Analysing censored longitudinal data with non-ignorable missing values: Depression in older age

Milena Falcaro; Neil Pendleton; Andrew Pickles

doi:10.1111/j.1467-985X.2011.01034.x

Analysing censored longitudinal data with non-ignorable missing values: Depression in older age

Milena Falcaro^*, Neil Pendleton, Andrew Pickles

^*Corresponding author for this work

Research output: Contribution to journal › Article › peer-review

6 Citations (Scopus)

Abstract

Missing values are common in cohort studies of the elderly. As part of a study of cognition in older age, we implemented a model for the analysis of longitudinal depression data complicated by the presence of non-ignorable missing values, censored measurements and individually varying times of observation. The repeated measures and non-response mechanisms are jointly modelled by assuming that they depend on a common underlying process. The results of our analysis suggest that both depression and non-response increase with age and that women have systematically higher depression scores than men but do not have higher levels of study non-participation.

Original language	English
Pages (from-to)	415-430
Number of pages	16
Journal	JOURNAL- ROYAL STATISTICAL SOCIETY SERIES A
Volume	176
Issue number	2
DOIs	https://doi.org/10.1111/j.1467-985X.2011.01034.x
Publication status	Published - Feb 2013

Keywords

Censoring
Individually varying times of observation
Longitudinal data
Non-ignorable missing values
Structural equations modelling
LATENT GROWTH-MODELS
DROP-OUT
ITEM NONRESPONSE
ATTITUDE SCALES

Access to Document

10.1111/j.1467-985X.2011.01034.x

Cite this

@article{58b5ec60e6964ade87ff135c7de7f595,

title = "Analysing censored longitudinal data with non-ignorable missing values: Depression in older age",

abstract = "Missing values are common in cohort studies of the elderly. As part of a study of cognition in older age, we implemented a model for the analysis of longitudinal depression data complicated by the presence of non-ignorable missing values, censored measurements and individually varying times of observation. The repeated measures and non-response mechanisms are jointly modelled by assuming that they depend on a common underlying process. The results of our analysis suggest that both depression and non-response increase with age and that women have systematically higher depression scores than men but do not have higher levels of study non-participation.",

keywords = "Censoring, Individually varying times of observation, Longitudinal data, Non-ignorable missing values, Structural equations modelling, LATENT GROWTH-MODELS, DROP-OUT, ITEM NONRESPONSE, ATTITUDE SCALES",

author = "Milena Falcaro and Neil Pendleton and Andrew Pickles",

year = "2013",

month = feb,

doi = "10.1111/j.1467-985X.2011.01034.x",

language = "English",

volume = "176",

pages = "415--430",

journal = "JOURNAL- ROYAL STATISTICAL SOCIETY SERIES A",

issn = "0964-1998",

publisher = "Wiley-Blackwell",

number = "2",

}

TY - JOUR

T1 - Analysing censored longitudinal data with non-ignorable missing values

T2 - Depression in older age

AU - Falcaro, Milena

AU - Pendleton, Neil

AU - Pickles, Andrew

PY - 2013/2

Y1 - 2013/2

N2 - Missing values are common in cohort studies of the elderly. As part of a study of cognition in older age, we implemented a model for the analysis of longitudinal depression data complicated by the presence of non-ignorable missing values, censored measurements and individually varying times of observation. The repeated measures and non-response mechanisms are jointly modelled by assuming that they depend on a common underlying process. The results of our analysis suggest that both depression and non-response increase with age and that women have systematically higher depression scores than men but do not have higher levels of study non-participation.

AB - Missing values are common in cohort studies of the elderly. As part of a study of cognition in older age, we implemented a model for the analysis of longitudinal depression data complicated by the presence of non-ignorable missing values, censored measurements and individually varying times of observation. The repeated measures and non-response mechanisms are jointly modelled by assuming that they depend on a common underlying process. The results of our analysis suggest that both depression and non-response increase with age and that women have systematically higher depression scores than men but do not have higher levels of study non-participation.

KW - Censoring

KW - Individually varying times of observation

KW - Longitudinal data

KW - Non-ignorable missing values

KW - Structural equations modelling

KW - LATENT GROWTH-MODELS

KW - DROP-OUT

KW - ITEM NONRESPONSE

KW - ATTITUDE SCALES

U2 - 10.1111/j.1467-985X.2011.01034.x

DO - 10.1111/j.1467-985X.2011.01034.x

M3 - Article

SN - 0964-1998

VL - 176

SP - 415

EP - 430

JO - JOURNAL- ROYAL STATISTICAL SOCIETY SERIES A

JF - JOURNAL- ROYAL STATISTICAL SOCIETY SERIES A

IS - 2

ER -

Analysing censored longitudinal data with non-ignorable missing values: Depression in older age

Abstract

Keywords

Access to Document

Fingerprint

Cite this