Nested Logit Analysis of Missing Response Observations.
ABSTRACT We propose a new estimation technique to deal with missing response variables in the context of a nested multinomial logit model. Survey data often have a significant number of incomplete or missing responses. If such data are systematically missing (i.e., not missing at random) and if such observations are deleted from the analysis, biased sample selection results. We apply our new method to the empirical analysis of determining job loss status.
[Show abstract] [Hide abstract]
ABSTRACT: A method to compute perfect values is developed for use with a weighted likelihood approach. It allows to obtain a direct one-iteration approximation for the parameter estimates. We study approximated perfect values applied to logistic regression and demonstrate their usefulness for predictive purposes when the response is missing. We also show that statistics for single-case outlier detection can be deduced. An empirical analysis to determine participation in a federal food-stamp program is presented to illustrate outlier detection and alternatives for estimating the probability of participation in the program. We compare results obtained with the new approach and those obtained maximizing the penalized log-likelihood function.Communication in Statistics- Theory and Methods 01/2003; No. 4(pp. 841–850):841-850. DOI:10.1081/STA-120018832 · 0.28 Impact Factor