-numerical data, such as expert opinions, market research, and scenario planning. | | Quantitative Forecasting | Forecasting methods that use historical numerical data and statistical techniques to predict future demand, such as time-series analysis and causal models. | | Moving Average Forecasting | A forecasting technique that calculates the average of demand from a specified number of the most recent periods to predict future demand, assuming each period has equal weight. | | Simple Exponential Smoothing | A forecasting method that assigns exponentially decreasing weights to past observations, giving more weight to recent data points and less weight to older data. It uses a smoothing factor (alpha) to adjust the forecast. | | Forecast Error | The difference between the actual demand and the forecasted demand, which is crucial for evaluating the accuracy and reliability of a forecasting method. | | Mean Absolute Deviation (MAD) | A measure of forecast accuracy calculated by averaging the absolute differences between actual demand and forecasted demand over a period. | | Mean Absolute Percent Error (MAPE) | A measure of forecast accuracy calculated by averaging the absolute percentage differences between actual demand and forecasted demand over a period. | | Capacity | The maximum level of value-added activity that an operation can achieve over a specific period. | | Utilization | A measure of how much of the available capacity is actually being used, calculated as actual output divided by design capacity. | | Efficiency | A measure of how well an operation is performing relative to its effective capacity, calculated as actual output divided by effective capacity. | | Overall Equipment Effectiveness (OEE) | A key performance indicator that measures the percentage of planned production time that is truly productive, considering availability, performance, and quality losses. | | Availability Loss | Reductions in operating time due to equipment breakdowns, setup times, or material shortages, impacting the availability of the equipment. | | Performance Loss | Reductions in output speed or throughput due to minor stops, slowdowns, or machine inefficiencies, impacting the performance of the equipment. | | Quality Loss | Reductions in good output due to defects, rework, or scrap, impacting the quality of the products produced by the equipment. | | Level Capacity Plan | A capacity management strategy where output and staffing levels are kept constant, with excess production stored as inventory during low demand periods and used to meet demand during high periods. | | Chase Capacity Plan | A capacity management strategy that adjusts output and staffing levels to match forecasted demand fluctuations, often involving flexible workforces and scheduling. | | Yield Management | A strategy used in industries with inflexible capacities and high fixed costs to optimize revenue by varying prices for the same service or product based on demand and time, relying heavily on statistical analysis. |

# Algoritmisch Human Resource Management (AHRM) Algoritmisch human resource management (AHRM) is de toepassing van algoritmes voor het analyseren van HR-data om patronen te identificeren en beslissingen te ondersteunen. ### 1.1 Kernconcepten van AHRM AHRM maakt gebruik van algoritmes, met name machine learning, om grote hoeveelheden HR-data te doorgronden. Dit stelt organisaties in staat om verborgen verbanden en patronen te ontdekken die anders onopgemerkt zouden blijven. De inzichten die hieruit voortkomen, worden gebruikt om voorspellingen te doen en besluitvorming op HR-gebied te optimaliseren. #### 1.1.1 Data-analyse en patroonherkenning Centraal binnen AHRM staat de analyse van diverse HR-gerelateerde datasets. Voorbeelden hiervan zijn gegevens over werknemersaanwezigheid, klanttevredenheidsscores, prestatiebeoordelingen en opleidingsrecords. Machine learning-algoritmes worden ingezet om deze data te doorzoeken en significante correlaties en patronen te identificeren. > **Voorbeeld:** Een algoritme kan data over werknemersaanwezigheid en klanttevredenheid analyseren om verbanden te ontdekken. Het zou bijvoorbeeld kunnen aantonen dat medewerkers die frequent overwerken en tegelijkertijd lage klanttevredenheidsscores behalen, een verhoogd risico lopen op burn-out. #### 1.1.2 Voorspellende analyses Op basis van de geïdentificeerde patronen kan AHRM voorspellende modellen ontwikkelen. Deze modellen kunnen waardevolle inzichten bieden met betrekking tot: * **Risicofactoren:** Het voorspellen van medewerkers die een verhoogd risico lopen op situaties zoals burn-out, verhoogd verzuim of ontslag. * **Potentieel en geschiktheid:** Het identificeren van medewerkers die in aanmerking komen voor promotie, training of nieuwe uitdagende projecten, gebaseerd op hun prestaties en gedragspatronen. #### 1.1.3 Besluitvorming en automatisering De voorspellingen die voortkomen uit AHRM-systemen ondersteunen managers bij het nemen van geïnformeerde HR-beslissingen. In