Academic journal article Journal of Contemporary Athletics

The Limiting Use of Meta-Analysis in Sport Management: A Case Study Examining the Effects of Constraints on Sport and Leisure Consumption

Academic journal article Journal of Contemporary Athletics

The Limiting Use of Meta-Analysis in Sport Management: A Case Study Examining the Effects of Constraints on Sport and Leisure Consumption

Article excerpt


Meta-analysis is a statistical tool used to integrate results of empirical research that are independent from each other (Rosenblad, 2009). Results of properly conducted meta-analyses can be used to identify relevant moderators in existing research. Additionally, meta-analysis, by combining results of previous quantitative research, can determine whether findings hold in a general context (Mullen, 1986). For example, Palmatier, Dant, Grewal, and Evans (2006) used meta-analysis to better understand which relationship marketing strategies were most effective for building strong relationships, and the conditions in which relationship marketing was most effective for generating positive seller outcomes. Accordingly, meta-analysis can provide practitioners with a better understanding of which strategies were most effective. This allows scholars to increase their return on investments. Furthermore, researchers can use meta-analysis to build more comprehensive models of how relationship marketing strategies influence performance (Palmatier et al., 2006). We use Palmatier et al's meta-analysis study as an example because it is highly cited among marketing scholars. In the next paragraphs we summarize the approach taken by Palmatier et al. (2006) in their meta-analysis.

Palmatier et al. (2006) were able to systematically review and analyze past research on relational mediators in a meta-analytic framework by employing various methods for the literature search including -(1) a search of the ABI/Informs, PsycINFO, and Business Source Premier databases for each relational mediator; (2) a search of the Social Sciences Citation Index, using the seminal articles for these constructs; (3) manual shelf searches of journals that contain research on relational mediators; and (4) e-mails sent to researchers in the domain asking for their published and unpublished works." Their search resulted in more than 100 published and unpublished studies. Since most meta-analysis studies used a correlational design (>95%), Palmatier et al. (2006) used two independent coders to calculate effect sizes -r." An average -r" was calculated for studies that reported more than one effect size estimate for the same relationship. In the end, 637 correlations were aggregated from 111 independent samples drawn from 94 different manuscripts to yield a combined N of 38,077.

First, Palmatier et al. (2006) adjusted correlations for measurement error (scale reliability differences) using the Hunter and Schmidt method (1990). Then, sampling error was adjusted as the sample-weighted reliability-adjusted r and its 95% confidence intervals (CIs) were calculated. The next step in their meta-analysis was to calculate the chi-square test for association followed by the file-drawer problem and the Q statistic test of homogeneity. Finally, the data were analyzed using multivariate technique (nomological causal model) which has the advantage of estimating all parameters simultaneously.

The above example broadly illustrates the use of a meta-analysis for researchers. Palmatier et al's (2006) is just one out of many meta-analyses conducted in the marketing field, but the use of meta-analysis is not common practice in sport management. Take a sport management example where, despite the quantity of evidence supporting the negative impact of constraints on sport and leisure consumption, there is still a lack of investigation to identify which type of constraint is more detrimental and what moderators influence the relationship between constraints and sport/leisure consumption. Meta-analysis is an appropriate method to address these limitations because it can provide evidence for (a) which constraints impact sport and leisure consumption more negatively and (b) which moderators impact the relationships between independent and dependent variables.

Past research further confirms that meta-analysis is an attractive tool because it secures representative sample, avoids potential bias, and calculates effect sizes (Churchill, Ford, Hartley, & Walker, 1985; Glass, 1976; Glass, McGaw, & Smith, 1981). …

Search by... Author
Show... All Results Primary Sources Peer-reviewed


An unknown error has occurred. Please click the button below to reload the page. If the problem persists, please try again in a little while.