Edited by Raymond J.G.M. Florax, Peter Nijkamp and Kenneth G. Willis
Chapter 10: Methodological pitfalls in meta-analysis: publication bias
179 pling of studies for the meta-analysis may still have a negative impact on the validity of the meta-analysis. Selectivity can refer to various aspects of the sampling process: the meta-sample may be biased in terms of, for instance, theoretical perspectives, spatial and / or temporal coverage, data type, publication outlet and statistical techniques. The negative connotation that we usually attach to ‘sample selection bias’ is indicative of the harmful eﬀect on the validity of the meta-analysis. The latter occurs when there is a systematic relationship between characteristics of the sampling process and the signiﬁcance or magnitude of the eﬀect size. The issue of publication bias did not generate a sizeable discussion in the economic literature. Among the few exceptions are Card and Krueger (1995) and Ashenfelter et al. (1999), who systematically investigate the occurrence and impact of publication bias with respect to studies on minimum wages and studies on the relation between schooling and earnings, respectively. In the area of environmental economics, speciﬁcally in the ﬁeld of environmental valuation that constitutes the prime area in which meta-analysis has been applied, publication bias received some attention as well.1 Smith and Huang (1995), for instance, stress the disturbing eﬀect that sample selection bias may have on the outcome of the metaanalysis. They use a two-stage Heckman-like probit model to determine the likelihood of sample selection bias, and subsequently include the inverse Mill’s ratio in the meta-regression. The ratio is related to the estimated probability of including...
You are not authenticated to view the full text of this chapter or article.
Elgaronline requires a subscription or purchase to access the full text of books or journals. Please login through your library system or with your personal username and password on the homepage.
Non-subscribers can freely search the site, view abstracts/ extracts and download selected front matter and introductory chapters for personal use.
Your library may not have purchased all subject areas. If you are authenticated and think you should have access to this title, please contact your librarian.