sommige gevallen kunnen deze beslissingen zelfs worden geautomatiseerd, wat leidt tot efficiëntere processen. #### 1.1.4 Strathern's paradox Een belangrijk concept dat relevant is voor AHRM is Strathern's paradox. Dit fenomeen beschrijft de neiging van mensen om hun gedrag aan te passen zodra ze weten dat ze worden geobserveerd. In de context van AHRM kan dit betekenen dat werknemers hun gedrag wijzigen om te voldoen aan de verwachtingen die door de algoritmes worden gesuggereerd, wat de objectiviteit van de data kan beïnvloeden. > **Tip:** Wees je bewust van de mogelijke impact van observatie op gedrag bij de interpretatie van AHRM-resultaten. Het kan nodig zijn om strategieën te implementeren die gericht zijn op het stimuleren van authentiek gedrag. --- # Gegevensanalyse en patroonherkenning in HR Het proces waarbij machine learning algoritmes HR-data analyseren om verbanden en patronen te ontdekken, die de basis vormen voor voorspellingen en besluitvorming. ## 2. Gegevensanalyse en patroonherkenning in HR Algorithmic Human Resource Management (AHRM) maakt gebruik van algoritmes om patronen te herkennen in HR-data en op basis daarvan beslissingen te nemen. Dit proces omvat het analyseren van verschillende databronnen, zoals aanwezigheid, klanttevredenheid, prestatiebeoordelingen, en andere werknemersgerelateerde informatie. ### 2.1 Het proces van patroonherkenning Machine learning algoritmes worden ingezet om deze data te analyseren en verbanden te ontdekken. Deze verbanden worden geïdentificeerd als patronen die inzicht geven in het gedrag en de prestaties van werknemers. > **Tip:** Het doel is om verborgen relaties bloot te leggen die met traditionele methoden moeilijk te detecteren zouden zijn. #### 2.1.1 Voorbeeld van patroonherkenning Een concreet voorbeeld is de analyse van data over de aanwezigheid van werknemers in combinatie met hun klanttevredenheidsscores. Hierdoor kunnen patronen worden herkend, zoals het verband tussen werknemers die regelmatig overwerken en het hebben van lage klanttevredenheidsscores. ### 2.2 Voorspellende analyses Op basis van de geïdentificeerde patronen kunnen algoritmes voorspellingen doen over toekomstige gebeurtenissen of werknemersrisico's. > **Tip:** Deze voorspellingen bieden proactieve mogelijkheden voor HR en management. #### 2.2.1 Toepassingen van voorspellende analyses * **Risico-identificatie:** Het voorspellen welke werknemers een verhoogd risico lopen op bijvoorbeeld een burn-out. * **Talentontwikkeling:** Het identificeren van werknemers die in aanmerking komen voor promotie of verdere ontwikkeling. ### 2.3 Besluitvorming op basis van voorspellingen De inzichten en voorspellingen die voortkomen uit de gegevensanalyse worden gebruikt door managers om gefundeerde beslissingen te nemen. In sommige gevallen kunnen deze beslissingen ook automatisch worden gegenereerd door het algoritme. ### 2.4 Strathern's paradox Een belangrijk concept in de context van observatie en gedrag is Strathern's paradox. Dit principe stelt dat wanneer individuen zich ervan bewust zijn dat ze worden geobserveerd, ze hun gedrag kunnen aanpassen aan het gedrag dat als wenselijk wordt beschouwd. > **Tip:** Houd rekening met de mogelijke invloed van observatie op het gedrag wanneer u data analyseert of beslissingen neemt op basis van geobserveerde patronen. Dit kan leiden tot een vertekening van de werkelijke situatie. --- # Besluitvorming op basis van AHRM-voorspellingen Besluitvorming op basis van AHRM-voorspellingen omvat het proces waarbij managers de inzichten uit algoritmes gebruiken om weloverwogen beslissingen te nemen binnen human resource management. ### 3.1 Kernconcepten van AHRM-voorspellingen Algorithmic Human Resource Management (AHRM) maakt gebruik van algoritmes om patronen te herkennen in HR-data. Deze patronen worden vervolgens gebruikt om voorspellingen te genereren die managers ondersteunen bij het nemen van beslissingen. #### 3.1.1 Data-analyse en patroonherkenning Machine learning algoritmes analyseren diverse HR-data, zoals aanwezigheid en klanttevredenheid. Door het herkennen van verbanden in deze data, kunnen potentiële problemen of kansen worden geïdentificeerd. > **Voorbeeld:** Een algoritme kan ontdekken dat medewerkers die vaak overwerken en lage tevredenheidsscores laten zien, een verhoogd risico lopen op een burn-out. #### 3.1.2 Genereren van voorspellingen Op basis van de gedetecteerde patronen genereren algoritmes voorspellingen. Deze voorspellingen kunnen variëren van het identificeren van medewerkers die risico lopen op burn-out tot het aanwijzen van geschikte kandidaten voor promotie. #### 3.1.3 Besluitvorming door managers Managers gebruiken deze algoritme-gegenereerde voorspellingen als input voor hun besluitvorming. Dit kan leiden tot proactieve maatregelen, zoals preventieve interventies om burn-out te voorkomen, of strategische beslissingen met betrekking tot carrièreontwikkeling. In sommige gevallen kunnen deze beslissingen ook automatisch worden uitgevoerd door