Significance bias in the tourism-led growth literature

Abstract

We use an original meta-regression analysis to test the existence of bias of statistical significance in the literature on the study of Granger causality relationships between tourism and income. We conclude for the presence of such bias. We also conclude that some methodological choices are more likely to lead to statistically significant results. Additionally, we find that the empirical association between tourism and income is stronger the shorter the time horizon analyzed and that it is correlated with the countries' economic, touristic and demographic profile. Altogether, our results suggest that there are reasons to mistrust the typical methodological approach followed by the literature reviewed and cast doubt on its usual implications for economic policy.