scholarly journals How to Test for Goodness of Fit in Ordinal Logistic Regression Models

2017 ◽  
Vol 17 (3) ◽  
pp. 668-686 ◽  
Author(s):  
Morten W. Fagerland ◽  
David W. Hosmer
Keyword(s):  
Regression Models ◽  
Goodness Of Fit ◽  
Logistic Models ◽  
Ratio Test ◽  
Response Variable ◽  
Logistic Regression Models ◽  
Explanatory Variables ◽  
Goodness Of Fit Tests ◽  
Interaction Terms ◽  
Different Types

Ordinal regression models are used to describe the relationship between an ordered categorical response variable and one or more explanatory variables. Several ordinal logistic models are available in Stata, such as the proportional odds, adjacent-category, and constrained continuation-ratio models. In this article, we present a command (ologitgof) that calculates four goodness-of-fit tests for assessing the overall adequacy of these models. These tests include an ordinal version of the Hosmer–Lemeshow test, the Pulkstenis–Robinson chi-squared and deviance tests, and the Lipsitz likelihood-ratio test. Together, these tests can detect several different types of lack of fit, including wrongly specified continuous terms, omission of different types of interaction terms, and an unordered response variable.

On Graphically Checking Goodness-of-fit of Binary Logistic Regression Models

2009 ◽  
Vol 48 (03) ◽  
pp. 306-310 ◽  
Author(s):  
C. E. Minder ◽  
G. Gillmann
Keyword(s):  
Logistic Regression ◽  
Regression Analysis ◽  
Regression Models ◽  
Goodness Of Fit ◽  
Graphical Method ◽  
Logistic Models ◽  
Binary Logistic Regression ◽  
Logistic Regression Models ◽  
Logistic Analysis ◽  
Viable Solution

Summary Objectives: This paper is concerned with checking goodness-of-fit of binary logistic regression models. For the practitioners of data analysis, the broad classes of procedures for checking goodness-of-fit available in the literature are described. The challenges of model checking in the context of binary logistic regression are reviewed. As a viable solution, a simple graphical procedure for checking goodness-of-fit is proposed. Methods: The graphical procedure proposed relies on pieces of information available from any logistic analysis; the focus is on combining and presenting these in an informative way. Results: The information gained using this approach is presented with three examples. In the discussion, the proposed method is put into context and compared with other graphical procedures for checking goodness-of-fit of binary logistic models available in the literature. Conclusion: A simple graphical method can significantly improve the understanding of any logistic regression analysis and help to prevent faulty conclusions.

scholarly journals Modelling Interaction Effects by Using Extended WOE Variables with Applications to Credit Scoring

Mathematics ◽  
2021 ◽  
Vol 9 (16) ◽  
pp. 1903
Author(s):  
Carlos Giner-Baixauli ◽  
Juan Tinguaro Rodríguez ◽  
Alejandro Álvaro-Meca ◽  
Daniel Vélez
Keyword(s):  
Regression Models ◽  
Computational Study ◽  
Classification Tree ◽  
Credit Scoring ◽  
Logistic Models ◽  
Interaction Effects ◽  
Weight Of Evidence ◽  
Logistic Regression Models ◽  
Explanatory Variables ◽  
Decision Making Processes

The term credit scoring refers to the application of formal statistical tools to support or automate loan-issuing decision-making processes. One of the most extended methodologies for credit scoring include fitting logistic regression models by using WOE explanatory variables, which are obtained through the discretization of the original inputs by means of classification trees. However, this Weight of Evidence (WOE)-based methodology encounters some difficulties in order to model interactions between explanatory variables. In this paper, an extension of the WOE-based methodology for credit scoring is proposed that allows constructing a new kind of WOE variable devised to capture interaction effects. Particularly, these new WOE variables are obtained through the simultaneous discretization of pairs of explanatory variables in a single classification tree. Moreover, the proposed extension of the WOE-based methodology can be complemented as usual by balance scorecards, which enable explaining why individual loans are granted or not granted from the fitted logistic models. Such explainability of loan decisions is essential for credit scoring and even more so by taking into account the recent law developments, e.g., the European Union’s GDPR. An extensive computational study shows the feasibility of the proposed approach that also enables the improvement of the predicitve capability of the standard WOE-based methodology.

