A quality control measure for longitudinal studies with continuous outcomes

Walter T. Ambrosius, Siu Hui

Research output: Contribution to journalArticle

4 Citations (Scopus)

Abstract

At the time of data acquisition in a longitudinal study a decision needs to be made whether or not the latest measurement of the primary outcome is a potential outlier. If the data point does not fit with the subject's prior data, the patient can be immediately remeasured before he/she leaves the office. From the third visit onwards, a least squares approach can be used to generate prediction intervals for the value of the response at that visit. We propose a Bayesian method for calculating a prediction interval that can incorporate external information about the process that can be used beginning at the first visit. Both the least squares and Bayesian approaches will be used to prospectively clean longitudinal data. An example using longitudinally measured bone density measurements in the elderly will be discussed. In addition, simulation studies will be described which show that both cleaning methods are better than doing nothing and that the Bayesian approach outperforms the least squares method. (C) 2000 John Wiley and Sons, Ltd.

Original languageEnglish
Pages (from-to)1339-1362
Number of pages24
JournalStatistics in Medicine
Volume19
Issue number10
DOIs
StatePublished - May 30 2000

Fingerprint

Prediction Interval
Bayes Theorem
Longitudinal Study
Quality Control
Least-Squares Analysis
Bayesian Approach
Longitudinal Studies
Least Squares
Cleaning
Bayesian Methods
Longitudinal Data
Data Acquisition
Least Square Method
Bone
Outlier
Immediately
Simulation Study
Bone Density

ASJC Scopus subject areas

  • Epidemiology

Cite this

A quality control measure for longitudinal studies with continuous outcomes. / Ambrosius, Walter T.; Hui, Siu.

In: Statistics in Medicine, Vol. 19, No. 10, 30.05.2000, p. 1339-1362.

Research output: Contribution to journalArticle

@article{1ca116d7b7fd40c6bbfa0ceb80f8c466,
title = "A quality control measure for longitudinal studies with continuous outcomes",
abstract = "At the time of data acquisition in a longitudinal study a decision needs to be made whether or not the latest measurement of the primary outcome is a potential outlier. If the data point does not fit with the subject's prior data, the patient can be immediately remeasured before he/she leaves the office. From the third visit onwards, a least squares approach can be used to generate prediction intervals for the value of the response at that visit. We propose a Bayesian method for calculating a prediction interval that can incorporate external information about the process that can be used beginning at the first visit. Both the least squares and Bayesian approaches will be used to prospectively clean longitudinal data. An example using longitudinally measured bone density measurements in the elderly will be discussed. In addition, simulation studies will be described which show that both cleaning methods are better than doing nothing and that the Bayesian approach outperforms the least squares method. (C) 2000 John Wiley and Sons, Ltd.",
author = "Ambrosius, {Walter T.} and Siu Hui",
year = "2000",
month = "5",
day = "30",
doi = "10.1002/(SICI)1097-0258(20000530)19:10<1339::AID-SIM480>3.0.CO;2-#",
language = "English",
volume = "19",
pages = "1339--1362",
journal = "Statistics in Medicine",
issn = "0277-6715",
publisher = "John Wiley and Sons Ltd",
number = "10",

}

TY - JOUR

T1 - A quality control measure for longitudinal studies with continuous outcomes

AU - Ambrosius, Walter T.

AU - Hui, Siu

PY - 2000/5/30

Y1 - 2000/5/30

N2 - At the time of data acquisition in a longitudinal study a decision needs to be made whether or not the latest measurement of the primary outcome is a potential outlier. If the data point does not fit with the subject's prior data, the patient can be immediately remeasured before he/she leaves the office. From the third visit onwards, a least squares approach can be used to generate prediction intervals for the value of the response at that visit. We propose a Bayesian method for calculating a prediction interval that can incorporate external information about the process that can be used beginning at the first visit. Both the least squares and Bayesian approaches will be used to prospectively clean longitudinal data. An example using longitudinally measured bone density measurements in the elderly will be discussed. In addition, simulation studies will be described which show that both cleaning methods are better than doing nothing and that the Bayesian approach outperforms the least squares method. (C) 2000 John Wiley and Sons, Ltd.

AB - At the time of data acquisition in a longitudinal study a decision needs to be made whether or not the latest measurement of the primary outcome is a potential outlier. If the data point does not fit with the subject's prior data, the patient can be immediately remeasured before he/she leaves the office. From the third visit onwards, a least squares approach can be used to generate prediction intervals for the value of the response at that visit. We propose a Bayesian method for calculating a prediction interval that can incorporate external information about the process that can be used beginning at the first visit. Both the least squares and Bayesian approaches will be used to prospectively clean longitudinal data. An example using longitudinally measured bone density measurements in the elderly will be discussed. In addition, simulation studies will be described which show that both cleaning methods are better than doing nothing and that the Bayesian approach outperforms the least squares method. (C) 2000 John Wiley and Sons, Ltd.

UR - http://www.scopus.com/inward/record.url?scp=0034732979&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0034732979&partnerID=8YFLogxK

U2 - 10.1002/(SICI)1097-0258(20000530)19:10<1339::AID-SIM480>3.0.CO;2-#

DO - 10.1002/(SICI)1097-0258(20000530)19:10<1339::AID-SIM480>3.0.CO;2-#

M3 - Article

C2 - 10814982

AN - SCOPUS:0034732979

VL - 19

SP - 1339

EP - 1362

JO - Statistics in Medicine

JF - Statistics in Medicine

SN - 0277-6715

IS - 10

ER -