The impact of survey nonresponse bias on conclusions drawn from a mammography intervention trial

Melissa R. Partin; Michael Malone; Mary Winnett; Jonathan Slater; Annette Bar-Cohen; Lee Caplan

doi:10.1016/S0895-4356(03)00061-1

The impact of survey nonresponse bias on conclusions drawn from a mammography intervention trial

Melissa R. Partin, Michael Malone, Mary Winnett, Jonathan Slater, Annette Bar-Cohen, Lee Caplan

Medicine - Veteran's Administration Medical Center

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

33 Scopus citations

Abstract

Background and Objective: This study demonstrates the impact of survey nonresponse bias on conclusions from a mammography trial targeting a disadvantaged population. Methods: The trial randomized 1558 women to three interventions designed to promote repeat mammography: mailed reminder (minimum group); mailed thank-you card, patient newsletters, and reminder (maximum group); and no mailings (control group). The primary outcome, repeat mammogram within 15 months, was assessed from administrative and phone survey data. Results: Administrative estimates revealed a statistically significant difference of 7% between the maximum and control groups on the primary outcome. Survey estimates (response rate 80%) revealed no significant differences. The differences by data source were traced to a survey nonresponse bias. There was a statistically significant difference of 16% between the maximum and control groups among survey nonrespondents for the primary outcome, but there were no differences among survey respondents. Conclusion: The findings reiterate that even a low survey nonresponse rate can bias study conclusions and suggest studies targeting disadvantaged populations should avoid relying solely on survey data for outcome analyses.

Original language	English (US)
Pages (from-to)	867-873
Number of pages	7
Journal	Journal of Clinical Epidemiology
Volume	56
Issue number	9
DOIs	https://doi.org/10.1016/S0895-4356(03)00061-1
State	Published - Sep 1 2003

Bibliographical note

Funding Information:
This research was made possible through a cooperative agreement between the Centers for Disease Control and Prevention (CDC) and the Association for Teachers of Preventive Medicine (ATPM), award number TS 254-13/15. The contents of this research are the responsibility of the authors and do not necessarily reflect the official views of the CDC or the ATPM. The study protocol was reviewed and approved by the Health Partners Research Foundation IRB for protection of human subjects.

Funding Information:
The target population for this study was women 40 to 64 years of age enrolled in the Minnesota Breast and Cervical Cancer Control Program (MBCCCP). The MBCCCP is part of a national program, funded by the Centers for Disease Control and Prevention, whose mission is to reduce avoidable mortality from breast and cervical cancer by increasing screening rates among women. The program provides free breast and cervical cancer screening to low-income women through a network of approximately 300 hospitals and clinics around the state. The MBCCCP has screened over 67,000 women and has provided roughly 72,000 mammograms.

Copyright:
Copyright 2017 Elsevier B.V., All rights reserved.

Keywords

Health education
Intervention studies
Mammography
Nonrespondents
Randomized controlled trial
Selection bias

Access

10.1016/S0895-4356(03)00061-1

Fingerprint Dive into the research topics of 'The impact of survey nonresponse bias on conclusions drawn from a mammography intervention trial'. Together they form a unique fingerprint.

Cite this

@article{16aed0121ece41a5b699fa9a8ba4652e,

title = "The impact of survey nonresponse bias on conclusions drawn from a mammography intervention trial",

abstract = "Background and Objective: This study demonstrates the impact of survey nonresponse bias on conclusions from a mammography trial targeting a disadvantaged population. Methods: The trial randomized 1558 women to three interventions designed to promote repeat mammography: mailed reminder (minimum group); mailed thank-you card, patient newsletters, and reminder (maximum group); and no mailings (control group). The primary outcome, repeat mammogram within 15 months, was assessed from administrative and phone survey data. Results: Administrative estimates revealed a statistically significant difference of 7% between the maximum and control groups on the primary outcome. Survey estimates (response rate 80%) revealed no significant differences. The differences by data source were traced to a survey nonresponse bias. There was a statistically significant difference of 16% between the maximum and control groups among survey nonrespondents for the primary outcome, but there were no differences among survey respondents. Conclusion: The findings reiterate that even a low survey nonresponse rate can bias study conclusions and suggest studies targeting disadvantaged populations should avoid relying solely on survey data for outcome analyses.",

keywords = "Health education, Intervention studies, Mammography, Nonrespondents, Randomized controlled trial, Selection bias",

author = "Partin, {Melissa R.} and Michael Malone and Mary Winnett and Jonathan Slater and Annette Bar-Cohen and Lee Caplan",

