Multiple Imputation for Nonresponse in Surveys
Demonstrates how nonresponse in sample surveys and censuses can be handled by replacing each missing value with two or more multiple imputations. Clearly illustrates the advantages of modern computing to such handle surveys, and demonstrates the benefit of this statistical technique for researchers who must analyze them. Also presents the background for Bayesian and frequentist theory. After establishing that only standard complete-data methods are needed to analyze a multiply-imputed set, the text evaluates procedures in general circumstances, outlining specific procedures for creating imputations in both the ignorable and nonignorable cases. Examples and exercises reinforce ideas, and the interplay of Bayesian and frequentist ideas presents a unified picture of modern statistics.
What people are saying - Write a review
We haven't found any reviews in the usual places.
Probability Distributions and Related Calculations
UNDERLYING BAYESIAN THEORY
The Posterior Cumulative Distribution Function of Q
The Conditional Distribution of Q Ux Given
SmallSample Monte Carlo Coverages of Asymptotically
PROCEDURES WITH IGNORABLE NONRESPONSE
Some Explicit Imputation Models with Univariate V
PROCEDURES WITH NON1GNORABLE
Formal Tasks with Nonignorable Nonresponse
5 The Imputation and Estimation Tasks with
Analysis of MultiplyImputed Data
approximately assume asymptotic average Bayesian Bayesian inference Chapter complete-data inferences complete-data statistics completed data set components conditional distribution covariates coverage degrees of freedom distribution of Q draw drawn values estimand estimation task evaluated example followed-up nonrespondents fraction of missing function given Sm hot-deck ignorable nonresponse imputation task imputed values interval estimate large samples linear regression matrix mean and variance missing data missing information missing values missingness mixture modeling modeling task monotone pattern multiple imputations multiply-imputed data set multivariate nominal level nonre notation observed values p-value parameters population posterior distribution posterior mean posterior probability prior distribution priori independent probability problem proper imputation methods public-use data bases Q given random variable random-response randomization-based reference distribution repeated imputations repeated-imputation response mechanism Rinc Rubin sampling mechanism Section significance level simple random sample specification standard complete-data standard errors Suppose Table tion unconfounded units univariate Yobs
Page 245 - An Overview of Hot-Deck Procedures." in Incomplete Data in Sample Surveys (Vol. 2): Theor\ ana
Page 247 - L (1983). Incomplete Data in Sample Surveys. Volume 3, Proceedings of the Symposium. New York: Academic Press. Madow, WG, Olkin. I., and Rubin. DB (1983). Incomplete Data in Sample Surveys, Volume 2, Theory and Bibliographies. New York: Academic Press, Marini, MM, Olsen.