PME, the Brazilian Monthly Employment Survey, is a sample survey conducted monthly by IBGE since 1980 in six metropolitan areas: Belo Horizonte, Porto Alegre, Recife, Rio de Janeiro, Salvador and São Paulo. The survey collects labor and income information from the population. PME is mainly used to compute the main unemployment index in the country (until 2014). It is the only IBGE survey in longitudinal format. Households are visited for two periods of four consecutive months, eight months apart from each other. In March 2014, PME's sample consisted of 33,809 households with 95,122 individuals.
There are two versions of PME, traditionally called by PME-Antiga (old PME) and PME-Nova (new PME). The PME-Antiga is the original survey. In 2002, this survey underwent a major change in design, giving rise to the PME-Nova, with a significantly larger questionnaire and differences in the definition of labor market participation, as well as in the rotation scheme of the samples. Until the end of 2002, the two methodologies were taken to the field. In December 2002, PME-Antiga was closed down and replaced by PME-Nova.
The user can access the information collected by this survey through microdata. PME-Antiga microdata files are separated by month, metropolitan area and type of register (individual and household). PME-Nova contains a single file for each month including individual and household information for all metropolitan areas.
Data Zoom offers a package for each version of PME. Each package contains a tool for reading the microdata through STATA, generating STATA format files (.dta). All variables are named as suggested by IBGE’s dictionary. Data Zoom provides an English version of the original dictionaries for download. In order to use the package, the user must first obtain the microdata related to the rounds she is interested in. Data Zoom does not provide these data. For PME-Nova (March 2002 onwards), all microdata and documentation are available from IBGE’s website. For information on how to acquire other waves, click here.
We provide tools to correctly assess the longitudinal nature of the survey. Households are correctly identified throughout all eight interviews. However, PME does not assign the same identification number to each individual in the household across interviews. To reduce attrition related to this problem, each Data Zoom package offers two identification algorithms based on Ribas and Soares (2008). The algorithms differ essentially according to the number of characteristics checked in order to identify the same individual across interviews.
To install the packages, type "net from http://www.econ.puc-rio.br/datazoom/english" in STATA's command window and click on "datazoom_pmeantiga" or "datazoom_pmenova". Due to the large number of options available for the user and the need to insert information for the proper functioning of the programs, it is strongly recommended that you use the package via dialog box. To access it, type "db datazoom_pmeantiga" or "db datazoom_pmenova" in the command window. The package also has a help file to support the user. It can be accessed through the dialog box or by typing “help datazoom_pmeantiga" or "datazoom_pmenova” in the command window.