Select Page

8.2 The differences between logistic and linear regression


The application examples listed above should provide hints about the purpose of logistic regression (classification) as well as the outcome type (categorical). These stand in contrast to the purpose and outcome type of logistic regression’s better-known cousin, linear regression, but their differences do not end there. The table below lists other ways in which both types of regression vary:

 Logistic regressionLinear regression
PurposeClassificationPrediction
Outcome typeCategoricalNumerical
Sample sizeSufficiently large sample size needed for model to have statistical powerThere is no clear rule for a minimum sample size3, with some believing that the minimum sample size depends on variance4  and the number of predictor variables.5  
BasisProbabilityOrdinary least squares
Other things to be mindful ofOutliers 
Multicollinearity between independent variables 
Overfitting 
Observations must be independent of each other
Outliers 
Multicollinearity between independent variables 
Observations must be independent of each other 
Model residuals are normally distributed 
Variance of residuals should be approximately the same (homoscedasticity)

3 University of Illinois (n.d.). ‘How many data points are enough?’ http://www.phy.ilstu.edu/pte/302content/student_lab_hdbk/How_Many_Data_Points.pdf

4 Jenkins, David G. and Quintana-Ascencio, Pedro F. (2020) ‘A solution to minimum sample size for regressions’. PLoS One; 15(2): e0229345. doi: 10.1371/journal.pone.0229345

5 Van Voorhis, Carmen R. W. and Morgan, B. (2007). ‘Understanding power and rules of thumb for determining sample sizes’. Tutorials for Quantitative Methods in Psychology. 2007, vol. 3 (2), p. 43‐50. doi: 10.20982/tqmp.03.2.p043