Experience with multiple control groups in a large population-based case control study on genetic and environmental risk factors

E.R. Pomp, K.J. van Stralen, S. le Cessie, J.P. Vandenbroucke, F.R. Rosendaal, Catharina Jacoba Maria Doggen

Research output: Contribution to journalArticleAcademicpeer-review

15 Citations (Scopus)
41 Downloads (Pure)

Abstract

We discuss the analytic and practical considerations in a large case–control study that had two control groups; the first control group consisting of partners of patients and the second obtained by random digit dialling (RDD). As an example of the evaluation of a general lifestyle factor, we present body mass index (BMI). Both control groups had lower BMIs than the patients. The distribution in the partner controls was closer to that of the patients, likely due to similar lifestyles. A statistical approach was used to pool the results of both analyses, wherein partners were analyzed with a matched analysis, while RDDs were analyzed without matching. Even with a matched analysis, the odds ratio with partner controls remained closer to unity than with RDD controls, which is probably due to unmeasured confounders in the comparison with the random controls as well as intermediary factors. However, when studying injuries as a risk factor, the odds ratio remained higher with partner control subjects than with RRD control subjects, even after taking the matching into account. Finally we used factor V Leiden as an example of a genetic risk factor. The frequencies of factor V Leiden were identical in both control groups, indicating that for the analyses of this genetic risk factor the two control groups could be combined in a single unmatched analysis. In conclusion, the effect measures with the two control groups were in the same direction, and of the same order of magnitude. Moreover, it was not always the same control group that produced the higher or lower estimates, and a matched analysis did not remedy the differences. Our experience with the intricacies of dealing with two control groups may be useful to others when thinking about an optimal research design or the best statistical approach.
Original languageEnglish
Pages (from-to)459-466
JournalEuropean journal of epidemiology
Volume25
Issue number7
DOIs
Publication statusPublished - 2010

Fingerprint

Case-Control Studies
Control Groups
Population
Life Style
Body Mass Index
Odds Ratio
Wounds and Injuries
factor V Leiden
Direction compound
Thinking

Keywords

  • IR-76793
  • METIS-271440

Cite this

Pomp, E.R. ; van Stralen, K.J. ; le Cessie, S. ; Vandenbroucke, J.P. ; Rosendaal, F.R. ; Doggen, Catharina Jacoba Maria. / Experience with multiple control groups in a large population-based case control study on genetic and environmental risk factors. In: European journal of epidemiology. 2010 ; Vol. 25, No. 7. pp. 459-466.
@article{35d0957d8b124d0893fcdef5f6ee0921,
title = "Experience with multiple control groups in a large population-based case control study on genetic and environmental risk factors",
abstract = "We discuss the analytic and practical considerations in a large case–control study that had two control groups; the first control group consisting of partners of patients and the second obtained by random digit dialling (RDD). As an example of the evaluation of a general lifestyle factor, we present body mass index (BMI). Both control groups had lower BMIs than the patients. The distribution in the partner controls was closer to that of the patients, likely due to similar lifestyles. A statistical approach was used to pool the results of both analyses, wherein partners were analyzed with a matched analysis, while RDDs were analyzed without matching. Even with a matched analysis, the odds ratio with partner controls remained closer to unity than with RDD controls, which is probably due to unmeasured confounders in the comparison with the random controls as well as intermediary factors. However, when studying injuries as a risk factor, the odds ratio remained higher with partner control subjects than with RRD control subjects, even after taking the matching into account. Finally we used factor V Leiden as an example of a genetic risk factor. The frequencies of factor V Leiden were identical in both control groups, indicating that for the analyses of this genetic risk factor the two control groups could be combined in a single unmatched analysis. In conclusion, the effect measures with the two control groups were in the same direction, and of the same order of magnitude. Moreover, it was not always the same control group that produced the higher or lower estimates, and a matched analysis did not remedy the differences. Our experience with the intricacies of dealing with two control groups may be useful to others when thinking about an optimal research design or the best statistical approach.",
keywords = "IR-76793, METIS-271440",
author = "E.R. Pomp and {van Stralen}, K.J. and {le Cessie}, S. and J.P. Vandenbroucke and F.R. Rosendaal and Doggen, {Catharina Jacoba Maria}",
note = "Open access journal",
year = "2010",
doi = "10.1007/s10654-010-9475-z",
language = "English",
volume = "25",
pages = "459--466",
journal = "European journal of epidemiology",
issn = "0393-2990",
publisher = "Springer",
number = "7",

