No label defined (Q4257546)
From MaRDI portal
!
This is the item page for this Wikibase entity, intended for internal use and editing purposes. Please use the normal view instead:
scientific article; zbMATH DE number 1329174
| Language | Label | Description | Also known as |
|---|---|---|---|
| default for all languages | No label defined |
||
| English | No label defined |
scientific article; zbMATH DE number 1329174 |
Statements
10 September 2000
0 references
growth curve analysis
0 references
univariate growth data
0 references
mean- and covariance structure models
0 references
maximum-likelihood
0 references
pseudo-ML estimation
0 references
multistage estimation
0 references
0.89285636
0 references
0.8756678
0 references
0.8668069
0 references
0.8667815
0 references
0.86555505
0 references
In growth curve analysis, one considers a random variable \(Y_{i,t}\) which varies over elements \(i= 1,\dots, n\) and time points \(t= 1,\dots, T\). Usually there is a large number \(n\) of independent elements which are observed at a small number \(T\) of occasions. The aim of paper is to describe the behavior of \(Y_{it}\) over time, where it is assumed that the repeated measurements follow smooth and fairly similar developments over time for each element, while there are variations in the initial status final status, and the rate of change between elements. Section 2 of the paper exposes three basic models for the analysis of univariate growth data. These basic models can be combined and embedded in the more mean- and covariance structure models. This property allows the use of the powerful computer programs (such as RAMONA or MECOSA 3) for the mean- and covariance structure analysis of the computation of growth curve models. Section 3 introduces extensions of the basic models discussed in Section 2, in order to analyze the growth curve of a latent variable that cannot be observed directly. Section 4 contains the general theory for the estimation and numerical analysis of parameters of main- and covariance structure models. There are discussed Maximum-Likelihood (ML) and pseudo-ML estimation for metrical dependent variables, and multistage estimation for non-metrical dependent variables. For the entire collection see [Zbl 0909.00064].
0 references