Kurse: Kursinformationen

Symposium "Causality in Educational Research"

From July 24 to 26, 2012 was held a conference at the "Altes Schloss Dornburg" near Jena.

Aim of the symposium

The symposium is intended to sharpen our ideas and instruments for the analysis of conditional and direct treatment effects. Why does this aim seem to be warranted? In the last decades, analyses of causal effects have mainly focussed on average total effects of treatments. This is appropriate if we are interested in the overall or total effectiveness of treatments in a population of subjects. However, conditional and direct treatment (intervention, exposition) effects are more informative and scientifically more interesting (MacKinnon, 2008).

With conditional total effects we consider the effects of a treatment on an outcome variable given a value of one or more covariates. Such a covariate can be sex, diagnostic group, severity of symptoms before treatment, motivation for treatment, or a multivariate variable consisting of several of such one-dimensional variables. Such conditional total effects can differ from each other between different values of the covariates. Hence, with conditional total effects we can quantify the total treatment effects for different (groups of) subjects. How big are the total effects for which kind of subjects? Note that total treatment effects may be positive for some and negative for others. Hence, in clinical research, conditional total effects deal with differential indication of a treatment.

Average and conditional total effects deal with the total effects of a treatment. In contrast, with direct effects we ask for the effects of a treatment that are not transmitted by intermediate variables that, in the process considered, occur up to a specified time point. Controlling for all pre-treatment variables and all variables in between treatment and a specified time point of the process, is there still an effect of the treatment? How big are these direct effects on average? How do they differ for different values of the variables controlled? Hence, now we ask: How big are the direct effects for which kinds of subjects? In educational research we may ask if the effects of a teaching method are transmitted to the outcome variable by raising the motivation to learn and by increasing time spent on learning, or if the total effect observed is not mediated through these and other variables occurring in the process up to the time point to which time spent on learning refers.

Asking for direct causal effects of a treatment has gained increasing interest in the last years because it has been shown that the well-known path analysis procedures for the analysis of direct and indirect effects often lead to systematically wrong results even in the randomized experiment. This is due to the fact that independence of treatment and covariates induced by randomization is cancelled as soon as we condition on an intermediate variable that is affected by treatment and is correlated with a pre-treatment variable. In this case, the partial correlation between the treatment variable and the covariate, controlling for the intermediate variable, is not zero. For example, if the intermediate motivation is affected by treatment and it depends on pre-treatment motivation, then a high score on intermediate motivation goes along with a high score on treatment (e. g., 1) and a high score on pre-treatment motivation, whereas a low score on intermediate motivation goes along with a low score on treatment (e. g., 0) and a low score on pre-treatment motivation. Independence of the treatment variable and all pre-treatment variables (induced by randomization) implies unbiasedness of mean differences of the outcome variable between treatment groups, but it does not imply unbiasedness of direct effects if we only include treatment, intermediate, and outcome variables in our analysis.

References:

• Baron, R. M., & Kenny, D. A. (1986). The moderator-mediator variable distinction in social psychological research: Conceptual, strategic and statistical considerations. Journal of Personality and Social Psychology, 51(6), 1173-1182.
• MacKinnon, D. P. (2008). Introduction to statistical mediation analysis. New York: Lawrence Erlbaum.

Organizational structure

The structure of the conference was closely followed the "Symposium on Causality 2010". There were 5 focus presentations by leading proponents in different fields of causality research. Each focus presentation was discussed and supplemented by two invited discussants, followed by an open discussion among all participants. There was also be room for participants to present their own research in short presentations.

For further information, please visit the website of the Symposium on Causality 2012.

Um die herunterladbaren Videos anzuschauen, benötigen Sie den VLC media player, den Sie hier herunterladen können. Die Videos werden bereitgestellt über die Digitale Bibliothek Thüringen (dbt). Die grün verlinkten Videos und Materialien sind kostenfrei abrufbar. Klicken Sie auf den grünen Link, um das Video zu sehen oder die Datei herunterzuladen! Um alle Materialien und Videos abrufen zu können, müssen Sie sich einloggen.