note = "Funding Information: This research was made possible through a cooperative agreement between the Centers for Disease Control and Prevention (CDC) and the Association for Teachers of Preventive Medicine (ATPM), award number TS 254-13/15. The contents of this research are the responsibility of the authors and do not necessarily reflect the official views of the CDC or the ATPM. The study protocol was reviewed and approved by the Health Partners Research Foundation IRB for protection of human subjects. Funding Information: The target population for this study was women 40 to 64 years of age enrolled in the Minnesota Breast and Cervical Cancer Control Program (MBCCCP). The MBCCCP is part of a national program, funded by the Centers for Disease Control and Prevention, whose mission is to reduce avoidable mortality from breast and cervical cancer by increasing screening rates among women. The program provides free breast and cervical cancer screening to low-income women through a network of approximately 300 hospitals and clinics around the state. The MBCCCP has screened over 67,000 women and has provided roughly 72,000 mammograms. Copyright: Copyright 2017 Elsevier B.V., All rights reserved.",

year = "2003",

month = sep,

day = "1",

doi = "10.1016/S0895-4356(03)00061-1",

language = "English (US)",

volume = "56",

pages = "867--873",

journal = "Journal of Chronic Diseases",

issn = "0895-4356",

publisher = "Elsevier USA",

number = "9",

}

TY - JOUR

T1 - The impact of survey nonresponse bias on conclusions drawn from a mammography intervention trial

AU - Partin, Melissa R.

AU - Malone, Michael

AU - Winnett, Mary

AU - Slater, Jonathan

AU - Bar-Cohen, Annette

AU - Caplan, Lee

N1 - Funding Information: This research was made possible through a cooperative agreement between the Centers for Disease Control and Prevention (CDC) and the Association for Teachers of Preventive Medicine (ATPM), award number TS 254-13/15. The contents of this research are the responsibility of the authors and do not necessarily reflect the official views of the CDC or the ATPM. The study protocol was reviewed and approved by the Health Partners Research Foundation IRB for protection of human subjects. Funding Information: The target population for this study was women 40 to 64 years of age enrolled in the Minnesota Breast and Cervical Cancer Control Program (MBCCCP). The MBCCCP is part of a national program, funded by the Centers for Disease Control and Prevention, whose mission is to reduce avoidable mortality from breast and cervical cancer by increasing screening rates among women. The program provides free breast and cervical cancer screening to low-income women through a network of approximately 300 hospitals and clinics around the state. The MBCCCP has screened over 67,000 women and has provided roughly 72,000 mammograms. Copyright: Copyright 2017 Elsevier B.V., All rights reserved.

PY - 2003/9/1

Y1 - 2003/9/1

N2 - Background and Objective: This study demonstrates the impact of survey nonresponse bias on conclusions from a mammography trial targeting a disadvantaged population. Methods: The trial randomized 1558 women to three interventions designed to promote repeat mammography: mailed reminder (minimum group); mailed thank-you card, patient newsletters, and reminder (maximum group); and no mailings (control group). The primary outcome, repeat mammogram within 15 months, was assessed from administrative and phone survey data. Results: Administrative estimates revealed a statistically significant difference of 7% between the maximum and control groups on the primary outcome. Survey estimates (response rate 80%) revealed no significant differences. The differences by data source were traced to a survey nonresponse bias. There was a statistically significant difference of 16% between the maximum and control groups among survey nonrespondents for the primary outcome, but there were no differences among survey respondents. Conclusion: The findings reiterate that even a low survey nonresponse rate can bias study conclusions and suggest studies targeting disadvantaged populations should avoid relying solely on survey data for outcome analyses.

AB - Background and Objective: This study demonstrates the impact of survey nonresponse bias on conclusions from a mammography trial targeting a disadvantaged population. Methods: The trial randomized 1558 women to three interventions designed to promote repeat mammography: mailed reminder (minimum group); mailed thank-you card, patient newsletters, and reminder (maximum group); and no mailings (control group). The primary outcome, repeat mammogram within 15 months, was assessed from administrative and phone survey data. Results: Administrative estimates revealed a statistically significant difference of 7% between the maximum and control groups on the primary outcome. Survey estimates (response rate 80%) revealed no significant differences. The differences by data source were traced to a survey nonresponse bias. There was a statistically significant difference of 16% between the maximum and control groups among survey nonrespondents for the primary outcome, but there were no differences among survey respondents. Conclusion: The findings reiterate that even a low survey nonresponse rate can bias study conclusions and suggest studies targeting disadvantaged populations should avoid relying solely on survey data for outcome analyses.

KW - Health education

KW - Intervention studies

KW - Mammography

KW - Nonrespondents

KW - Randomized controlled trial

KW - Selection bias

UR - http://www.scopus.com/inward/record.url?scp=0141849361&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0141849361&partnerID=8YFLogxK

U2 - 10.1016/S0895-4356(03)00061-1

DO - 10.1016/S0895-4356(03)00061-1

M3 - Article

C2 - 14505772

AN - SCOPUS:0141849361

VL - 56

SP - 867

EP - 873

JO - Journal of Chronic Diseases

JF - Journal of Chronic Diseases

SN - 0895-4356

IS - 9

ER -

The impact of survey nonresponse bias on conclusions drawn from a mammography intervention trial

Abstract

Bibliographical note

Keywords

Access

Other files and links

Cite this