Abstract
Hurdle regression models are regression models where the dependent variable is left censored at zero, which is typically the case in household expenditure surveys. These models are of particular interest to explain the presence of a large proportion of zero observations for the dependent variable by means of censoring mechanisms, called hurdles. For the analysis of censored household expenditure data, up to three hurdles, expressing respectively a good selection mechanism, a desired consumption mechanism and a purchasing mechanism, have been suggested by the econometric literature. This chapter presents the methodology for specifying single, double or triple hurdle regression models based on these censoring mechanisms in a fully parametric form and to estimate them using the maximum likelihood method for random samples. Model evaluation and selection are tackled by means of goodness of fit measures and Shi’s correted Vuong tests. The practical use of this modeling methodology is illustrated with a real-world data set using a package for R especially developed for this purpose.