Affiliations: [a] Mathematica Policy Research, Inc., P.O. Box 2393,
Princeton, NJ 08543-2393, USA | [b] The Center for Studying Health System Change,
Washington, DC, USA | [c] Medical Technology and Practice Patterns Institute,
Inc., Washington, DC, USA
Note: [1] The authors would like to thank Steven B. Cohen for statistical advice and
encouragement throughout this project; Steve Botman, Vicki Freedman, Margie
Odie, Jim Reschovsky, Iris Shimizu, John Sornrners, Bill Spector, and Brenda
Spillman for helpful cornrnents on an earlier version of this paper; Social
and Scientific Systems, Inc., Bethesda, MD for prograrnrning support; and
Dawn French for secretarial support. Most of the work for this paper was
carried out while the authors were at the Agency for Health Care Policy and
Research, Rockville, MD, USA. The views expressed in this paper are those of
the authors. No official endorsement by the Department of Health and Human
Services or the Agency for Health Care Policy and Research is intended or
should be inferred.
Abstract: This paper describes the methodology used in selecting and reweighting discharge
level data from the 1985 National Nursing Home Survey so that it represents a
sample of decedents who used nursing homes sometime during their lives. Such a
strategy allows for the analysis of lifetime nursing home use and financing with
a level of information that previously was not available. Adjustments to the
existing weight included those for unit nonresponse, multiple probabilities of
selection, and differential follow-up periods, as well as a ratio adjustment to
bring the distribution of nursing home users with and without use in the last
year of life in line with an external distribution from the 1986 National
Mortality Followback Survey. A comparison of weighted estimates is made between
the reweighted Nursing Home Survey data and the Mortality Followback data.
