Thomas D. Cook's scientific contributions

Publications (3)

Article
explicate four kinds of validity [statistical conclusion validity, internal validity, construct validity and external validity] / describe and critically examine some quasi-experimental designs from the perspective of these four kinds of validity, especially internal validity / argue that the quality of causal inference depends on the structural at...

Citations

... Specifically, we collected alliance data from the SDC Platinum database, while we used COMPUSTAT and the USPTO databases to obtain firms' financial and patent data. Further, to establish causality (Cook & Campbell, 1979) and determine the direction of relationships, we used a four-year time lag to separate independent and dependent variables. ...
... First, although the study conducted a three-wave time-lagged model to reduce common method effects (e.g., Podsakoff et al., 2012), we were not able to establish strong inferences about causality. Future research could improve on this by instituting experimental or quasi-experimental designs (e.g., Cook et al., 1990). CMV probably did not have strong effects on the results, however, for multiple reasons. ...
... The phenomena as observed within our case study (e.g. the processes, the attributes of involved actors etc.) correspond well with what we know from theory. A study with clear rationale for the case selection, including details on the study context (Cook and Campbell, 1979;Coviello and Jones, 2004) and additional qualitative preliminary interviews (see Supplementary material) enables us to gain substantial insights in understanding our setting as well as to reconcile the results with the theory. The weak point remains our inability to account for potential heterogeneity in terms of the comparison between different organizations, although we did perform several robustness checks (reminiscent of the nested approach) which indicated that the observed relationships are stable across the sample and in time (with technology transfer literature often citing the lack of insights from longitudinal data as limitations (e.g. ...