D-optimal population designs for the simple linear random coefficients regression model
dc.contributor.author | Debusho, Legesse Kassa | |
dc.contributor.author | Haines, Linda M. | |
dc.contributor.email | legesse.debusho@up.ac.za | en_US |
dc.date.accessioned | 2012-02-27T12:56:36Z | |
dc.date.available | 2012-02-27T12:56:36Z | |
dc.date.issued | 2010-11 | |
dc.description.abstract | In this paper D-optimal population designs for the simple linear random coefficients regression model with values of the explanatory variable taken from a set of equally spaced, non-repeated time points are considered. The D-optimal designs depend on the values of the variance components and locally optimal designs are therefore considered. It is shown that, if the time points are linearly transformed, then the D-optimal population designs for both the fixed effects and the variance components do not necessarily map onto one another. This result is illustrated numerically by means of a simple example. | en |
dc.description.librarian | nf2012 | en |
dc.description.uri | http://www.sastat.org.za/journal.htm | en_US |
dc.identifier.citation | Debusho, LK & Haines, LM 2010, 'D-optimal population designs for the simple linear random coefficients regression model', South African Statistical Journal, no. 1, pp. 52-59. | en |
dc.identifier.issn | 0038-271X | |
dc.identifier.uri | http://hdl.handle.net/2263/18247 | |
dc.language.iso | en | en_US |
dc.publisher | South African Statistical Association | en_US |
dc.rights | South African Statistical Association | en |
dc.subject | Linear regression | en |
dc.subject | Random coefficients | en |
dc.subject | Information matrix | en |
dc.subject | Population designs | en |
dc.subject | D-optimality | en |
dc.subject.lcsh | Regression analysis | en |
dc.subject.lcsh | Multilevel models (Statistics) | en |
dc.title | D-optimal population designs for the simple linear random coefficients regression model | en |
dc.type | Article | en |