|
Modern Management Techniques’ Impact on Performance: Do Matched Sample Studies Provide Valid Evidence?
Donald P. Cram,
Unaffiliated
Vijay Karan, California State University Fullerton
Iris Stuart, California State University Fullerton
ABSTRACT. Management accounting researchers have used matched samples to study the effects on firms’ performance of adopting various modern management techniques. We apply Cram, Karan, and Stuart’s (CKS, 2006) framework to review 12 such papers, and observe three methodological errors in their implementation. Analysis in five papers suffers from CKS’s Error 1: use of unconditional analysis when conditional analysis is required. Ten suffer from CKS’s Errors 2 and 3: failure to control for imperfectly matched variables and failure to reweight according to differential sampling rates. All fail to untangle the interaction between prospective future performance from self-selection in choosing to adopt the management technique. Two studies apply two-stage models that could control for self-selection in random samples, but which we observe cannot be applied to matched samples. Matched samples may yet serve in identifying determinants of adoption, which contributes to the intended research goals.
Full-Text is no longer available online. Please contact the author(s) for more information about this manuscript.
Back to Session Listing
|