Missing data methods for arbitrary missingness with small samples

Research output: Contribution to journalArticle

22 Citations (Scopus)

Abstract

Missing data are a prevalent and widespread data analytic issue and previous studies have performed simulations to compare the performance of missing data methods in various contexts and for various models; however, one such context that has yet to receive much attention in the literature is the handling of missing data with small samples, particularly when the missingness is arbitrary. Prior studies have either compared methods for small samples with monotone missingness commonly found in longitudinal studies or have investigated the performance of a single method to handle arbitrary missingness with small samples but studies have yet to compare the relative performance of commonly implemented missing data methods for small samples with arbitrary missingness. This study conducts a simulation study to compare and assess the small sample performance of maximum likelihood, listwise deletion, joint multiple imputation, and fully conditional specification multiple imputation for a single-level regression model with a continuous outcome. Results showed that, provided assumptions are met, joint multiple imputation unanimously performed best of the methods examined in the conditions under study.

Original languageEnglish (US)
Pages (from-to)24-39
Number of pages16
JournalJournal of Applied Statistics
Volume44
Issue number1
DOIs
StatePublished - Jan 2 2017
Externally publishedYes

Fingerprint

Missing Data
Small Sample
Multiple Imputation
Arbitrary
Longitudinal Study
Deletion
Maximum Likelihood
Regression Model
Monotone
Missing data
Small sample
Simulation Study
Specification
Multiple imputation
Simulation
Context

Keywords

  • finite sample
  • full information maximum likelihood
  • incomplete data
  • missing data
  • Monte Carlo simulation
  • multiple imputation
  • Small sample

ASJC Scopus subject areas

  • Statistics and Probability
  • Statistics, Probability and Uncertainty

Cite this

Missing data methods for arbitrary missingness with small samples. / McNeish, Daniel.

In: Journal of Applied Statistics, Vol. 44, No. 1, 02.01.2017, p. 24-39.

Research output: Contribution to journalArticle

@article{4e779dbcfdb049d1bafe4e5ca798aad9,
title = "Missing data methods for arbitrary missingness with small samples",
abstract = "Missing data are a prevalent and widespread data analytic issue and previous studies have performed simulations to compare the performance of missing data methods in various contexts and for various models; however, one such context that has yet to receive much attention in the literature is the handling of missing data with small samples, particularly when the missingness is arbitrary. Prior studies have either compared methods for small samples with monotone missingness commonly found in longitudinal studies or have investigated the performance of a single method to handle arbitrary missingness with small samples but studies have yet to compare the relative performance of commonly implemented missing data methods for small samples with arbitrary missingness. This study conducts a simulation study to compare and assess the small sample performance of maximum likelihood, listwise deletion, joint multiple imputation, and fully conditional specification multiple imputation for a single-level regression model with a continuous outcome. Results showed that, provided assumptions are met, joint multiple imputation unanimously performed best of the methods examined in the conditions under study.",
keywords = "finite sample, full information maximum likelihood, incomplete data, missing data, Monte Carlo simulation, multiple imputation, Small sample",
author = "Daniel McNeish",
year = "2017",
month = "1",
day = "2",
doi = "10.1080/02664763.2016.1158246",
language = "English (US)",
volume = "44",
pages = "24--39",
journal = "Journal of Applied Statistics",
issn = "0266-4763",
publisher = "Routledge",
number = "1",

}

TY - JOUR

T1 - Missing data methods for arbitrary missingness with small samples

AU - McNeish, Daniel

PY - 2017/1/2

Y1 - 2017/1/2

N2 - Missing data are a prevalent and widespread data analytic issue and previous studies have performed simulations to compare the performance of missing data methods in various contexts and for various models; however, one such context that has yet to receive much attention in the literature is the handling of missing data with small samples, particularly when the missingness is arbitrary. Prior studies have either compared methods for small samples with monotone missingness commonly found in longitudinal studies or have investigated the performance of a single method to handle arbitrary missingness with small samples but studies have yet to compare the relative performance of commonly implemented missing data methods for small samples with arbitrary missingness. This study conducts a simulation study to compare and assess the small sample performance of maximum likelihood, listwise deletion, joint multiple imputation, and fully conditional specification multiple imputation for a single-level regression model with a continuous outcome. Results showed that, provided assumptions are met, joint multiple imputation unanimously performed best of the methods examined in the conditions under study.

AB - Missing data are a prevalent and widespread data analytic issue and previous studies have performed simulations to compare the performance of missing data methods in various contexts and for various models; however, one such context that has yet to receive much attention in the literature is the handling of missing data with small samples, particularly when the missingness is arbitrary. Prior studies have either compared methods for small samples with monotone missingness commonly found in longitudinal studies or have investigated the performance of a single method to handle arbitrary missingness with small samples but studies have yet to compare the relative performance of commonly implemented missing data methods for small samples with arbitrary missingness. This study conducts a simulation study to compare and assess the small sample performance of maximum likelihood, listwise deletion, joint multiple imputation, and fully conditional specification multiple imputation for a single-level regression model with a continuous outcome. Results showed that, provided assumptions are met, joint multiple imputation unanimously performed best of the methods examined in the conditions under study.

KW - finite sample

KW - full information maximum likelihood

KW - incomplete data

KW - missing data

KW - Monte Carlo simulation

KW - multiple imputation

KW - Small sample

UR - http://www.scopus.com/inward/record.url?scp=84961393564&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84961393564&partnerID=8YFLogxK

U2 - 10.1080/02664763.2016.1158246

DO - 10.1080/02664763.2016.1158246

M3 - Article

AN - SCOPUS:84961393564

VL - 44

SP - 24

EP - 39

JO - Journal of Applied Statistics

JF - Journal of Applied Statistics

SN - 0266-4763

IS - 1

ER -