Another Look at the Method of Y-Standardization in Logit and Probit Models
Research output: Contribution to journal › Journal article › Research › peer-review
Standard
Another Look at the Method of Y-Standardization in Logit and Probit Models. / Karlson, Kristian Bernt.
In: Journal of Mathematical Sociology, Vol. 39, No. 1, 01.2015, p. 29-38.Research output: Contribution to journal › Journal article › Research › peer-review
Harvard
APA
Vancouver
Author
Bibtex
}
RIS
TY - JOUR
T1 - Another Look at the Method of Y-Standardization in Logit and Probit Models
AU - Karlson, Kristian Bernt
PY - 2015/1
Y1 - 2015/1
N2 - This paper takes another look at the derivation of the method of Y-standardization used in sociological analysis involving comparisons of coefficients across logit or probit models. It shows that the method can be derived under less restrictive assumptions than hitherto suggested. Rather than assuming that the logit or probit fixes the variance of the latent error at a known constant, it suffices to assume that the variance of the error is unknown. A further result suggests that using Y-standardization for cross-model comparisons is likely to be biased by model differences in the fit of the latent error to the assumed logistic or normal distribution. Under correct specification Y-standardization recovers an effect size metric similar to Cohen's d.
AB - This paper takes another look at the derivation of the method of Y-standardization used in sociological analysis involving comparisons of coefficients across logit or probit models. It shows that the method can be derived under less restrictive assumptions than hitherto suggested. Rather than assuming that the logit or probit fixes the variance of the latent error at a known constant, it suffices to assume that the variance of the error is unknown. A further result suggests that using Y-standardization for cross-model comparisons is likely to be biased by model differences in the fit of the latent error to the assumed logistic or normal distribution. Under correct specification Y-standardization recovers an effect size metric similar to Cohen's d.
U2 - 10.1080/0022250X.2014.897950
DO - 10.1080/0022250X.2014.897950
M3 - Journal article
VL - 39
SP - 29
EP - 38
JO - Journal of Mathematical Sociology
JF - Journal of Mathematical Sociology
SN - 0022-250X
IS - 1
ER -
ID: 90550196