The effects of imputing the missing standard deviations on the standard error of meta analysis estimates

N.R.N. Idris, C. Robertson

Research output: Contribution to journalArticle

10 Citations (Scopus)

Abstract

A common problem in the meta analysis of continuous data is that some studies do not report sufficient information to calculate the standard deviation (SDs) of the treatment effect. One of the approaches in handling this problem is through imputation. This article examines the empirical implications of imputing the missing SDs on the standard error (SE) of the overall meta analysis estimate. The simulation results show that if the SDs are missing under Missing Completely at Random and Missing at Random mechanism, imputation is recommended. With non random missing, imputation can lead to overestimation of the SE of the estimate.
LanguageEnglish
Pages513-526
Number of pages13
JournalCommunications in Statistics - Simulation and Computation
Volume38
Issue number3
DOIs
Publication statusPublished - 2009

Fingerprint

Imputation
Standard error
Standard deviation
Estimate
Missing Completely at Random
Missing at Random
Treatment Effects
Sufficient
Calculate
Simulation

Keywords

  • imputation
  • MCAR
  • meta analysis
  • missing SDs
  • standard error

Cite this

@article{e1c7a936d36e4cd0b1a3a452ff9a0069,
title = "The effects of imputing the missing standard deviations on the standard error of meta analysis estimates",
abstract = "A common problem in the meta analysis of continuous data is that some studies do not report sufficient information to calculate the standard deviation (SDs) of the treatment effect. One of the approaches in handling this problem is through imputation. This article examines the empirical implications of imputing the missing SDs on the standard error (SE) of the overall meta analysis estimate. The simulation results show that if the SDs are missing under Missing Completely at Random and Missing at Random mechanism, imputation is recommended. With non random missing, imputation can lead to overestimation of the SE of the estimate.",
keywords = "imputation, MCAR, meta analysis, missing SDs, standard error",
author = "N.R.N. Idris and C. Robertson",
year = "2009",
doi = "10.1080/03610910802556106",
language = "English",
volume = "38",
pages = "513--526",
journal = "Communications in Statistics - Simulation and Computation",
issn = "0361-0918",
number = "3",

}

TY - JOUR

T1 - The effects of imputing the missing standard deviations on the standard error of meta analysis estimates

AU - Idris, N.R.N.

AU - Robertson, C.

PY - 2009

Y1 - 2009

N2 - A common problem in the meta analysis of continuous data is that some studies do not report sufficient information to calculate the standard deviation (SDs) of the treatment effect. One of the approaches in handling this problem is through imputation. This article examines the empirical implications of imputing the missing SDs on the standard error (SE) of the overall meta analysis estimate. The simulation results show that if the SDs are missing under Missing Completely at Random and Missing at Random mechanism, imputation is recommended. With non random missing, imputation can lead to overestimation of the SE of the estimate.

AB - A common problem in the meta analysis of continuous data is that some studies do not report sufficient information to calculate the standard deviation (SDs) of the treatment effect. One of the approaches in handling this problem is through imputation. This article examines the empirical implications of imputing the missing SDs on the standard error (SE) of the overall meta analysis estimate. The simulation results show that if the SDs are missing under Missing Completely at Random and Missing at Random mechanism, imputation is recommended. With non random missing, imputation can lead to overestimation of the SE of the estimate.

KW - imputation

KW - MCAR

KW - meta analysis

KW - missing SDs

KW - standard error

UR - https://www.tandfonline.com/doi/abs/10.1080/03610910802556106

U2 - 10.1080/03610910802556106

DO - 10.1080/03610910802556106

M3 - Article

VL - 38

SP - 513

EP - 526

JO - Communications in Statistics - Simulation and Computation

T2 - Communications in Statistics - Simulation and Computation

JF - Communications in Statistics - Simulation and Computation

SN - 0361-0918

IS - 3

ER -