Comparing Logit & Probit Coefficients Between Nested Models (Social Science Research)
![](http://abbyjorgensen.com/wp-content/uploads/2022/10/xavi-cabrera-glostt_i3e0-unsplash.jpg?w=768)
Social scientists are often interested in seeing how the estimated effects of variables change once other variables are controlled for. For example, a simple analysis may reveal that income differs by race – but why does it differ?
To answer such a question, a researcher might estimate a model where race is the only independent variable, and then add variables such as education to subsequent models. If the original estimated effect of race declines, this may be because race affects education, which in turn affects income.
What is not universally realized is that the interpretation of such nested models can be problematic when logit or probit techniques are employed with binary dependent variables. Naïve comparisons of coefficients between models can indicate differences where none exist, hide differences that do exist, and even show differences in the opposite direction of what actually exists. We discuss why problems occur and illustrate their potential consequences. Proposed solutions, such as Linear Probability Models, y-standardization, the Karlson/ Holm/ Breen method, and marginal effects, are explained and evaluated.
Williams, Richard A and Jorgensen, Abigail, Comparing Logit & Probit Coefficients Between Nested Models (May 10, 2022).
Saying ‘I Do’ to Feminism (Religion & Gender)
![](http://abbyjorgensen.com/wp-content/uploads/2022/10/beatriz-perez-moya-m2t1j-6fn8w-unsplash.jpg?w=1024)
Do Christian women who identify as feminist act differently than those who do not? Scholars have pointed out that religious women may exhibit beliefs about gender equality, whether or not they identify as feminists. But do women who choose to identify explicitly as feminists differ in their behavior from women who do not? We answer this question by analyzing 307 qualitative survey responses from Christian women in the U.S. about an important point in their lives, when gender and religious identities become particularly salient and fraught: weddings. We found that explicit feminists thought and acted differently compared to “implicit” and “non” feminists. Further, Protestant and Catholic feminists used different strategies to intersect their feminist and religious identities. We conclude that the decision to identify explicitly as a feminist or not does not just represent a semantic difference between Christian women but a real difference in both beliefs and actions.
Trudeau, Elizabeth, and Abigail Jorgensen. “Saying ‘I Do’ to Feminism”. Religion and Gender (published online ahead of print 2022). https://doi.org/10.1163/18785417-tat00002 Web.
Goodness-Of-Fit Measures (SAGE Research Methods Foundations)
![](http://abbyjorgensen.com/wp-content/uploads/2022/10/hatiful-yosa-gaeqrqeeqps-unsplash.jpg?w=1024)
Quantitative researchers must make decisions about which model and which variables best address a particular research question. In order to answer questions about the distribution of the data and to decide on the best model, researchers often consider “goodness of fit.” While there are many types of goodness-of-fit measures, these measures generally compare the observed data to a model’s predictions to see how well the model matches the data. This entry provides an overview of four types of goodness-of-fit measures and details definitions, explanations, and examples for several common measures.
Jorgensen, Abigail and Richard A. Williams. “Goodness-of-Fit Measures” SAGE Research Methods Foundations, Edited by Paul Atkinson, et al. London: SAGE Publications Ltd, 2020. SAGE Research Methods. 9 Oct 2022, doi: https://dx.doi.org/10.4135/9781526421036946001