2012
DOI: 10.1007/s11577-012-0167-4
|View full text |Cite
|
Sign up to set email alerts
|

Modellvergleich und Ergebnisinterpretation in Logit- und Probit-Regressionen

Abstract: B e r i c h t e u n d d i s k u s s i o n e nZusammenfassung: Logit-und Probitregression werden als multivariate Analyseverfahren zur Analyse von dichotomen abhängigen Variablen in den sozialwissenschaften routinemäßig eingesetzt. Beide Verfahren können so interpretiert werden, dass sich aus einer linearen Modellierung einer unbeobachteten Variable y* eine nichtlineare Modellierung der Wahrscheinlichkeiten für y = 1 ergibt. Wir zeigen erstens, dass diese nichtlinearität im Vergleich zu linearen regressionsverf… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1
1

Citation Types

0
43
1
12

Year Published

2013
2013
2021
2021

Publication Types

Select...
3
3
1

Relationship

0
7

Authors

Journals

citations
Cited by 133 publications
(56 citation statements)
references
References 11 publications
0
43
1
12
Order By: Relevance
“…We report average marginal effects (AME), which are, in contrast to odds-ratios, intuitively interpretable and robust towards unobserved heterogeneity due to scaling issues that arise in non-linear regression analysis (see Best and Wolf 2012;Mood 2010). Based on this model we also estimate propensity scores for the following analysis on scarring effects.…”
Section: Resultsmentioning
confidence: 99%
“…We report average marginal effects (AME), which are, in contrast to odds-ratios, intuitively interpretable and robust towards unobserved heterogeneity due to scaling issues that arise in non-linear regression analysis (see Best and Wolf 2012;Mood 2010). Based on this model we also estimate propensity scores for the following analysis on scarring effects.…”
Section: Resultsmentioning
confidence: 99%
“…Mood (2010) points to the difficulty in finding estimates that enable to achieve all purposes in an analysis, as it is often requested by researchers 150 . In this regard, an appropriate solution suggested by Best and Wolf (2012) and which is used in this study, is the Average Marginal Effects (AME). AME represents the average effect of the independent variable on the probability that the event P(y=1|x) happens, and consider the easiest solution for the interpretation and comparison of the logistic regression coefficients.…”
Section: Cross-sectional Analysis: Logistic Regressionmentioning
confidence: 99%
“…the problem discussed above by Mood (2010) concerning the unobserved heterogeneity. In other words, AME offer the advantage that non-correlated non-observed heterogeneity will not be biased (Best & Wolf, 2012).…”
Section: Cross-sectional Analysis: Logistic Regressionmentioning
confidence: 99%
See 2 more Smart Citations