Interpreting and Understanding Logits, Probits, and Other Nonlinear Probability Models
Associate Professor Kristian Bernt Karlson has contributed to a review article published in the Annual Review of Sociology, a high impact sociology journal. The article explores the uses and abuses of logistic models in sociology. Together with his co-authors (Anders Holm, Western University, and Richard Breen, Oxford University) Kristian Bernt Karlson reviews state-of-the-art within the use of nonlinear probability models in sociology.
The article explains the many limitations of these models that have been highlighted in recent research and it points to solutions and new ways of interpreting the parameters from these models. Methods textbooks in sociology and other social sciences routinely recommend the use of the logit or probit model when an outcome variable is binary, an ordered logit or ordered probit when it is ordinal, and a multinomial logit when it has more than two categories. But these methodological guidelines take little or no account of a body of work that, over the past 30 years, has pointed to problematic aspects of these nonlinear probability models and, particularly, to difficulties in interpreting their parameters. In this review, the authors draw on that literature to explain the problems, show how they manifest themselves in research, discuss the strengths and weaknesses of alternatives that have been suggested, and point to lines of further analysis.
Kristian Bernt Karlson, Interpreting and Understanding Logits, Probits, and Other Nonlinear Probability Models, Annual Review of Sociology, Volume 44, July 2018.