Analysis of Incomplete Multivariate Data

By David E. Booth. Technometrics, 2000

4,388 citations recorded by the source corpus.

View Paper: https://www.semanticscholar.org/paper/36ed58fa79c9600be66ab88637293b1dc5526efd

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Statistics and Probability

Citations in the corpus

Resilience in parenting among young mothers: Family and ecological risks and opportunities (2011, methodology): “03 software program (Schafer, 1997); analysis based on two imputations provides much better inference than just using one imputed database (Graham et al.”
Stress, Marital Satisfaction, and Psychological Distress Among African Americans (2010, methodology): “In regression analyses, multiple imputation was used to generate values for missing data on all variables using a Markov chain Monte Carlo method (Schafer, 1997; Schafer & Graham, 2002).”
Model averaging, missing data and multiple imputation: a case study for behavioural ecology (2010, methodology): “On the other hand, the distinction between MAR and MNAR is very difficult in many cases because we usually do not have information about missing values, which is required to determine if missing observations are MNAR (Schafer 1997; McKnight et al. 2007).”
Parent Involvement as Parental Monitoring of Student Motivation and Parent Expectations Predicting Later Achievement Among African American and European American Middle School Age Students (2002, methodology): “Data files used in this study were prepared using the NORM (Version 2.02) program developed by Schafer (1997).”
Learning Gaussian Process Kernels via Hierarchical Bayes (2004, methodology): “An efficient EM-based solution for the case σ = 0 is also given by [9].”
Multiple Imputation Using SAS Software (2011, methodology): “Repeatedly simulating steps of the chain simulates draws from the distribution of interest Schafer (1997).”
Mardia's Multivariate Kurtosis with Missing Data (2004, methodology): “Assuming ignorable missing data mechanisms for this data set as in Schafer (1997), we first check whether the observed marginals for these nine missing variables sit in a cluster with a restricted range.”
Latent Class Analysis With Distal Outcomes: A Flexible Model-Based Approach (2013, methodology): “The missing data literature provides relevant insight into the impact of imputing data under a model that is more restrictive than the analysis model (e.g., Collins, Schafer, & Kam, 2001; Schafer, 1997).”
Nearest neighbor imputation algorithms: a critical evaluation (2016, neutral): “These comprise: 15 variables drawn from a non-central chi square distribution with μ = [10, 50] and degree of freedom = [2, 5], 20 normally-distributed variables with μ = [10, 200] and ϭ = μ/5, 3 blocks of 3 variables drawn from a multinormal distribution with μ = [10, 100] and ϭ = [μ/5, μ/2] and 3 ”
An Introduction to Intermediate and Advanced Statistical Analyses for Sport and Exercise Scientists (2015, methodology): “The analyses were done on five imputed data sets and the results were combined automatically by Mplus using the Rubin (1987; Schafer, 1997) strategy to obtain unbiased parameter estimates, standard errors, and goodness of fit statistics.”
Latent Class Modeling with Covariates: Two Improved Three-Step Approaches (2010, methodology): “This could be repeated several times, yielding a procedure similar to multiple imputation (Rubin 1987; Schafer 1997).”
Measurement Equivalence of the Job Descriptive Index Across Chinese and American Workers: Results from Confirmatory Factor Analysis and Item Response Theory (2005, methodology): “The FIML procedure contains an expectation maximization algorithm that handles multiple imputations of missing values (Schafer, 1997).”
The imputation of wages above the contribution limit with the German IAB employment sample (2005, background): “discussion of the problems with imputation of missing data is found in Little and Rubin (1987); Schafer (1997) ).”
Changing the ideological roots of prejudice: Longitudinal effects of ethnic intergroup contact on social dominance orientation (2014, methodology): “Applying maximum likelihood procedures has been shown to produce more reliable parameter estimates and standard errors as compared to conventional methods of dealing with missing data, for example, pair-wise or list-wise deletion (Schafer, 1997; Schafer & Graham, 2002; see also Al Ramiah & Hewstone,”
Perceived fit with an academic environment: Attitudinal and behavioral outcomes (2008, methodology): “Using a likelihood function that assumes the missing data structure is conditional only on the variables in the model and not unspecified variables external to the model (i.e., data are missing at random, Schafer, 1997 ), the expectation–maximization algorithm was used to generate missing values te”
Small-sample degrees of freedom for multi-component significance tests with multiple imputation for missing data (2007, methodology): “Multiple imputation (Rubin, 1987) has been used to handle missing data in both large samples (Heitjan & Little, 1991; Schafer et al., 1998; Raghunathan & Paulin, 1998) and modest samples; see, for example, the examples in Schafer (1997).”