A Bayesian model for measurement and misclassification errors alongside missing data, with an application to higher education participation in Australia

Harvey Goldstein; William J. Browne; Christopher Charlton

doi:10.1080/02664763.2017.1322558

A Bayesian model for measurement and misclassification errors alongside missing data, with an application to higher education participation in Australia

Harvey Goldstein^*, William J. Browne, Christopher Charlton

^*Corresponding author for this work

Research output: Contribution to journal › Article (Academic Journal) › peer-review

14 Citations (Scopus)

471 Downloads (Pure)

Abstract

In this paper we consider the impact of both missing data and measurement errors on a longitudinal analysis of participation in higher education in Australia. We develop a general method for handling both discrete and continuous measurement errors that also allows for the incorporation of missing values and random effects in both binary and continuous response multilevel models. Measurement errors are allowed to be mutually dependent and their distribution may depend on further covariates. We show that our methodology works via two simple simulation studies. We then consider the impact of our measurement error assumptions on the analysis of the real data set.

Original language	English
Pages (from-to)	918-931
Number of pages	14
Journal	Journal of Applied Statistics
Volume	45
Issue number	5
Early online date	9 May 2017
DOIs	https://doi.org/10.1080/02664763.2017.1322558
Publication status	Published - 4 Apr 2018

Research Groups and Themes

Jean Golding

Keywords

higher education participation
measurement errors
missclassification errors
MCMC
MISSING DATA
multilevel

Access to Document

10.1080/02664763.2017.1322558

Full-text PDF (accepted author manuscript)
This is the author accepted manuscript (AAM). The final published version (version of record) is available online via Taylor & Francis at http://www.tandfonline.com/doi/abs/10.1080/02664763.2017.1322558. Please refer to any applicable terms of use of the publisher.
Accepted author manuscript, 743 KB

Handle.net

Persistent link

The use of interactive electronic-books in the teaching and application of modern, quantitative social science methods
Browne, W. J. (Principal Investigator), Goldstein, H. (Co-Investigator), Jones, K. (Co-Investigator), Leckie, G. B. (Co-Investigator), Moreau, L. (Co-Investigator), Parker, R. M. A. (Researcher) & Michaelides, D. (Researcher)
1/10/13 → 30/09/17
Project: Research

Professor William J Browne
- William.Brownebristol.acuk
Person: Academic , Member, Group lead

Cite this

@article{7be6d0451890435d85ec21b817684aab,

title = "A Bayesian model for measurement and misclassification errors alongside missing data, with an application to higher education participation in Australia",

abstract = "In this paper we consider the impact of both missing data and measurement errors on a longitudinal analysis of participation in higher education in Australia. We develop a general method for handling both discrete and continuous measurement errors that also allows for the incorporation of missing values and random effects in both binary and continuous response multilevel models. Measurement errors are allowed to be mutually dependent and their distribution may depend on further covariates. We show that our methodology works via two simple simulation studies. We then consider the impact of our measurement error assumptions on the analysis of the real data set.",

keywords = "higher education participation, measurement errors, missclassification errors, MCMC, MISSING DATA, multilevel",

author = "Harvey Goldstein and Browne, {William J.} and Christopher Charlton",

year = "2018",

month = apr,

day = "4",

doi = "10.1080/02664763.2017.1322558",

language = "English",

volume = "45",

pages = "918--931",

journal = "Journal of Applied Statistics",

issn = "0266-4763",

publisher = "Taylor & Francis Group",

number = "5",

}

A Bayesian model for measurement and misclassification errors alongside missing data, with an application to higher education participation in Australia. / Goldstein, Harvey; Browne, William J.; Charlton, Christopher.
In: Journal of Applied Statistics, Vol. 45, No. 5, 04.04.2018, p. 918-931.

Research output: Contribution to journal › Article (Academic Journal) › peer-review

TY - JOUR

T1 - A Bayesian model for measurement and misclassification errors alongside missing data, with an application to higher education participation in Australia

AU - Goldstein, Harvey

AU - Browne, William J.

AU - Charlton, Christopher

PY - 2018/4/4

Y1 - 2018/4/4

N2 - In this paper we consider the impact of both missing data and measurement errors on a longitudinal analysis of participation in higher education in Australia. We develop a general method for handling both discrete and continuous measurement errors that also allows for the incorporation of missing values and random effects in both binary and continuous response multilevel models. Measurement errors are allowed to be mutually dependent and their distribution may depend on further covariates. We show that our methodology works via two simple simulation studies. We then consider the impact of our measurement error assumptions on the analysis of the real data set.

AB - In this paper we consider the impact of both missing data and measurement errors on a longitudinal analysis of participation in higher education in Australia. We develop a general method for handling both discrete and continuous measurement errors that also allows for the incorporation of missing values and random effects in both binary and continuous response multilevel models. Measurement errors are allowed to be mutually dependent and their distribution may depend on further covariates. We show that our methodology works via two simple simulation studies. We then consider the impact of our measurement error assumptions on the analysis of the real data set.

KW - higher education participation

KW - measurement errors

KW - missclassification errors

KW - MCMC

KW - MISSING DATA

KW - multilevel

U2 - 10.1080/02664763.2017.1322558

DO - 10.1080/02664763.2017.1322558

M3 - Article (Academic Journal)

AN - SCOPUS:85019159270

SN - 0266-4763

VL - 45

SP - 918

EP - 931

JO - Journal of Applied Statistics

JF - Journal of Applied Statistics

IS - 5

ER -

A Bayesian model for measurement and misclassification errors alongside missing data, with an application to higher education participation in Australia

Abstract

Research Groups and Themes

Keywords

Access to Document

Handle.net

Fingerprint

Projects

The use of interactive electronic-books in the teaching and application of modern, quantitative social science methods

Profiles

Professor William J Browne

Cite this