Direction Dependence Analysis

News:

 

  • (April 15, 2019) New article: "Direction dependence analysis in the presence of confounders: Applications to linear mediation models using observational data" published in Multivariate Behavioral Research (click here for the article) 

 

  • (March 19, 2019) New article: "Confounder detection in linear mediation models: Performance of kernel-based tests of independence" published in Behavior Research Methods (click here for the article)

 

  • (December 7, 2018) R functions for standard DDA (v. 0.1) and introductory material have been released (click here to download)

 

  • (May 21, 2018) New article: "Testing the Causal Direction of Mediation Effects in Randomized Intervention Studies" published in Prevention Science (click here for the article)

 

  • (May 2, 2018) SPSS GUI Component package for standard DDA (v. 2.0) has been released (click here to download).

 

  • (April 19, 2018) SPSS Macros and Auxiliary GUI Component for conditional DDA (CDDA; beta version) has been released (click here to download)

 

 

Workshops/Presentations:
 
  • Basel, Switzerland, July 9-12, 2019 (Conference of the International School Psychology Association): "Prosocial Skills Causally Mediate the Relation Between Effective Classroom Management and Academic Competence: An Application of Direction Dependence Analysis". Paper presented at the Symposium "Specifying Mediators of Classroom Social-Behavioral Interventions".

 

  • Chicago, IL, May, 26, 2019 (45th Annual Convention of the Association for Behavior Analysis International): "Direction Dependence Analysis: Testing the direction of causation in non-experimental person-oriented research". Paper presented at the B. F. Skinner Lecture Series.

 

  • Vancouver, BC, August 1, 2018 (Joint Statistical Meeting): "Direction Dependence Modeling: A Diagnostic Framework to test the Causal Direction of Effects in Linear Models". Paper presented at the Symposion "Recent Development in the Assessment and Modeling of Asymmetric Dependence".
 

 

What is Direction Dependence Analysis?

 
A common problem with observational research is that it is often difficult to prove that a specific action causes an effect. Further, in many cases, alternative causal theories exist which may serve as an explanation for observed variable associations. In non-experimental studies, at least three possible explanations exist for the association of two variables x and y:
 
x is the cause of y (i.e., x y)
y is the cause of x (i.e., y x)
an unmeasured confounder u is present (i.e., x u y).
 
Direction Dependence Analysis (DDA) can be used to uniquely identify each explanatory model. DDA assumes that variables are non-normally distributed and makes use of higher moments (i.e., skewness and kurtosis) to gain deeper insight into the data-generating mechanism. DDA consists of three core components:
 
  • Distributional properties of observed variables
  • Distributional properties of error terms of competing models
  • Independence properties of predictors and error terms of competing models
 
Statistical inference methods for model selection, SPSS macros, and R scripts to implement DDA are provided here. Please go to the RESOURCES section to download source codes, manuals, posters, slides, and further information.

RESOURCES

PosterS AND SLIDES
SPSS mACROS
R SCRIPTS
uSER gUIDE & more

team


 

Network for Educator Effectiveness

 

University of Missouri


Department of Psychology

Michigan State University

REFERENCES 

  • Wiedermann, W., & Li, X. (2019). Confounder detection in linear mediation models: Performance of kernel-based tests of independence. Behavior Research Methods, (in press). [R Scripts
  • Wiedermann, W., Li, X., & von Eye A. (2018). Testing the causal direction of mediation effects in randomized intervention studies. Prevention Science, (in press) .
  • Wiedermann, W., & Sebastian, J. (2018). Direction dependence analysis in the presence of confounders: Applications to linear mediation models. Multivariate Behavioral Research, (in press). [R Scripts]
  • Wiedermann, W. (2018). A note on fourth-moment based direction dependence measures when regression errors are non-normal. Communications in Statistics: Theory and Methods, 47, 5255-5264.
  • Wiedermann, W., & Li, X. (2018). Direction dependence analysis: Testing the direction of effects in linear models with implementation in SPSS. Behavior Research Methods, 50 (4), 1581-1601.
  • Wiedermann, W., & von Eye, A. (2018). Log-linear models to evaluate direction of effect in binary variables. Statistical Papers, (in press). 
  • von Eye, A. & Wiedermann, W. (2018). Locating event-based causal effects: A configural perspective. Integrative Psychological and Behavioral Science, 52, 307-330. 
  • Wiedermann, W., Merkle, E.C., & von Eye, A. (2018). Direction of dependence in measurement error models. British Journal of Mathematical and Statistical Psychology, 71, 117-145. [R Script] [Supplement]
  • Wiedermann, W., Artner, R., & von Eye, A. (2017). Heteroscedasticity as a basis for direction dependence in reversible linear regression models. Multivariate Behavioral Research, 52, 222-241.
  • Wiedermann, W., & von Eye, A. (2016). Directional dependence in the analysis of single subjects. Journal of Person-Oriented Research, 2, 20-33. [pdf]
  • Wiedermann, W., & von Eye, A. (2016). Testing directionality of effects in causal mediation analysis. In W. Wiedermann & A. von Eye (eds), Statistics and Causality: Methods for applied empirical research, pp. 63-106. Hoboken, NJ: Wiley & Sons.
  • von Eye, A., & Wiedermann, W. (2016). Direction of effects in categorical variables: A structural perspective. In W. Wiedermann and A. von Eye (eds), Statistics and Causality: Methods for applied empirical research, pp. 107-130. Hoboken, NJ: Wiley & Sons.
  • Wiedermann, W., & Hagmann, M. (2016). Asymmetric properties of the Pearson correlation coefficient: Correlation as the negative association between linear regression residuals. Communications in Statistics: Theory and Methods, 45, 6263-6283. 
  • Wiedermann, W. (2015). Decisions concerning the direction of effects in linear regression models using fourth central moments. In M. Stemmler, W. Wiedermann, & A. von Eye (eds), Dependent data in social sciences research: Forms, issues, and methods of analysis, pp.149-169. Cham, CH: Springer.
  • Wiedermann, W., & von Eye, A. (2015). Direction dependence analysis: A confirmatory approach for testing directional theories. International Journal of Behavioral Development, 39, 570-580. 
  • Wiedermann, W., & von Eye, A. (2015). Direction of effects in mediation analysis. Psychological Methods, 20, 221-244.
  • Wiedermann, W., & von Eye, A. (2015). Direction of effects in multiple linear regression models. Multivariate Behavioral Research, 50, 23-40. 
  • Wiedermann, W., Hagmann, M., & von Eye, A. (2015). Significance tests to determine the direction of effects in linear regression models. British Journal of Mathematical and Statistical Psychology, 68, 116-141. 
  • von Eye, A., & Wiedermann, W. (2014). On direction of dependence in latent variable contexts. Educational and Psychological Measurement, 74, 5-30. 
  • von Eye, A., & DeShon, R.P. (2012). Directional dependence in developmental research. International Journal of Behavioral Development, 36, 303-312.

COMMUNICATIONS

We really appreciate, if you have any suggestions to help us improve, or if you have bugs to report.

We are glad to assist if you have unexpected warnings or other technical issues while using the macros.

You can also contact us via email