Linear versus logistic regression when the dependent variable is a dichotomy

By Ottar Hellevik. 2009

727 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

The Millennial Generation (2017, background): “The potential violation of homoscedasticity assumption with linear models does not seem to be of practical importance because the basic tests used with these kinds of models are robust (Hellevik, 2009).”
The Effect of Grandparental Support on Mothers’ Labour Market Participation: An Instrumental Variable Approach (2014, unknown): “This choice is justified by the fact that the interpretation of results is more straightforward (Hellevik, 2009; Powers and Xie, 2008), and tests on the IVs can be easily implemented 7 .”
On Modeling and Estimation for the Relative Risk and Risk Difference (2015, unknown): “rresponds to choosing the parameter of interest to make it variation independent of parameters of the simplest nuisance model, i.e. the baseline risk p 0(v). However, as argued by many authors (e.g., Hellevik, 2009), the choice of statistical model should target the parameter of substantive interest”