Regression with Missing X's: A Review

By Roderick J. A. Little. 2011

1,363 citations recorded by the source corpus.

Subfields: Management Science and Operations Research, Statistics and Probability

View Paper: https://www.semanticscholar.org/paper/deee8503ca9371916243783cd2026cc1bf47d296

How researchers see this paper

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

In Management Science and Operations Research

In Statistics and Probability

Citations in the corpus

A Review of Methods for Missing Data (2001, background): “Little (1992) shows that available case analysis provides consistent estimates (the correct point estimates, see e.g., Cox & Hinckley, 1974) when variables are moderately correlated in regression models.”
Missing data techniques for structural equation modeling. (2003, methodology): “One version of this approach has been shown to produce approximately unbiased estimates of regression coefficients when there are missing data on explanatory variables, under the MCAR assumption (Little, 1992).”
Bias From Censored Regressors (2009, methodology): “The estimation of a model with censored regressors often can be viewed as an estimation problem with missing data, as discussed by Little (1992) and Little and Rubin (2002), among many others.”
Much Ado About Nothing (2007, background): “It is possible to formally test the MCAR assumption against thealternatehypothesisofMAR(Little1988;Diggleetal.2002).”
The taxman tools up: An event history study of the introduction of the personal income tax (2009, methodology): “Linear interpolation seems a reasonable solution, although more sophisticated methods are available ( Little, 1992 ).”
New Confidence Intervals and Bias Comparisons Show That Maximum Likelihood Can Beat Multiple Imputation in Small Samples (2013, methodology): “…for the moments of X are obtained using the usual complete-data ML formulas: ̂ , 1 , 1 ̂ , (6) And ML estimates for the regression of Y on X can be obtained simply by ignoring the incomplete cases and applying OLS to the cases with Y observed (Anderson, 1957; Little, 1992; von Hippel, 2007).”
External validation is necessary in prediction research: a clinical example. (2003, methodology): “Simple exclusion of patients with missing values on one or more of the variables commonly causes biased results and decreases statistical efficiency [37,38].”
Analysis of Multivariate Longitudinal Outcomes With Nonignorable Dropouts and Missing Covariates (2002, background): “There is extensive literature on missing covariates for cross-sectional data (Little 1992; Little and Rubin 1987).”