Biometrika Advance Access originally published online on September 16, 2009
Biometrika 2009 96(4):917-932; doi:10.1093/biomet/asp041
Article |
A unified approach to linearization variance estimation from survey data after imputation for item nonresponse
Department of Statistics, Iowa State University, Ames, Iowa 50011, U.S.A. jkim{at}iastate.edu
School of Mathematics and Statistics, Carleton University, Ottawa, Ontario K1S 5B6, Canada jrao{at}math.carleton.ca
Received for publication 1 March 2008. Revision received 1 February 2009.
Variance estimation after imputation is an important practical problem in survey sampling. When deterministic imputation or stochastic imputation is used, we show that the variance of the imputed estimator can be consistently estimated by a unifying linearize and reverse approach. We provide some applications of the approach to regression imputation, fractional categorical imputation, multiple imputation and composite imputation. Results from a simulation study, under a factorial structure for the sampling, response and imputation mechanisms, show that the proposed linearization variance estimator performs well in terms of relative bias, assuming a missing at random response mechanism.
Key Words: Composite imputation • Fractional imputation • Imputed estimator • Multiple imputation • Regression imputation
References
-
Chen J., Shao J. Jackknife variance estimation for nearest-neighbor imputation. J. Am. Statist. Assoc. (2001) 96:260–69.[CrossRef][Web of Science]
Davison A. C., Sardy S. Resampling variance estimation in surveys with missing data. J. Offic. Statist. (2007) 23:371–86.
Deville J.C., Särndal C. E. Variance estimation for the regression imputed Horvitz-Thompson estimator. J. Offic. Statist. (1994) 10:381–94.
Fay R. E. When are inferences from multiple imputation valid? In: Proc. Survey Res. Meth. Sect. Am. Statist. Assoc. (1992) Washington, DC: American Statistical Association. 227–32.
Fuller W. A., Kim J. K. Hot deck imputation under response model. Survey Methodol. (2005) 31:139–49.
Haziza D. Imputation and inference in the presence of missing data. In: Handbook of Statistics. Sample Surveys: Theory, Methods and Inference—Pfeffermann D., Rao C.R., eds. (2009) 29. Amsterdam: Elsevier BV. 215–46.
Kim J. K., Fuller W. A. Inference procedures for hot deck imputation. Biometrika (2004) 91:559–78.
Kim J. K., Brick M. J., Fuller W. A., Kalton G. On the bias of the multiple imputation variance estimator in survey sampling. In: J. R. Statist. Soc. (2006) B 68:509–21.[CrossRef]
McCullagh P., Nelder J. Generalized Linear Models (1989) London: Chapman & Hall.
Meng X.-L. Multiple-imputation inferences with uncongenial sources of input. Statist. Sci. (1994) 9:538–73.
Randles R. H. On the asymptotic normality of statistics with estimated parameters. Ann. Statist. (1982) 10:462–74.[CrossRef]
Rao J. N. K., Shao J. Jackknife variance estimation with survey data under hot deck imputation. Biometrika (1992) 79:811–22.
Rubin D. B. Multiple Imputation for Nonresponse in Surveys. (1987) New York: Wiley.
Särndal C. E. Methods for estimating the precision of survey estimates when imputation is used. Survey Methodol. (1992) 18:241–52.
Shao J., Steel P. Variance estimation for survey data with composite imputation and nonnegligible sampling fractions. J. Am. Statist. Assoc. (1999) 94:254–65.[CrossRef][Web of Science]
CiteULike 
Connotea 
Del.icio.us What's this?
| ||||||||||||||||||||||||||||||||||||||||||||||||