PGR Student Presentation: Pam Nangsue - Adjusting for Nonresponse in the Analysis of Sample Survey Data, Jennifer Baird - Going Solo Revisited: The dynamics of living alone at older ages in two Nairobi slums Seminar

Pam Nangsue - Adjusting for Nonresponse in the Analysis of Sample Survey Data: Nonresponse in sample surveys has been increasing over the years. This paper is concerned with how to use observed data to make inference about regression coefficients in a linear regression model of cluster-level variables when some of the response variable data is missing. A naive approach estimates the regression coefficients without considering nonresponse. We propose new methods for estimating coefficients which incorporate information on nonresponse at the cluster level. The Workplace Employment Relations Survey (WERS) 2004 data is used to compare the new methods with the naive approach.

Jennifer Baird - Going Solo Revisited: The dynamics of living alone at older ages in two Nairobi slums: There has been little investigation into the living arrangements of older people in slum environments in sub-Saharan Africa. In this region, there is an assumption that older people live in the same household as their family with care and support for older people being closely interlinked with this coresidence with kin. Thus the living arrangements of older people are important indicators of their welfare and have the potential to highlight existing vulnerability among this group, with the decision to live alone having potentially adverse consequences for an older person. This research aims to explore this further by looking at the changes in living arrangements of older people in this environment over time and the events connected to this. The research is currently in the early stages and this presentation will detail the data being used and how this has been refined for analytical work. The study settings are two slums in Nairobi which are demographic surveillance systems and have yielded panel data on the household types of older people from 2002 through to 2006. These panels have been linked to an Older Persons Survey conducted in the same sites in 2006 with the aim that transitions in living arrangements for older people can be explored from 2002 to 2006, using event history analysis, with particular emphasis on the circumstances which lead to an older person moving from a multiple person household to a single person household. The research aims not just to understand the dynamics of living arrangements for older people in slum settings but to establish whether these moves can be viewed as positive or negative and if the latter is the case, whether there is need for a strengthening of both formal and informal types of support for older people in this context.