SPSS and SAS Programming for the Testing of Mediation Models

BackgroundMediation modeling can explain the nature of the relation among three or more variables. In addition, it can be used to show how a variable mediates the relation between levels of intervention and outcome. The Sobel test, developed in 1990, provides a statistical method for determining the influence of a mediator on an intervention or outcome. Although interactive Web-based and stand-alone methods exist for computing the Sobel test, SPSS and SAS programs that automatically run the required regression analyses and computations increase the accessibility of mediation modeling to nursing researchers. ObjectivesTo illustrate the utility of the Sobel test and to make this programming available to the Nursing Research audience in both SAS and SPSS. MethodsThe history, logic, and technical aspects of mediation testing are introduced. The syntax files sobel.sps and sobel.sas, created to automate the computation of the regression analysis and test statistic, are available from the corresponding author. ResultsThe reported programming allows the user to complete mediation testing with the user’s own data in a single-step fashion. A technical manual included with the programming provides instruction on program use and interpretation of the output. ConclusionMediation modeling is a useful tool for describing the relation between three or more variables. Programming and manuals for using this model are made available.

[1]  D. A. Kenny,et al.  The moderator-mediator variable distinction in social psychological research: conceptual, strategic, and statistical considerations. , 1986, Journal of personality and social psychology.

[2]  Y. Miller,et al.  Mediators of physical activity behavior change among women with young children. , 2002, American journal of preventive medicine.

[3]  D. Mackinnon,et al.  Estimating Mediated Effects in Prevention Studies , 1993 .

[4]  S. Walker,et al.  Theoretical and methodological differentiation of moderation and mediation. , 1993, Nursing research.

[5]  R. Schulz,et al.  Activity restriction mediates the association between pain and depressed affect: a study of younger and older adult cancer patients. , 1995, Psychology and aging.

[6]  D P MacKinnon,et al.  Analysis of mediating variables in prevention and intervention research. , 1994, NIDA research monograph.

[7]  L. A. Goodman.  On the Exact Variance of Products , 1960 .

[8]  J. A. Bennett,et al.  Mediator and moderator variables in nursing research: conceptual and statistical differences. , 2000, Research in nursing & health.

[9]  D. R. Shaffer,et al.  Caregiver models of self and others, coping, and depression: predictors of depression in children with chronic pain. , 2002, Health psychology : official journal of the Division of Health Psychology, American Psychological Association.

[10]  M. Sobel.  Effect analysis and causation in linear structural equation models , 1990 .

[11]  A. Stewart,et al.  The Mediating Effect of Pain and Fatigue on Level of Functioning in Older Adults , 2002, Nursing research.

[12]  M. Hennessy,et al.  Using structural equations to estimate effects of behavioral interventions , 1994 .

[13]  G. Williamson,et al.  The Role of Activity Restriction in the Association Between Pain and Depression: A Study of.. , 1999 .

[14]  S. West,et al.  A comparison of methods to test mediation and other intervening variable effects. , 2002, Psychological methods.

[15]  A. Dunn,et al.  Psychosocial mediators of physical activity behavior among adults and children. , 2002, American journal of preventive medicine.