TEACHER'S CORNER: How Many Imputations Are Needed? A Comment on Hershberger and Fisher (2003)

66 citations recorded by the source corpus.

How researchers see this paper

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

New Confidence Intervals and Bias Comparisons Show That Maximum Likelihood Can Beat Multiple Imputation in Small Samples (2013, background): “Storage and runtime are not major concerns in small samples, but can be serious issues in large samples, particularly if the analysis runs slowly on each imputed dataset (von Hippel, 2005).”
What Improves with Increased Missing Data Imputations? (2008, background): “In response, von Hippel (2005) challenged the sampling theory approach, clariﬁed Rubin’s earlier work on this topic, and was generally thankful for practical reasons that so many imputations were in fact not needed.”
On Obtaining Estimates of the Fraction of Missing Information From Full Information Maximum Likelihood (2012, background): “An estimate of œj can therefore be useful in determining how many imputations are needed to achieve reasonable relative efficiency (Allison, 2002; Rubin, 1987; von Hippel, 2005).”
The role of adolescents’ hopeful futures in predicting positive and negative developmental trajectories: Findings from the 4-H Study of Positive Youth Development (2011, methodology): “However, with recent improvement in computer software, recent work to clarify optimal numbers of imputation, and taking a conservative stance on the number of imputations (Bodner, 2006; Graham, 2009; von Hippel, 2005), analyses for this study were conducted on 100 imputed data sets.”