Multinomial goodness-of-fit tests for logistic regression models

2008 ◽  
Vol 27 (21) ◽  
pp. 4238-4253 ◽  
Author(s):  
Morten W. Fagerland ◽  
David W. Hosmer ◽  
Anna M. Bofin
Keyword(s):  
Logistic Regression ◽  
Regression Models ◽  
Goodness Of Fit ◽  
Logistic Regression Models ◽  
Goodness Of Fit Tests

scholarly journals Role of ocular perfusion pressure in glaucoma: the issue of multicollinearity in statistical regression models

2016 ◽  
Vol 1 (2) ◽  
pp. 89-96
Author(s):  
Alessandra Guglielmi ◽  
Giovanna Guidoboni ◽  
Alon Harris
Keyword(s):  
Blood Pressure ◽  
Regression Models ◽  
Goodness Of Fit ◽  
Perfusion Pressure ◽  
Logistic Models ◽  
Statistical Regression ◽  
Ocular Perfusion Pressure ◽  
Logistic Regression Models ◽  
Ocular Perfusion ◽  
Clinical Dataset

Purpose: Intraocular pressure (IOP), mean arterial pressure (MAP), systolic blood pressure (SYS), diastolic blood pressure (DIA), ocular perfusion pressure (OPP) are important factors for clinical considerations in glaucoma. The existence of linear relationships among these factors, referred to as multicollinearity in statistics, makes it difficult to determine the contribution of each factor to the overall glaucoma risk. The aim of thiswork is to describe howto account for multicollinearity when applying statistical methods to quantify glaucoma risk.Methods: Logistic regression models including multicollinear covariates are reviewed, and statistical techniques for the selection of non-redundant covariates are discussed. A meaningful statistical model including IOP, OPP and SYS as non-redundant covariates is obtained from a clinical dataset including 84 glaucoma patients and 73 healthy subjects, and is used to predict the probability that new individuals joining the study may have glaucoma, based on the values of their covariates.Results: Logistic models with satisfactory goodness-of-fit to the clinical dataset include age, gender, heart rate and either one of the following triplets as covariates: (i)(SYS, DIA, OPP); (ii) (IOP, SYS, OPP); (iii) (IOP, SYS, DIA); or (iv) (IOP, SYS, MAP). Choosing triplet (ii), higher disease probabilities are predicted for higher IOP levels. Similar predictions in terms of disease probability can be obtained for dierent combinations of OPP, SYS and IOP.Conclusion: Multicollinearity does not allow to clearly estimate the single eect of an individual covariate on the overall glaucoma risk. Instead, statistically assessing the combined eects of IOP, OPP, and blood pressure provide useful predictions of disease probability.

scholarly journals Self-Rated Health Status Based on the Type of Health Insurance: A Socioeconomic Perspective

2021 ◽  
Vol 58 ◽  
pp. 004695802110281
Author(s):  
Minsung Sohn ◽  
Minsoo Jung ◽  
Mankyu Choi
Keyword(s):  
Socioeconomic Status ◽  
Health Insurance ◽  
Health Status ◽  
Regression Models ◽  
Private Health Insurance ◽  
Public And Private ◽  
Logistic Regression Models ◽  
Self Rated Health ◽  
Interaction Terms ◽  
Healthcare Coverage

To investigate the effects of public and private health insurance on self-rated health (SRH) status within the National Health Insurance (NHI) system based on socioeconomic status in South Korea. The data were obtained from 10 867 respondents of the Korea Health Panel (2008-2011). We used hierarchical panel logistic regression models to assess the SRH status. We also added the interaction terms of socioeconomic status and type of health insurance as moderators. Medical aid (MA) recipients were 2.10 times more likely to have a low SRH status than those who were covered only by the NHI, even though the healthcare utilization was higher. When the interaction terms were included, those not covered by the NHI and had completed elementary school or less were 16.59 times more likely to have a low SRH status than those covered by the NHI and had earned a college degree or higher. Expanding healthcare coverage to reduce the burden of non-payment and unmet use to improve the health status of MA beneficiaries should be considered. Particularly, the vulnerability of less-educated groups should be focused on.

Innovation in the aftermath of downsizing: evidence from the threat-rigidity perspective

2020 ◽  
Vol 49 (9) ◽  
pp. 1859-1877
Author(s):  
José Fernández-Menéndez ◽  
Óscar Rodríguez-Ruiz ◽  
José-Ignacio López-Sánchez ◽  
María Isabel Delgado-Piña
Keyword(s):  
Regression Models ◽  
Negative Impact ◽  
Content Type ◽  
Logistic Regression Models ◽  
Marketing Innovation ◽  
Different Types ◽  
Threat Rigidity ◽  
The Impact ◽  
Research Show ◽  
Innovation Outcomes

PurposeThe purpose of this paper is to study how job reductions affect product innovation and marketing innovation in a sample of 2,034 Spanish manufacturing firms in the period 2007–2014.Design/methodology/approachPoisson and logistic regression models with random effects were used to analyse the impact of downsizing on some innovation outcomes of firms.FindingsThe results of this research show that the stressful measure of job reductions may have unexpected consequences, stimulating innovation. However downsizing combined with radical organisational changes such as new equipment, techniques or processes seems to have a negative impact on product and marketing innovation.Originality/valueThis research has two original features. First, it explores the unconventional direction of causality from the planned elimination of jobs to innovation outputs. Secondly, the paper looks at the combined effect of downsizing and other restructuring measures on different types of innovation. Following the threat-rigidity theory, we assume that this combination represents a major threat for survivors that leads to lower levels of product and marketing innovation.

Sign in / Sign up

Export Citation Format

Share Document