Lazic, Stanley (2015) Analytical strategies for the marble burying test: avoiding impossible predictions and invalid p-values. BMC Research Notes.

Abstract

The marble burying test is increasingly being used to measure repetitive and anxiety-related behaviour in rodents. The number of marbles that animals bury are non-negative integers, which are bounded below by zero and above by the number of marbles present. These data are typically analysed using t-tests and analysis of variance (ANOVA), which assume that the values are unbounded and that the variance is constant across groups. These requirements are rarely met with this type of data, leading to 95% con�dence intervals that can include impossible values (less than zero or greater than the number of marbles present) and misleading p-values. Transforming the data or using nonparametric methods are common alternatives but transformations do not always work well and nonparametric methods have a number of drawbacks. A better option in many cases is to use generalised linear models (GLMs), which have been developed to deal with count and other types of data, are straightforward to use and interpret, and will lead to more sensible inferences. GLMs are briefly described and compared with alternative methods on an example marble burying data set.

Item Type:	Article
Date Deposited:	13 Oct 2015 13:12
Last Modified:	04 Jul 2016 23:45
URI:	https://oak.novartis.com/id/eprint/22819