Videos

	Monday, July 23	Tuesday, July 24	Wednesday, July 25	Thursday, July 26
09:00 - 09:45		David MacKinnon "Introduction to Mediation Analysis: Importance, Applications, and Examples" Video 01 with slides Rolf Steyer "The definition of total, direct and indirect effects and their identification" Video 01 with slides	Kosuke Imai "The potential outcome approach to direct effects: Definition, identification, and sensitivity analysis" Video 05 with slides Stephen West Invited discussion Video 05 with slides	Felix Thoemmes "Covariate selection for total and direct effects: A comparative view" Video 09 with slides Peter Steiner Invited discussion Video 09 with slides
09:45 - 10:15
10:15 - 10:45
10:45 - 11:15		Coffee break	Coffee break	Coffee break
11:15 - 12:30		Axel Mayer "Identification and estimation of direct and indirect effects" Video 02 with slides General discussion	General discussion Video 06 with slides	Johannes Textor "Graphical Approaches to Covariate Selection for Direct and Partial Causal Effects" Video 10 with slides General discussion Video 10 with slides
12:30 - 14:15		Lunch	Lunch	Packed lunch at departure instead of lunch
14:15 - 15:15		Short contributions Marie-Ann Sengewald "Accounting for fallible covariates - a comparison of ANCOVA and Propensity Score methods" Video 03 with slides Martin Huber "Identifying causal mechanisms in experiments (primarily) based on inverse probability weighting" Video 03 with slides	Short contributions Ana Kolar "Causal Inference From Small Samples Using Propensity Score Matching Techniques" Video 07 with slides Sonja Hahn "Unbalanced designs containing a qualitative covariate as a factor: Are two-way ANOVA procedures adequate to test a causal hypothesis?" Video 07 with slides Boris Mayer "Conditional Causal Effects in Cross-Cultural Research: Two Examples using HLM and SEM" Video 07 with slides
15:15 - 15:45		Coffee break	Coffee break
15:45 - 16:30		Philip Dawid "A probabilistic approach to direct and indirect effects" Video 04 with slides Andreas Klein "Conceptual difficulties of modeling mediation: Logical and statistical problems intertwined" Video 04 with slides	Susanne Rässler "Conditional effects: How to use them in practice" Video 08 with slides David Rindskopf Invited discussion Video 08 with slides
16:30 - 17:00
17:00 - 17:30
17:30 - 18:00		General discussion	General discussion
19:30	Welcome Reception
20:00			Conference Dinner

Material related to the contributions

Focus presentations

Philip Dawid - "A probabilistic approach to direct and indirect effects"

• Didelez, V., Dawid, A. P. and Geneletti, S. (2006). Direct and indirect effects of sequential treatments. In Proc. 22nd Annual Conference on Uncertainty in Artical Intelligence (R. Dechter and T. S. Richardson, Eds.). AUAI Press, Arlington, Virginia, 138-146.
• Geneletti, S. (2007). Identifying direct and indirect effects in a non-counterfactual framework. J. R. Statist. Soc. B 69, Part 2, 199-215.

Kosuke Imai - "The potential outcome approach to direct effects: Definition, identification, and sensitivity analysis"

• Identification and Sensitivity Analysis for Multiple Causal Mechanisms: Revisiting Evidence from Framing Experiments

David MacKinnon - "Introduction to Mediation Analysis: Importance, Applications, and Examples"

• Slides: Introduction to Mediation Analysis: Importance, Applications, and Examples
• Reference list: Introduction to Mediation Analysis: Importance, Applications, and Examples

Rolf Steyer - "The definition of total, direct and indirect effects and their identification"

• Total, Direct and Indirect Effects
• Slides: Total, direct, and indirect effects in experiments and quasi-experiments

Johannes Textor - "Graphical Approaches to Covariate Selection for Direct and Partial Causal Effects"

• Presentation: Graphical Approaches to Covariate Selection for Direct and Partial Causal Effects

Felix Thoemmes - "Covariate selection for total and direct effects: A comparative view"

• Slides: Covariate selection for total and direct effects: A comparative view

Short contributions

Sonja Hahn

• Abstract: "Unbalanced designs containing a qualitative covariate as a factor: Are two-way ANOVA procedures adequate to test a causal hypothesis?"
• Slides: "Unbalanced designs containing a qualitative covariate as a factor: Are two-way ANOVA procedures adequate to test a causal hypothesis?"

Martin Huber

• Abstract: "Identifying causal mechanisms in experiments (primarily) based on inverse probability weighting"
• Presentation: "Identifying causal mechanisms in experiments (primarily) based on inverse probability weighting"

Ana Kolar

• Abstract: "Causal Inference From Small Samples Using Propensity Score Matching Techniques"

Boris Mayer

• Abstract: "Conditional Causal Effects in Cross-Cultural Research: Two Examples using HLM and SEM"

Marie-Ann Sengewald

• Abstract: "Accounting for fallible covariates - a comparison of ANCOVA and Propensity Score methods"
• Slides: "Accounting for fallible covariates in ANCOVA and Propensity Score methods"