Censored Data

A very common problem in microeconomic data is censoring of the dependent variable. When the dependent variable is censored, values in a certain range are all transformed to (or reported as) a single value. Some examples that have appeared in the empirical literature are as follows:9

1. Household purchases of durable goods [Tobin (1958)],

2. The number of extramarital affairs [Fair (1977,1978)],

3. The number of hours worked by a woman in the labor force [Quester and Greene (1982)],

4. The number of arrests after release from prison [Witte (1980)],

7See Heckman (1979) who formulates this as a "specification error."

8See the appendix in Hausman and Wise (1977) and Greene (1983) as well.

9More extensive listings may be found in Amemiya (1984) and Maddala (1983).

5. Household expenditure on various commodity groups [Jarque (1987)],

6. Vacation expenditures [Melenberg and van Soest (1996)].

Each of these studies analyzes a dependent variable that is zero for a significant fraction of the observations. Conventional regression methods fail to account for the qualitative difference between limit (zero) observations and nonlimit (continuous) observations.

Was this article helpful?

0 0

Post a comment