Multilevel diagnostics for mixed and hierarchical linear models

In this dissertation, I develop a multilevel approach to diagnosing and assessing t in mixed linear models and hierarchical linear models, which may be extended to other generalizations of mixed models. Since these models include multiple sources of error, I de ne several di erent types of resid...

Descripción completa

Detalles Bibliográficos
Autor principal: Hilden-Minton, J.A.
Formato: Tesis
Lenguaje:Inglés
Publicado: University of California 1995
Materias:
Acceso en línea:https://hdl.handle.net/10568/81585
_version_ 1855537585902845952
author Hilden-Minton, J.A.
author_browse Hilden-Minton, J.A.
author_facet Hilden-Minton, J.A.
author_sort Hilden-Minton, J.A.
collection Repository of Agricultural Research Outputs (CGSpace)
description In this dissertation, I develop a multilevel approach to diagnosing and assessing t in mixed linear models and hierarchical linear models, which may be extended to other generalizations of mixed models. Since these models include multiple sources of error, I de ne several di erent types of residuals. Most residuals are confounded in the sense that they are subject to extraneous sources of error. The confounding of residuals reduces the analyst's power to detect violations of modeling assumptions. I present various approaches for reducing the confounding in residuals. I give a construction for uncorrelated standardized residuals which are also least confounded. I argue that a multilevel approach to diagnostics can overcome some confounding. Furthermore, the multilevel approach simpli es the diagnostician's task by justifying the use of well known procedures on within-unit models. I discuss the problem of identifying and discriminating between in uential cases and units. The case-deletion approach moti-vates the generalization of several common diagnostic measures. Unfortunately, the discrete approach to case-deletion, which I clarify, is imprecise relative to approaches bases on analytic approximations. Also I give some attention to the graphical presentation and interpretation of diagnostics while discussing various examples.
format Tesis
id CGSpace81585
institution CGIAR Consortium
language Inglés
publishDate 1995
publishDateRange 1995
publishDateSort 1995
publisher University of California
publisherStr University of California
record_format dspace
spelling CGSpace815852023-02-15T11:18:25Z Multilevel diagnostics for mixed and hierarchical linear models Hilden-Minton, J.A. analysis statistics linear models In this dissertation, I develop a multilevel approach to diagnosing and assessing t in mixed linear models and hierarchical linear models, which may be extended to other generalizations of mixed models. Since these models include multiple sources of error, I de ne several di erent types of residuals. Most residuals are confounded in the sense that they are subject to extraneous sources of error. The confounding of residuals reduces the analyst's power to detect violations of modeling assumptions. I present various approaches for reducing the confounding in residuals. I give a construction for uncorrelated standardized residuals which are also least confounded. I argue that a multilevel approach to diagnostics can overcome some confounding. Furthermore, the multilevel approach simpli es the diagnostician's task by justifying the use of well known procedures on within-unit models. I discuss the problem of identifying and discriminating between in uential cases and units. The case-deletion approach moti-vates the generalization of several common diagnostic measures. Unfortunately, the discrete approach to case-deletion, which I clarify, is imprecise relative to approaches bases on analytic approximations. Also I give some attention to the graphical presentation and interpretation of diagnostics while discussing various examples. 1995 2017-06-16T09:03:45Z 2017-06-16T09:03:45Z Thesis https://hdl.handle.net/10568/81585 en Limited Access University of California Hilden-Minton J. A. 1995. Multilevel diagnostics for mixed and hierarchical linear models. PhD thesis in Mathematics. University f California.
spellingShingle analysis
statistics
linear models
Hilden-Minton, J.A.
Multilevel diagnostics for mixed and hierarchical linear models
title Multilevel diagnostics for mixed and hierarchical linear models
title_full Multilevel diagnostics for mixed and hierarchical linear models
title_fullStr Multilevel diagnostics for mixed and hierarchical linear models
title_full_unstemmed Multilevel diagnostics for mixed and hierarchical linear models
title_short Multilevel diagnostics for mixed and hierarchical linear models
title_sort multilevel diagnostics for mixed and hierarchical linear models
topic analysis
statistics
linear models
url https://hdl.handle.net/10568/81585
work_keys_str_mv AT hildenmintonja multileveldiagnosticsformixedandhierarchicallinearmodels