Approximate Bayesian inference under informative sampling

Summary Statistical inference with complex survey data is challenging because the sampling design can be informative, and ignoring it can produce misleading results. Current methods of Bayesian inference under complex sampling assume that the sampling design is noninformative for the specified model. In this paper, we propose a Bayesian approach which uses the sampling distribution of a summary statistic to derive the posterior distribution of the parameters of interest. Asymptotic properties of the method are investigated. It is directly applicable to combining information from two independent surveys and to calibration estimation in survey sampling. A simulation study confirms that it can provide valid estimation under informative sampling. We apply it to a measurement error problem using data from the Korean Longitudinal Study of Aging.

[1]  V. P. Godambe,et al.  Parameters of superpopulation and survey population: their relationships and estimation , 1986 .

[2]  R. Little.  To Model or Not To Model? Competing Modes of Inference for Finite Population Sampling , 2004 .

[3]  Regression Analysis for Complex Survey Data with Missing Values of a Covariate , 1996 .

[4]  Edward L. Korn,et al.  Analysis of Health Surveys , 1999 .

[5]  Minge Xie,et al.  Combining information from independent sources through confidence distributions , 2005, math/0504507.

[6]  R. Sugden,et al.  Ignorable and informative designs in survey sampling inference , 1984 .

[7]  David Firth,et al.  Robust models in probability sampling , 1998 .

[8]  D.Sc. Joseph Berkson.  Are there Two Regressions , 1950 .

[9]  Michael R Elliott,et al.  A nonparametric method to generate synthetic populations to adjust for complex sampling design features. , 2014, Survey methodology.

[10]  J. Monahan,et al.  Proper likelihoods for Bayesian analysis , 1992 .

[11]  D. Horvitz,et al.  A Generalization of Sampling Without Replacement from a Finite Universe , 1952 .

[12]  Richard Valliant,et al.  Finite population sampling and inference : a prediction approach , 2000 .

[13]  J. N. K. Rao,et al.  Combining data from two independent surveys: a model-assisted approach , 2012 .

[14]  T. Merkouris,et al.  Combining information from multiple surveys by using regression for efficient small domain estimation , 2010 .

[15]  R. Little,et al.  Bayesian penalized spline model-based inference for finite population proportion in unequal probability sampling. , 2010, Survey methodology.

[16]  D. Binder.  On the variances of asymptotically normal estimators from complex surveys , 1983 .

[17]  Roderick J. A. Little,et al.  Calibrated Bayes, an alternative inferential paradigm for official statistics , 2012 .

[18]  E. Korn,et al.  Analysis of Health Surveys: Korn/Analysis , 1999 .

[19]  Guosheng Yin,et al.  Bayesian generalized method of moments , 2009 .

[20]  Edward L. Korn,et al.  Examples of Differing Weighted and Unweighted Estimates from a Sample Survey , 1995 .

[21]  D. Pfeffermann.  The Role of Sampling Weights when Modeling Survey Data , 1993 .

[22]  W. Gilks,et al.  Adaptive Rejection Metropolis Sampling Within Gibbs Sampling , 1995 .

[23]  Kimberly D. Zieschang.  Sample Weighting Methods and Estimation of Totals in the Consumer Expenditure Survey , 1990 .

[24]  Taesung Park,et al.  Statistical Matching using Fractional Imputation , 2015, 1510.03782.

[25]  Danny Pfeffermann,et al.  Multi-level modelling under informative sampling , 2006 .

[26]  Danny Pfeffermann,et al.  PARAMETRIC DISTRIBUTIONS OF COMPLEX SURVEY DATA UNDER INFORMATIVE PROBABILITY SAMPLING , 1998 .

[27]  Robert Chambers,et al.  Analysis of survey data , 2003 .