Your Cart

Your cart is empty

Home  >  Volume 38

25. Estimation of Covariance Structures for Repeated Measure Under Normal Distribution by Ishaq O.O,James Tolulope O., A. Danbaba and A. Ayodele Volume 38, (November, 2016), pp 179 – 184
Sale price: $5.00
Quantity:

Abstract

Repeated measures analyses of variance are themethods of choice in many studies from experimental psychologyand the neurosciences. One of the major problems in conducting repeated measures analysis is the sphericity assumption. The consequences of applying univariate or multivariate repeated measure methods when this assumption is violated lead to inappropriate use of covariance structure. Recently,there are very fewcomparative studies that have been done so far but such comparisons do not compare them in terms of probability distributions, different sample sizes and simulation techniques.The eight covariance structures used in the study are: Compound symmetry (CS), Unstructured (UN) covariance structure, First order-auto regressive (AR (1)), Heterogeneous first order-auto regressive (ARH(1)), Heterogeneous compound symmetry (CSH),Huynh-Feldt (HF), Toeplitz Covariance structure and First order-autoregressive-moving average (ARMA1,1). The Goodness of fit criteria used to evaluate the performances of covariance structures were Akaike information criterion (AIC), Burnham-Handerson criterion (AICC) and Schwartz’s Bayes criterion (SBC).The results show that Unstructured (UN) covariance structurewas found to be the best covariance structures to fit a data that follows normaldistribution across all the different sample sizes considered in this study.

Keywords: Akaike information criterion, Burnham-Handerson criterion, Schwartz’s Bayes criterion, Covariance Structures

Close
Loading...