Skip to main content
ARS Home » Southeast Area » Mississippi State, Mississippi » Crop Science Research Laboratory » Genetics and Sustainable Agriculture Research » Research » Publications at this Location » Publication #236549
Title: Testing variance components by two jackknife methods

Author
item WU, JIXIANG - MISSISSIPPI STATE UNIV
item Jenkins, Johnie
item McCarty, Jack

Submitted to: Applied Statistics In Agriculture Conference Proceedings
Publication Type: Proceedings
Publication Acceptance Date: 12/1/2008
Publication Date: 12/15/2008
Citation: Wu, J., Jenkins, J.N., McCarty Jr., J.C. 2009. Testing variance components by two jackknife methods. In: Applied Statistics In Agriculture Conference Proceedings, April 27-29, 2008, Manhattan, KS. pp. 1-17.

Interpretive Summary: A re-sampling technique, known as the jackknife method, has been widely used for statistical tests. The jackknife method is pseudo value based and is commonly used to reduce bias for an estimate. Sometimes there are large variations for an estimate which reduces the power of the test. In this study the common jackknife method was compared to a non-pseudo based method for testing variance components. Based on simulated results biases obtained by the two jackknife methods were similar; however, the non-pseudo value based method had lower error rates and higher testing power. It was concluded that the non-pseudo value based jackknife method was superior to the common jackknife method for testing variance components when using a general mixed linear statistical model.

Technical Abstract: The jacknife method, a resampling technique, has been widely used for statistical tests for years. The pseudo value based jacknife method (defined as pseudo jackknife method) is commonly used to reduce the bias for an estimate; however, sometimes it could result in large variaion for an estmimate and thus reduce the power for parameters of interest. In this study, a non-pseudo value based jackknife method (defined as non-pseudo jackknife method) was used for testing variance components under mixed linear models. We compared this non-pseudo value based jackknife method and the pseudo value based method by simulation regarding their biases, Type I errors, and powers. Our simulated results showed that biases obtained by the two jackknife methods are very similar; howeveer, the non-pseudo value based method had higher testing powers than the pseudo value based method while the non-pseudo value based method had lower Type I error rates than the preset nominal probability values. Thus, we concluded that the non-pseudo value based jackknife method is superior to the pseudo value based method for testing variance components under a general mixed linear model.