ABSTRACT
Truncated samples from discrete distributions arise in numerous situations where counts of zero are not observed. As an example, consider the distribution of the number of children per family in developing nations, where records are maintained only if there is at least one child in the family. The number of childless families remains unknown. The resulting sample is thus truncated with the zero class missing. In a continuous distribution, a sample of this type would be described as singly left truncated. In other situations, samples from discrete distributions might be censored on the right. This occurs when for larger values of the random variable, sample data include only the information that a certain number of observations exceed a specified cutoff point. Similarly, in some situations, samples might be censored on the left, and on some occasions they might even be doubly censored or doubly truncated. In this chapter we consider truncated and censored samples from the Poisson, negative binomial, binomial, and hypergeometric distributions.
