Alternative link functions in binomial response models

Malinda Coa Ravelo () and Ernesto Ponsot Balaguer ()
Additional contact information
Malinda Coa Ravelo: MSc en Estadística por la Universidad de Los Andes. Escuela de Estadística. Universidad de Los Andes. Mérida, Venezuela.
Ernesto Ponsot Balaguer: PhD en Estadística. Escuela de Ciencias Matemáticas y Computacionales. Universidad de Investigación de Tecnología Experimental Yachay. Imbabura, Ecuador.

Economía, 2019, vol. 44, issue 48, 9-35

Abstract: In this research, alternative link functions to the logit function are considered in the adjustment of binomial response models. The logit model is the most used within the analysis of categorical data with dichotomous response; however, some alternative link functions may be more appropriate in specific applications. Along with the logit link, the probit, cauchit, cloglog, loglog, clog and log links are explored in this research. Starting from the saturated binomial model, for each mentioned link, the necessary equations for the calculation of the estimators and their variances are developed, and their behavior is discussed in some interesting situations, suggesting the researcher concerning the most suitable model to select according to the objectives that are pursued.

Keywords: generalized linear models; link function; binomial response models; estimation (search for similar items in EconPapers)
JEL-codes: C01 C02 C13 C25 (search for similar items in EconPapers)
Date: 2019
References: Add references at CitEc
Citations:

Downloads: (external link)
ftp://iies.faces.ula.ve/Pdf/Revista48/Rev48Coa.pdf (application/pdf)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:ula:econom:v:44:y:2019:i:48:p:9-35

Access Statistics for this article

Economía is currently edited by Dyanna María Ruíz Uzcátegui and Yibeli Emilia Briceño Carrero

More articles in Economía from Instituto de Investigaciones Económicas y Sociales (IIES). Facultad de Ciencias Económicas y Sociales. Universidad de Los Andes. Mérida, Venezuela Facultad de Ciencias Económicas y Sociales. Instituto de Investigaciones Económicas y Sociales. Campus Universitario Liria, Edificio G, Tercer Nivel. Mérida 5101, Estado Mérida, Venezuela. Contact information at EDIRC.
Bibliographic data for series maintained by Alexis Vásquez ().