Skip to main content
. Author manuscript; available in PMC: 2015 Apr 1.
Published in final edited form as: Eval Program Plann. 2013 Dec 10;43:93–102. doi: 10.1016/j.evalprogplan.2013.11.003

Table 5.

Mediation analysis examining effects of implementation variables on study outcomes of physical activity and fruit and vegetable intake.

Group assignment → change in
implementation variable a path		 Change in implementation variable
→change in outcome variable
b path		 Asymmetric confidence limits
Estimate (SE) p-Value Estimate (SE) p-Value
Physical activity (n = 632)
Physical activity messages .1032 (.04856) .0374 −.04158 (.1042) .690 −.031, .019
Physical activity opportunities .305 (.03572) <.0001 −.1368 (.1122) .2232 −.112, .025
Physical activity pastor support .1747 (.03221) <.0001 −.05434 (.1326) .6821 −.057, .037
Physical activity policy (n = 314) .2836 (.04291) <.0001 −.02440 (.2208) .9121 −.133, .118
Healthy eating (n = 627)
Healthy eating messages .1261 (.04658) .0086 .05158 (.06275) .4114 −.009, .026
Healthy eating opportunities .04332 (.04751) .3652 −.01843 (.07647) .8097 −.012, .009
Healthy eating pastor support .1342 (.04278) .0025 .01591 (.06441) .8050 −.016, .021
Fruit and vegetable policy (n = 316) .5348 (.04245) <.0001 −.1196 (.1367) .3825 −.210, .079

Note: If the asymmetric confidence limits include 0, there is no evidence of mediation.