Modelling of correlated soil animals count data

Show simple item record Debusho, Legesse Kassa Sileshi, Gudeta W. 2013-07-16T12:26:42Z 2013-07-16T12:26:42Z 2012-11
dc.description.abstract Ecological studies naturally result in correlated data. Ignoring these correlations can result in biased estimation of ecological effects jeopardizing the integrity of the scientific inference. Mixed effects models are likely to appeal to ecologists for handling correlated data (e.g. Sileshi, 2008), however careful consideration must be given to the interpretation of the parameter estimates from generalized linear mixed effects models with non-identity link functions. The objective of this study was to compare the generalized estimating equations (GEE) under different correlation structures and suggest appropriate models to describe the relationship between soil animal counts and covariates. The GEE with independence, exchangeable and AR1 correlation structures were compared using count data set of ants from soils under the agroforestry systems in eastern Zambia. The GEE model with AR1 correlation structure gave a better description of the data than did the independence and exchangeable correlation structures. en_US
dc.description.librarian am2013 en_US
dc.description.uri en_US
dc.identifier.citation Debusho, LK & Sileshi, GW 2012, 'Modelling of correlated soil animals count data', South African Statistical Journal, no. sp 1, pp. 75-82. en_US
dc.identifier.issn 0038-271X
dc.language.iso en en_US
dc.publisher South African Statistical Association en_US
dc.rights South African Statistical Association en_US
dc.subject.lcsh Soil animals en
dc.title Modelling of correlated soil animals count data en
dc.type Article en

Files in this item

This item appears in the following Collection(s)

Show simple item record