A Three‐Stage Estimator for Studies with Repeated and Possibly Missing Binary Outcomes

Stuart R. Lipsitz, Nan M. Laird and David P. Harrington

Journal of the Royal Statistical Society Series C, 1992, vol. 41, issue 1, 203-213

Abstract: This paper describes methods for analysing repeated measures data when the outcome is binary at each occasion. The models relate the expected value of the binary response at each occasion to covariates via the logistic link function. The method of estimation is a three‐stage, generalized least squares method and is similar to the methods described by Ware and Jennrich and Schluchter for repeated continuous outcomes. The estimates are asymptotically equivalent to the estimates obtained from Liang and Zeger's 'generalized estimating equations' but have the advantage that they exist in some situations (i.e. small sample sizes, unbalanced data) when the Liang and Zeger estimates do not and can be computed using a newly available statistical package (BMDP 5V) designed for analysing unbalanced repeated continuous responses. Residual diagnostics are also briefly discussed.

Date: 1992
References: Add references at CitEc
Citations: View citations in EconPapers (3)

Downloads: (external link)
https://doi.org/10.2307/2347629

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:bla:jorssc:v:41:y:1992:i:1:p:203-213

Ordering information: This journal article can be ordered from
http://ordering.onli ... 1111/(ISSN)1467-9876

Access Statistics for this article

Journal of the Royal Statistical Society Series C is currently edited by R. Chandler and P. W. F. Smith

More articles in Journal of the Royal Statistical Society Series C from Royal Statistical Society Contact information at EDIRC.
Bibliographic data for series maintained by Wiley Content Delivery ().