A Markov chain model for longitudinal categorical data when there may be non-ignorable non-response (Q4935560)
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 1396134
| Language | Label | Description | Also known as |
|---|---|---|---|
| default for all languages | No label defined |
||
| English | A Markov chain model for longitudinal categorical data when there may be non-ignorable non-response |
scientific article; zbMATH DE number 1396134 |
Statements
A Markov chain model for longitudinal categorical data when there may be non-ignorable non-response (English)
0 references
21 September 2000
0 references
Markov chain model
0 references
parameter estimation
0 references
hypothesis testing
0 references
incomplete data
0 references
longitudinal categorical data
0 references
least squares method
0 references
medical data
0 references
0.8057974576950073
0 references
0.8054776191711426
0 references
0.7868075966835022
0 references
0.782997727394104
0 references
In longitudinal studies the data may be incomplete. When the cause for missing data is related to the response that would have been recorded, the missing data mechanism is called 'non-ignorable'. The authors model this situation by a second-order Markov process. The parameters of the model are estimated from the data by a least squares procedure. Simulation is used to study the properties of the estimators. A statistic is devised to test the hypothesis of whether the non-response mechanism is ignorable. The model is applied to a set of medical data.
0 references