This study examines how factors affected individual return decision after Hurricane Katrina struck New Orleans City in 2005. Survey data from a representative sample of pre-Katrina New Orleans residents collected in the Displaced New Orleans Residents Pilot Survey (DNORPS) was used. The individual return decision was separated into three categories, namely, return, relocate and possible. Mixed logit model revealed that increasing age decreases the possibility of relocation and increases the possibility of return. Model estimation results also found that marital status, housing damage, housing tenure, education background, race and employment status are important predictors of individual decision. It was also determined that random-parameter approach is plausible in the return decision model. Housing damage and age are random parameters which were estimated using one-sided triangular distribution. Heterogeneity in the random parameter means were tested as a function of sex. The results further demonstrate the potential of the model to address unobserved heterogeneity in the analysis of return decision.