Tobit Models in Social Science Research

Anuja, A R (2023) Tobit Models in Social Science Research. In: Training Manual on Advanced Analytical Tools for Social Science Research Vol.2. CMFRI Training Manual Series No. 29/2023 . ICAR- Central Marine Fisheries Research Institute, Kochi, pp. 46-53.

Text Winter School on Social Science Research_2023_An overview of tobit models in social science research_Anuja A R.pdf Restricted to Registered users only Download (1MB)

Abstract

Qualitative response regression models are widely used in social sciences. These are models with qualitative dependent variables. The dependent/response variables may take dichotomous (0 or 1), trichotomous (0,1 or 2), or polychotomous (multiple category) values. Thus, the basic difference between a classic linear regression model and a qualitative response regression model is that the dependent variable in the former is quantitative whereas the latter is qualitative. In quantitative regression models, the aim is to estimate the mean value of the dependent variable, given the values of the independent variables. However, in qualitative regression model, the intention is to estimate the probability of something happening such as owning a house, getting loan, participating in a welfare program, etc. Hence these qualitative models are also known as probability models

Actions (login required)

View Item