Statistical Analysis With Missing DataAcknowledged experts on the subject bring together diverse sources on methods for statistical analysis of data sets with missing values, a pervasive problem for which standard methods are of limited value. Blending theory and application, it reviews historical approaches to the subject, and rigorous yet simple methods for multivariate analysis with missing values. Goes on to provide a coherent theory for analysis of problems based on likelihoods derived from statistical models for the data and the missing data mechanism. The theory is applied to a wide range of important missing-data problems. Extensive references, examples, and exercises. |
Contents
678 | 3 |
LIKELIHOODBASED APPROACHES TO | 77 |
Methods Based on Factoring the Likelihood Ignoring | 97 |
Copyright | |
6 other sections not shown
Common terms and phrases
adjustment cells algorithm analysis ANOVA assumption Bayesian bivariate normal block calculated categorical variables cell probabilities censoring Chapter completely observed component computations conditional distribution contingency table correlation covariance matrix data are MAR defined degrees of freedom denote discussed EM algorithm Example factor function given Hence hot deck incomplete data inferences interval iteration least squares estimates linear regression loglikelihood loglinear model marginal distribution maximizing Maximum likelihood estimation MCAR mean and covariance methods missing data missing values missing-data mechanism ML estimates monotone pattern multiple imputation multivariate normal multivariate normal distribution nonignorable nonresponse normal data normal distribution normal with mean obtained parameters partially classified pattern of missing population mean problem R₁ residual responding units Rubin sample mean sample surveys Section simple random sampling standard errors step sufficient statistics sum of squares Suppose U₁ Uinc vector X₁ Xobs Y₁ y₁₁ y₁₂ Y₂ yields Ymis Yobs zero σ²