TY - JOUR
T1 - A comparison of methods to test for mediation in multisite experiments
AU - Pituch, Keenan A.
AU - Whittaker, Tiffany A.
AU - Stapleton, Laura M.
N1 - Funding Information:
This research was supported by a Summer Research Assignment grant from the University of Texas at Austin to Keenan A. Pituch. We would like to thank Professor David P. MacKinnon, Arizona State University, for providing the SAS code used to implement the MacKinnon and Lockwood (2001) asymmetric confidence limits method.
PY - 2005
Y1 - 2005
N2 - A Monte Carlo study extended the research of MacKinnon, Lockwood, Huffman, West, and Sheets (2002) for single-level designs by examining the statistical performance of four methods to test for mediation in a multilevel experimental design. The design studied was a two-group experiment that was replicated across several sites, included a single intervening variable and outcome, and assumed that the effects of the treatment and mediator were constant across sites. The findings provide new evidence of the benefits of and further support for using the asymmetric confidence limits approach to test for mediation. In addition, the authors provide further support for using confidence intervals to assess if treatment effects are completely mediated, as using traditional hypothesis testing may lead to erroneous conclusions.
AB - A Monte Carlo study extended the research of MacKinnon, Lockwood, Huffman, West, and Sheets (2002) for single-level designs by examining the statistical performance of four methods to test for mediation in a multilevel experimental design. The design studied was a two-group experiment that was replicated across several sites, included a single intervening variable and outcome, and assumed that the effects of the treatment and mediator were constant across sites. The findings provide new evidence of the benefits of and further support for using the asymmetric confidence limits approach to test for mediation. In addition, the authors provide further support for using confidence intervals to assess if treatment effects are completely mediated, as using traditional hypothesis testing may lead to erroneous conclusions.
UR - http://www.scopus.com/inward/record.url?scp=25444435952&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=25444435952&partnerID=8YFLogxK
U2 - 10.1207/s15327906mbr4001_1
DO - 10.1207/s15327906mbr4001_1
M3 - Article
AN - SCOPUS:25444435952
SN - 0027-3171
VL - 40
SP - 1
EP - 23
JO - Multivariate Behavioral Research
JF - Multivariate Behavioral Research
IS - 1
ER -