Working With Missing Values

By A. Acock. 2005

1,929 citations recorded by the source corpus.

View Paper: https://www.semanticscholar.org/paper/4b3a1e76df91cbe05ea2a39e6aad59e20931bffd

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

The psychological impact of intragenerational social class mobility (2011, methodology): “Multiple imputation has several advantages over other strategies of handling missing data and provides unbiased estimates for standard errors (Acock, 2005, p. 1020).”
Perceived Marginalization and the Prediction of Romantic Relationship Stability (2007, methodology): “able sample size, permits the use of traditional approaches to handling missing data (Acock, 2005).”
Trajectories of psychological need satisfaction from early to late adolescence as a predictor of adjustment in school (2014, methodology): “Because longitudinal research inevitably entails missing data, we imputed the data to correct for loss of statistical power, as well as diminished precision of and biases in estimates that result from pairwise and listwise deletion (see Acock, 2005; Peugh & Enders, 2004; Schafer & Graham, 2002).”
Early gender differences in self-regulation and academic achievement. (2009, methodology): “Expectation maximization is a maximum likelihood single imputation procedure using all available variables in the data set on participants to iteratively calculate values for missing data (Acock, 2005).”
Taking Stock of the Relationship Between Gang Membership and Offending (2016, methodology): “To avoid the systematic bias associated with removing these cases, missing standard errors were computed using multiple imputation (Acock, 2005; Allison, 2002; White, Royston, & Wood, 2011).”
A structured observation of behavioral self-regulation and its contribution to kindergarten outcomes. (2009, methodology): “, listwise deletion or mean imputation) can produce biased parameter estimates (Acock, 2005; McCartney, Burchinal, & Bub, 2006), we used multiple imputation to create 10 data sets with the PROC MI command in SAS.”
The Construct of Creativity: Structural Model for Self‐Reported Creativity Ratings (2009, background): “Gender, in particular, has been shown to be a predictor of missingness in self-report surveys (Acock, 2005).”