}

Experience with multiple control groups in a large population-based case control study on genetic and environmental risk factors. / Pomp, E.R.; van Stralen, K.J.; le Cessie, S.; Vandenbroucke, J.P.; Rosendaal, F.R.; Doggen, Catharina Jacoba Maria.

In: European journal of epidemiology, Vol. 25, No. 7, 2010, p. 459-466.

Research output: Contribution to journalArticleAcademicpeer-review

TY - JOUR

T1 - Experience with multiple control groups in a large population-based case control study on genetic and environmental risk factors

AU - Pomp, E.R.

AU - van Stralen, K.J.

AU - le Cessie, S.

AU - Vandenbroucke, J.P.

AU - Rosendaal, F.R.

AU - Doggen, Catharina Jacoba Maria

N1 - Open access journal

PY - 2010

Y1 - 2010

N2 - We discuss the analytic and practical considerations in a large case–control study that had two control groups; the first control group consisting of partners of patients and the second obtained by random digit dialling (RDD). As an example of the evaluation of a general lifestyle factor, we present body mass index (BMI). Both control groups had lower BMIs than the patients. The distribution in the partner controls was closer to that of the patients, likely due to similar lifestyles. A statistical approach was used to pool the results of both analyses, wherein partners were analyzed with a matched analysis, while RDDs were analyzed without matching. Even with a matched analysis, the odds ratio with partner controls remained closer to unity than with RDD controls, which is probably due to unmeasured confounders in the comparison with the random controls as well as intermediary factors. However, when studying injuries as a risk factor, the odds ratio remained higher with partner control subjects than with RRD control subjects, even after taking the matching into account. Finally we used factor V Leiden as an example of a genetic risk factor. The frequencies of factor V Leiden were identical in both control groups, indicating that for the analyses of this genetic risk factor the two control groups could be combined in a single unmatched analysis. In conclusion, the effect measures with the two control groups were in the same direction, and of the same order of magnitude. Moreover, it was not always the same control group that produced the higher or lower estimates, and a matched analysis did not remedy the differences. Our experience with the intricacies of dealing with two control groups may be useful to others when thinking about an optimal research design or the best statistical approach.

AB - We discuss the analytic and practical considerations in a large case–control study that had two control groups; the first control group consisting of partners of patients and the second obtained by random digit dialling (RDD). As an example of the evaluation of a general lifestyle factor, we present body mass index (BMI). Both control groups had lower BMIs than the patients. The distribution in the partner controls was closer to that of the patients, likely due to similar lifestyles. A statistical approach was used to pool the results of both analyses, wherein partners were analyzed with a matched analysis, while RDDs were analyzed without matching. Even with a matched analysis, the odds ratio with partner controls remained closer to unity than with RDD controls, which is probably due to unmeasured confounders in the comparison with the random controls as well as intermediary factors. However, when studying injuries as a risk factor, the odds ratio remained higher with partner control subjects than with RRD control subjects, even after taking the matching into account. Finally we used factor V Leiden as an example of a genetic risk factor. The frequencies of factor V Leiden were identical in both control groups, indicating that for the analyses of this genetic risk factor the two control groups could be combined in a single unmatched analysis. In conclusion, the effect measures with the two control groups were in the same direction, and of the same order of magnitude. Moreover, it was not always the same control group that produced the higher or lower estimates, and a matched analysis did not remedy the differences. Our experience with the intricacies of dealing with two control groups may be useful to others when thinking about an optimal research design or the best statistical approach.

KW - IR-76793

KW - METIS-271440

U2 - 10.1007/s10654-010-9475-z

DO - 10.1007/s10654-010-9475-z

M3 - Article

VL - 25

SP - 459

EP - 466

JO - European journal of epidemiology

JF - European journal of epidemiology

SN - 0393-2990

IS - 7

ER -