Tests of homogeneity of means and covariance matrices for multivariate incomplete data

By Kevin H. Kim, Peter M. Bentler. 2002

91 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Food Science, Statistics and Probability

View Paper: https://www.semanticscholar.org/paper/519ecb6c053d8c94ee2719ce6e6256b1c2a8d211

How researchers see this paper

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

In Artificial Intelligence

In Food Science

In Statistics and Probability

Citations in the corpus

Little's Test of Missing Completely at Random (2013, background): “5 Simulation study In this section, I evaluate the performance of Little’s χ(2) test of MCAR and CDM through simulation studies. In general, when the true missing-data mechanism is MCAR, the empirical rejection probability of Little’s test of MCAR fits well with the nominal significance level, with ”
Mardia's Multivariate Kurtosis with Missing Data (2004, methodology): “There exist tests for the MCAR mechanism (Kim & Bentler, 2002; Little, 1988); if a MCAR mechanism test is passed, then one can use Equation 13 to see if the data set has a multivariate kurtosis that is significantly different from that of a normal distribution.”
Is the ML Chi-Square Ever Robust to Nonnormality? A Cautionary Note With Missing Data (2008, background): “We also assume that xj has mean j and covariance matrix †j, which are appropriate subvectors and submatrices of the overall and †. This homogeneity of means and covariance matrices is a consequence of the MCAR assumption ( Kim & Bentler, 2002 ).”
A Two-Stage Approach to Missing Data: Theory and Application to Auxiliary Variables (2009, methodology): “This is only possible if we make the assumption of homogeneity of means and covariances (HMC) across missing data patterns, which is a consequence of the MCAR assumption (Kim & Bentler, 2002).”
A Statistically Justified Pairwise ML Method for Incomplete Nonnormal Data: A Comparison With Direct ML and Pairwise ADF (2005, methodology): “Several tests of the MCAR assumption for normal data are available (e.g., Kim & Bentler, 2002), and when this assumption is violated, researchers are usually urged to exercise caution when interpreting their findings, because one cannot further test whether the data are MAR or NMAR.”