Self-controlled designs to control confounding

Pouwels, K., 2015, [Groningen]: University of Groningen. 233 p.

Research output: ThesisThesis fully internal (DIV)

Copy link to clipboard


  • Title and contents

    Final publisher's version, 179 KB, PDF document

  • Chapter 1

    Final publisher's version, 191 KB, PDF document

  • Chapter 2

    Final publisher's version, 1.21 MB, PDF document

  • Chapter 3

    Final publisher's version, 669 KB, PDF document

  • Chapter 4

    Final publisher's version, 762 KB, PDF document

  • Chapter 5

    Final publisher's version, 648 KB, PDF document

  • Chapter 6

    Final publisher's version, 535 KB, PDF document

  • Chapter 7

    Final publisher's version, 1.32 MB, PDF document

  • Chapter 8

    Final publisher's version, 1.47 MB, PDF document

  • Chapter 9

    Final publisher's version, 1.21 MB, PDF document

  • Summary

    Final publisher's version, 239 KB, PDF document

  • Samenvatting

    Final publisher's version, 328 KB, PDF document

  • Dankwoord

    Final publisher's version, 312 KB, PDF document

  • List of publications

    Final publisher's version, 229 KB, PDF document

  • Research Institute SHARE

    Final publisher's version, 326 KB, PDF document

  • Curriculum Vitae

    Final publisher's version, 155 KB, PDF document

  • Complete thesis

    Final publisher's version, 1.49 MB, PDF document

  • Propositions

    Final publisher's version, 51.6 KB, PDF document

  • Koen Pouwels
The best available evidence for decision-making on interventions will often come from observational studies. Given the vulnerability of observational studies to confounding, complete and transparent reporting on confounding is necessary to enable readers to assess the validity of study findings. In this thesis we assessed whether the reporting of confounding improved after the publication of the STROBE guideline. The reporting of confounding was similar before and after the publication of this reporting guideline and was not better in journals that more actively endorsed the guideline. Hence, research into the development and evaluation of strategies to improve the quality of reporting and adherence to reporting guidelines is needed rather than adding another guideline to the steadily increasing pile.

One of the more novel developments with regard to the control of confounding in observational studies is the application of a self-controlled design. In this thesis we applied and empirically compared various available self-controlled designs. Although self-controlled methods seemed to be able to control confounding better in situations where strong unmeasured time-invariant confounding was present, such designs are often applied when it is likely that assumptions underlying these designs are violated. Discrepancies between parallel group designs and self-controlled designs could be predicted by failure to meet assumptions of the self-controlled designs. Therefore, we recommend to apply self-controlled designs when there are concerns about unmeasured confounders, but also to verify whether assumptions are likely met and in case of uncertainty to apply sensitivity analyses.
Original languageEnglish
QualificationDoctor of Philosophy
Awarding Institution
  • Hak, Eelko, Supervisor
  • Stolk, Ronald, Assessment committee
  • Vansteelandt, Stijn, Assessment committee, External person
  • Zielhuis, Gerhard, Assessment committee, External person
Award date4-Dec-2015
Place of Publication[Groningen]
Print ISBNs978-90-367-8283-8
Electronic ISBNs978-90-367-8281-4
Publication statusPublished - 2015

Download statistics

No data available

ID: 25734011