Wade, Angela M;
(1997)
Likelihood-based methods for the construction of cross-sectional age related standards.
Doctoral thesis (Ph.D), UCL (University College London).
![]() |
Text
Likelihood-based_methods_for_t.pdf Download (6MB) |
Abstract
The problems associated with the construction of age-related standards have been recognised for almost half a century. The limiting factor has tended to be the difficulties associated with complex model fitting. Increased software capabilities have lead to increased interest over recent years. In chapter 1 both the past and current literature is reviewed. Chapters 2,3 and 4 use a likelihood based approach to create age related centiles. A continuous outcome is considered in chapters 2 and 3. Separate parametric curves are used to characterise changes in the skew, spread and median. These curves are then combined to create centiles and can be used to calculate z-scores throughout the age range. In chapter 4 similar methodology is applied to create standards for an ordinal outcome. Proportional odds models are used with parametric forms to model the logit of the probabilities. For both the continuous and ordinal outcomes curve forms were chosen that would asymptote at adult values. The likelihood approach has several advantages. Firstly, the likelihoods form a basis for significance testing between models. Secondly, profile likelihoods can be used to create confidence intervals for any of the model parameters, the centiles or z-scores obtained from them. Thirdly, if measurements are not independent then the correlation structure can be explicitly modelled and incorporated into the likelihood. This latter point is illustrated in chapter 3. The final chapter is an overview which discusses the relevance of the results given in chapters 2-4 and highlights potential areas for future development.
Type: | Thesis (Doctoral) |
---|---|
Qualification: | Ph.D |
Title: | Likelihood-based methods for the construction of cross-sectional age related standards |
Open access status: | An open access version is available from UCL Discovery |
Language: | English |
Additional information: | Thesis digitised by ProQuest. |
Keywords: | Applied sciences |
URI: | https://discovery-pp.ucl.ac.uk/id/eprint/10099878 |
Archive Staff Only
![]() |
View Item |