J. Mullahy, INSTRUMENTAL-VARIABLE ESTIMATION OF COUNT DATA MODELS - APPLICATIONS TO MODELS OF CIGARETTE-SMOKING BEHAVIOR, Review of economics and statistics, 79(4), 1997, pp. 586-593
As with most analyses involving microdata, applications of count data
models must somehow account for unobserved heterogeneity. The count mo
del literature has generally assumed that unobservables and observed c
ovariates are statistically independent. Yet for many applications thi
s independence assumption is clearly tenuous. When the unobservables a
re omitted variables correlated with included regressors, standard est
imation methods will generally be inconsistent. Though alternative con
sistent estimators may exist in special circumstances, it is suggested
here that a nonlinear instrumental-variable strategy. offers a reason
ably general solution to such estimation problems. This approach is ap
plied in two examples that focus on cigarette smoking behavior.