• journals@UrMEL
  • UrMEL
  • Imprint
  • Privacy
  • Login
    • DE
  • advanced search
Search the entire inventorySearch within the journalSearch within the volume
  1. A-Z
  2. Jena Economic Resea...
  3. Volume 7
  4. Endogenous variable...
  1. « Zurück
  2. Weiter »
Endogenous variables in non-linear models with mixed effects: Inconsistence under perfect identification conditions?
Pictured person

Buscha, Franz

Conte, Anna

published
Sat Aug 10 2013
Number of discussion paper

2013-027

keyword(s)

bivariate ordered probit

bivariate probit

constant parameters

endogenous binary variables

mixed effects

abstract

This paper examines the consequences of introducing a normally distributed effect into a system where the dependent variable is ordered and the explanatory variable is ordered and endogenous. Using simulation techniques we show that a naïve bivariate ordered probit estimator which fails to take a mixed effect into account will result in inconsistent estimates even when identification conditions are optimal. Our results suggest this finding only applies to non-linear endogenous systems.

article pub. typess JER
Research article
article languages JER
Englisch
JEL-Classification for JER
C35 - Discrete Regression and Qualitative Choice Models ; C51 - Model Construction and Estimation