On the estimation of latent variable models of health, with an application to the health- investment behaviour of the British elderly

Publication type

Research Paper

Series Number



Working Papers of the ESRC Research Centre on Micro-Social Change


Publication date

November 1, 1998


The estimation of econometric latent variable models of health has been hampered by the impracticability of existing 'Feasible' Generalised Least Squares methods for data of mixed scale types. This paper proposes a new FGLS estimator that can be implemented with smaller samples, enables more variables to be analysed, and yields asymptotically correct x2 goodness-of-fit statistics and standard errors. The new approach is applied to the estimation of health-investment equations for elderly men and women, using data from the 1991 and 1995 waves of the British Household Panel Survey. The results help to reconcile conflicting evidence from the economic and epidemiologic literatures on the link between poor health and low socioeconomic status at old age.



working paper



Latest findings, new research

Publications search

Search all research by subject and author


Researchers discuss their findings and what they mean for society


Background and context, methods and data, aims and outputs


Conferences, seminars and workshops

Survey methodology

Specialist research, practice and study

Taking the long view

ISER's annual report


Key research themes and areas of interest