The teacher, the physician and the person: exploring causal connections between teaching performance and role model types using directed acyclic graphs

PLoS One. 2013 Jul 23;8(7):e69449. doi: 10.1371/journal.pone.0069449. Print 2013.


Background: In fledgling areas of research, evidence supporting causal assumptions is often scarce due to the small number of empirical studies conducted. In many studies it remains unclear what impact explicit and implicit causal assumptions have on the research findings; only the primary assumptions of the researchers are often presented. This is particularly true for research on the effect of faculty's teaching performance on their role modeling. Therefore, there is a need for robust frameworks and methods for transparent formal presentation of the underlying causal assumptions used in assessing the causal effects of teaching performance on role modeling. This study explores the effects of different (plausible) causal assumptions on research outcomes.

Methods: This study revisits a previously published study about the influence of faculty's teaching performance on their role modeling (as teacher-supervisor, physician and person). We drew eight directed acyclic graphs (DAGs) to visually represent different plausible causal relationships between the variables under study. These DAGs were subsequently translated into corresponding statistical models, and regression analyses were performed to estimate the associations between teaching performance and role modeling.

Results: The different causal models were compatible with major differences in the magnitude of the relationship between faculty's teaching performance and their role modeling. Odds ratios for the associations between teaching performance and the three role model types ranged from 31.1 to 73.6 for the teacher-supervisor role, from 3.7 to 15.5 for the physician role, and from 2.8 to 13.8 for the person role.

Conclusions: Different sets of assumptions about causal relationships in role modeling research can be visually depicted using DAGs, which are then used to guide both statistical analysis and interpretation of results. Since study conclusions can be sensitive to different causal assumptions, results should be interpreted in the light of causal assumptions made in each study.

Publication types

  • Research Support, Non-U.S. Gov't

MeSH terms

  • Faculty*
  • Humans
  • Mentors / education*
  • Models, Statistical
  • Models, Theoretical*
  • Physicians*
  • Professional Competence*
  • Teaching*

Grant support

This study is part of the research project “Quality of clinical teachers and residency training programs,” which is co-financed by the Dutch Ministry of Health; the Academic Medical Center, Amsterdam; and the Faculty of Health and Life Sciences of the University of Maastricht. BB and KL are employed by the Academic Medical Centre, Amsterdam. AS is employed by the University of Maastricht. OA is a recipient of a Veni grant (#916.96.059) from the Netherlands Organization for Scientific Research (NWO). The funders had no role in study design, data collection, data analysis, data interpretation, decision to publish, or writing of the report.