Andrew M. Jones and Jose M. Labeaga, "Individual Heterogeneity and Censoring
in Panel Data Estimates of Tobacco Expenditure", Journal of Applied
Econometrics, Vol. 18, No. 2, 2003, pp. 157-177.

The data used in this paper come from the Encuesta Continua de Presupuestos
Familiares (ECPF). This is a quarterly survey conducted by the Instituto
Nacional de Estadistica (National Bureau of Statistics) with approximately
3200 households surveyed each quarter and a rotating rate of 12.5 per cent.
We have selected a sample formed by the balanced panel in which each
household provides information for eight quarters. The sample used
in the paper has N=6100 households and T=8, so the final sample size is
48800 observations.

The definitions of the variables can be found in the code-book for the survey,
which can be obtained from the Instituto Nacional de Estadistica (the web
page is http://www.ine.es). The price of tobacco, the retail price index and
the weights of the expenditure categories can also be obtained from the
Instituto Nacional de Estadistica.

The data are in the file tobacco.data, an ASCII file in DOS format that is
zipped in the file jl-data.zip. Unix users should use "unzip -a".

The data are organised by household and date, i.e., the first eight
observations correspond to the first household and are in ascending order by
date, the next eight correspond to the second household, and so on.

The variables for each household and date are in the following order:

  Identification of the household
  Date of the interview (formed by year -two digits- and quarter -last digit-)
  Number of the collaborating period
  Real tobacco consumption
  Real price of tobacco
  Number of males in the household
  Number of females in the household
  Number of adults in the household
  Number of children aged less than 6 years old
  Number of children aged between 7 and 14 years old
  Number of children aged between 15 and 23 years old
  Age of the head of the household
  Age of the partner
  Gender of the head of the household (male=1)
  No educational backgroud = 1
  Primary education = 1
  Pre-university studies = 1
  University degree = 1
  Dummy for self-employed
  Dummy for unemployed
  Dummy for not active
  Dummy for skilled worker
  Dummy for owing second home
  Dummy for residence in rural area
  Dummy for residence in city