Improved Wealth Measures in the Health and Retirement Study Asset Reconciliation and Cross-Wave Imputation

Michael Hurd (), Erik Meijer, Michael Moldoff and Susann Rohwedder

No WR-1150, Working Papers from RAND Corporation

Abstract: In this report, we present improved wealth measures for the Health and Retirement Study (HRS), which aim to reduce the effect of observation error on wealth levels and changes in wealth. The new wealth measures take account of the asset verification section in the HRS and use cross-wave information, most notably the value of the same asset in adjacent waves, in the imputation models, so imputed values better preserve serial correlation in the asset values. We document how we dealt with several methodological challenges in the implementation of these improvements. The corrections from the asset verification data reduce the standard deviations of wave-to-wave changes by substantial amounts (up to 57 percent for total wealth). The most important effect of the cross-wave imputations is a considerable reduction of the number of spikes and trenches (large changes in value followed by large changes back).

JEL-codes: C81 D14 D31 (search for similar items in EconPapers)
Pages: 79 pages
Date: 2016-04
References: Add references at CitEc
Citations: View citations in EconPapers (10)

Downloads: (external link)
https://www.rand.org/content/dam/rand/pubs/working ... 1150/RAND_WR1150.pdf (application/pdf)
Our link check indicates that this URL is bad, the error code is: 403 Forbidden

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:ran:wpaper:wr-1150

Access Statistics for this paper

More papers in Working Papers from RAND Corporation Contact information at EDIRC.
Bibliographic data for series maintained by Benson Wong ().