Page 334 - Contributed Paper Session (CPS) - Volume 4

CPS2253 Gabrielle Palermo

Weighting Longitudinal School Surveys with
population changes: The case of Geres
Gabrielle Palermo
University of Southampton (UK)

Abstract
The Longitudinal Study of the 2005 School Generation (Geres) is the first
survey of its kind successfully achieved and remain the only one in Brazil. It
aimed to observe pupils’ achievements in mathematics and reading, and
changes in individual performance and school characteristics over junior
school years, from 2005 to 2008 in five cities: Rio de Janeiro, Belo Horizonte,
Campinas, Campo Grande and Salvador. All pupils that were registered in the
1st grade of the selected schools made up the Geres sample for the first wave.
They were followed by five waves, two in 2005 and one every year from 2006
to 2008. Also, the survey tracked additional pupils that joined the main grade
currently in each wave in the selected schools. Each city represents one
stratum, and they were divided into three to four strata according to the
schools’ administration system: state, municipal, private and exceptional
schools. The survey had 17 strata in total, and they were called explicit strata.
The published weights include weights for the explicit strata at wave 1.
Furthermore, the survey report (Brooke and Bonamino, 2011) explained the
implicit stratification, where each explicit stratum was divided by up to eight
groups, according to the school size and socio-economic levels. This report
defined weights for the first wave only, for schools and pupils separately,
though incomplete for pupils. There was not a subsample into the selected
schools, then the inclusion probability of the selected pupils was the same as
their school. The municipal schools of Rio de Janeiro were chosen to be
studied. Following the weights’ report of the survey, we computed the weights
for all pupils from the first wave to estimate the total of pupils and compared
the same estimation but using different estimators, considering only the
schools’ weights for explicit and implicit strata. We proposed to compute the
total of pupils that repeated one or more grades considering this observation
at wave 4. Different cross-sectional weights were proposed, according to the
population of interested. Longitudinal weights for pupils observed at wave 4,
considering some of the combinations of the previous waves were also
estimated.

Keywords
Educational survey; Mobility; Weight share method; Cross-sectional estimates.

323 | I S I W S C 2 0 1 9