Bayesian and profile likelihood change point methods for modeling cognitive function over time

Change point models are often used to model longitudinal data. To estimate the change point, Bayesian (Biometrika 62 (1975) 407; Appl. Statist. 41 (1992) 389; Biometrics 51 (1995) 236) or profile likelihood (Statist. Med. 19 (2000) 1555) methods may be used.We compare and contrast the two methods in analyzing longitudinal cognitive data from the Bronx Aging Study. The Bayesian method has advantages over the profile likelihood method in that it does not require all subjects to have the same change point. Caution must be taken regarding sensitivity to choice of prior distribution, identifiability, and goodness of fit. Analyses show that decline in memory precedes diagnosis of dementia by 7.5-8 years, and individual change points are not needed to model heterogeneity across subjects.

[1]  David V. Hinkley,et al.  Inference about the change-point in a sequence of binomial variables , 1970 .

[2]  C B Hall,et al.  A change point model for estimating the onset of cognitive decline in preclinical Alzheimer's disease. , 2000, Statistics in medicine.

[3]  A. F. Smith.  A Bayesian approach to inference about a change-point in a sequence of random variables , 1975 .

[4]  Herman Buschke,et al.  Selective reminding for analysis of memory and learning , 1973 .

[5]  M. Folstein,et al.  Clinical diagnosis of Alzheimer's disease , 1984, Neurology.

[6]  E G Tangalos,et al.  Memory function in very early Alzheimer's disease , 1994, Neurology.

[7]  H C Hendrie,et al.  Epidemiology of dementia and Alzheimer's disease. , 1998, The American journal of geriatric psychiatry : official journal of the American Association for Geriatric Psychiatry.

[8]  A. Gelfand,et al.  Bayesian Model Choice: Asymptotics and Exact Calculations , 1994 .

[9]  Adrian F. M. Smith,et al.  Hierarchical Bayesian Analysis of Changepoint Problems , 1992 .

[10]  T R Holford,et al.  Change points in the series of T4 counts prior to AIDS. , 1995, Biometrics.

[11]  J. Ware,et al.  Random-effects models for longitudinal data. , 1982, Biometrics.

[12]  M. Y. El-Bassiouni,et al.  Testing a null variance ratio in mixed models with zero degrees of freedom for error , 2004, Comput. Stat. Data Anal..

[13]  R. Hu.  Diagnostic and Statistical Manual of Mental Disorders (DSM-IV) , 2003 .

[14]  E. Tangalos,et al.  Mild Cognitive Impairment Clinical Characterization and Outcome , 1999 .

[15]  S. E. Hills,et al.  Illustration of Bayesian Inference in Normal Data Models Using Gibbs Sampling , 1990 .

[16]  H. Buschke,et al.  Screening for dementia by memory testing , 1988, Neurology.

[17]  H Morgenstern,et al.  Development of dementing illnesses in an 80‐year‐old volunteer cohort , 1989, Annals of neurology.

[18]  P. Diggle.  Analysis of Longitudinal Data , 1995 .

[19]  M. Newton.  Approximate Bayesian-inference With the Weighted Likelihood Bootstrap , 1994 .

[20]  Ronald C. Petersen,et al.  Definition, course, and outcome of mild cognitive impairment , 1996 .

[21]  K. Cowles,et al.  CODA: convergence diagnosis and output analysis software for Gibbs sampling output , 1995 .

[22]  R. Katzman.,et al.  Education and the prevalence of dementia and Alzheimer's disease , 1993, Neurology.

[23]  M. Aitkin.  Posterior Bayes Factors , 1991 .

[24]  A. Gelfand,et al.  Hierarchical Bayes Models for the Progression of HIV Infection Using Longitudinal CD4 T-Cell Numbers , 1992 .

[25]  S. Geisser,et al.  A Predictive Approach to Model Selection , 1979 .

[26]  Lynn Kuo,et al.  Sampling based approach for one-hit and multi-hit models in quantal bioassay , 1997, Stat. Comput..