A Minorization-Maximization (MM) Algorithm for Semiparametric Logit Models: Bottlenecks, Extensions, and Comparisons

2018 ◽  
Author(s):  
Prateek Bansal ◽  
Ricardo Daziano ◽  
Erick Guerra
Keyword(s):  
Logit Models ◽  
Mm Algorithm

Ethnic niching in a segmented labour market: Evidence from Spain

2012 ◽  
Vol 9 (3) ◽  
pp. 249-262 ◽  
Author(s):  
Mikolaj Stanek ◽  
Alberto Veira
Keyword(s):  
Social Capital ◽  
Labour Market ◽  
Significant Role ◽  
Immigrant Workers ◽  
Structural Factors ◽  
Immigrant Communities ◽  
Logit Models ◽  
Human And Social Capital

Using the Spanish National Immigrant Survey (NIS-2007) we identify the ethnic niches where workers from five main immigrant communities concentrate. We then implement logit models in order to assess how structural factors and human and social capital variables affect the odds of working in these niches. We observe that the strong segmentation of the Spanish labour market strongly favours the concentration of immigrants in certain occupational niches. Nevertheless, variables related to human and social capital still play a significant role in the placement of immigrant workers in different niches, all of which are not equally attractive. 

Condom Use and HIV/AIDS Among Young People in Edo State, Nigeria

2020 ◽  
pp. 0044118X2098138
Author(s):  
Eric Y. Tenkorang
Keyword(s):  
Young People ◽  
Condom Use ◽  
Random Effects ◽  
Rural Youth ◽  
Sexually Active ◽  
Logit Models ◽  
Junior Secondary Schools ◽  
Junior Secondary ◽  
Edo State ◽  
Gender Specific

This study used the Information Motivation Behavioral (IMB) skills model to examine condom use among rural youth in Edo State, Nigeria. Data were collected from 4,801 youth aged 11 to 17 years attending Junior Secondary Schools. Analysis focused on 1,749 (Male = 1,134, Female = 615) sexually active youth. Random-effects ordinal logit models were used to examine the effects of the various components of the IMB framework on frequency of condom use. Gender-specific models were estimated. Results provided qualified support for the IMB. Specifically, youth who communicated with teachers and peers about condoms and HIV had higher odds of saying they used condoms always than sometimes or never. Compared to males who did not think they could get HIV, those who thought they probably could get infected were less likely to use condoms frequently. Similarly, compared to those who didn’t, females who knew others infected with HIV were less likely to use condoms frequently.

Constrained and Unconstrained Partial Adjacent Category Logit Models for Ordinal Response Variables

2015 ◽  
Vol 47 (2) ◽  
pp. 169-206 ◽  
Author(s):  
Andrew S. Fullerton ◽  
Jun Xu
Keyword(s):  
General Social Survey ◽  
Estimation Method ◽  
Logit Models ◽  
Proportional Odds ◽  
Social Survey ◽  
Partial Model ◽  
Ordinal Response ◽  
Proportional Odds Assumption ◽  
Using Data ◽  
Response Variables

Adjacent category logit models are ordered regression models that focus on comparisons of adjacent categories. These models are particularly useful for ordinal response variables with categories that are of substantive interest. In this article, we consider unconstrained and constrained versions of the partial adjacent category logit model, which is an extension of the traditional model that relaxes the proportional odds assumption for a subset of independent variables. In the unconstrained partial model, the variables without proportional odds have coefficients that freely vary across cutpoint equations, whereas in the constrained partial model two or more of these variables have coefficients that vary by common factors. We improve upon an earlier formulation of the constrained partial adjacent category model by introducing a new estimation method and conceptual justification for the model. Additionally, we discuss the connections between partial adjacent category models and other models within the adjacent approach, including stereotype logit and multinomial logit. We show that the constrained and unconstrained partial models differ only in terms of the number of dimensions required to describe the effects of variables with nonproportional odds. Finally, we illustrate the partial adjacent category logit models with empirical examples using data from the international social survey program and the general social survey.

Sign in / Sign up

Export Citation Format

Share Document