het systeem. ### 3.2 Strathern's paradox en gedragsaanpassing Een belangrijk aspect bij het inzetten van AHRM-systemen is Strathern's paradox. Dit fenomeen beschrijft dat individuen hun gedrag kunnen aanpassen wanneer zij weten dat ze geobserveerd worden, met als doel te voldoen aan het verwachte of gewenste gedrag. > **Tip:** Het bewustzijn van Strathern's paradox is cruciaal voor managers om de objectiviteit van de data en de daarop gebaseerde voorspellingen te evalueren, aangezien gedragsaanpassing de werkelijke situatie kan vertekenen. --- # De paradox van Strathern en gedragsaanpassing De paradox van Strathern beschrijft hoe individuen hun gedrag aanpassen wanneer zij zich bewust zijn van observatie, en zich meer conformeren aan verwachte of gewenste normen. ### 4.1 Kernconcept van de paradox van Strathern Dit fenomeen, ook wel bekend als het Hawthorne-effect, stelt dat de aanwezigheid van een observator of de kennis van het ondergaan van een onderzoek, leidt tot een verandering in het gedrag van de onderzochte personen. Deze verandering is doorgaans gericht op het gedragen zoals men denkt dat van hen verwacht wordt of hoe zij wensen te worden gezien. > **Tip:** De paradox van Strathern is relevant in diverse sociale en organisatiecontexten, waaronder onderzoek naar productiviteit, naleving van regels, en de effectiviteit van interventies. ### 4.2 Implicaties voor gedrag Het bewustzijn van observatie kan leiden tot: * **Verhoogde prestaties:** Individuen kunnen harder werken of efficiënter handelen uit angst voor negatief oordeel of de wens om positief beoordeeld te worden. * **Aanpassing aan normen:** Gedrag dat als wenselijk of acceptabel wordt beschouwd binnen een bepaalde groep of context, zal vaker worden vertoond. * **Vertekende onderzoeksresultaten:** In onderzoek kan dit effect leiden tot resultaten die niet de werkelijke, niet-geobserveerde gedragspatronen weerspiegelen. ### 4.3 Toepassing binnen Algorithmic Human Resource Management (AHRM) Hoewel de tekst de paradox van Strathern kort noemt in relatie tot algemeen gedrag, is het concept ook relevant binnen de context van Algorithmic Human Resource Management (AHRM). AHRM maakt gebruik van algoritmes om patronen in HR-data te herkennen en op basis daarvan beslissingen te nemen. Als medewerkers weten dat hun gegevens, zoals aanwezigheid en klanttevredenheid, worden geanalyseerd door algoritmes om hun prestaties en risico's (zoals burn-out of promotiekansen) te voorspellen, kunnen zij hun gedrag hierop aanpassen. * **Voorbeeld:** Als een algoritme analyseert dat medewerkers met een lage tevredenheidsscore en veel overwerk een verhoogd risico op burn-out lopen, kunnen medewerkers die zich bewust zijn van deze analyse hun werklast gaan managen of hun tevredenheid uiten, zelfs als hun onderliggende stressniveau niet daadwerkelijk is verminderd. Dit kan leiden tot een vertekening van de data die het algoritme analyseert. > **Tip:** Bij het implementeren van AHRM-systemen is het cruciaal om rekening te houden met de mogelijke impact van de paradox van Strathern. Transparantie over welke data worden geanalyseerd en hoe dit gebeurt, kan helpen om de verwachtingen van medewerkers te managen en de betrouwbaarheid van de voorspellingen te vergroten. --- ## Veelgemaakte fouten om te vermijden - Bestudeer alle onderwerpen grondig voor examens - Let op formules en belangrijke definities - Oefen met de voorbeelden in elke sectie - Memoriseer niet zonder de onderliggende concepten te begrijpen

| Term | Definition | |------|------------| | Algoritmisch Human Resource Management (AHRM) | Een benadering waarbij algoritmes worden ingezet om patronen in personeelsgegevens te herkennen en op basis daarvan beslissingen te nemen, zoals het voorspellen van burn-out risico's of promotiegeschiktheid. | | Machine learning algoritmes | Algoritmes die in staat zijn om patronen te herkennen en voorspellingen te doen door middel van analyse van grote datasets, zonder expliciet geprogrammeerd te zijn voor elke specifieke taak. | | Data-analyse | Het proces van het inspecteren, opschonen, transformeren en modelleren van data met als doel het ontdekken van nuttige informatie, het vormen van conclusies en het ondersteunen van besluitvorming. | | Patroonherkenning | Het identificeren van consistente en herhaalbare structuren of trends binnen een dataset, wat essentieel is voor het maken van voorspellingen of het begrijpen van onderliggende mechanismen. | | Voorspelling | Een uitspraak over een toekomstige gebeurtenis of situatie, gebaseerd op analyse van bestaande gegevens en geïdentificeerde patronen. | | Besluitvorming | Het proces van het kiezen van een bepaalde handelwijze uit meerdere alternatieven, vaak gebaseerd op analyse, voorspellingen en beoordeling van mogelijke uitkomsten. | | Paradox van Strathern | Een sociaal-psychologisch effect waarbij mensen hun gedrag aanpassen zodra ze zich bewust worden dat ze geobserveerd worden, vaak in de richting van wat als wenselijk wordt beschouwd. |