Developing confidence intervals for economic impacts: A multi-regional analysis of a recreational fishery in Korea

This study constructs confidence intervals for the economic impacts of recreational fishing in the Gyeong-Nam (GN) province of Korea, using a multi-regional input-output (MRIO) model for 16 provinces in Korea. Recreation-related expenditures are first bootstrapped, and then confidence intervals surrounding the change in total industry output of each province were calculated using two methods normal approximation and bias corrected percentile (BCP). The results show that, at the 95% confidence level, the interval endpoints of the economic impacts for the provinces are 8.9-10.3% percent above or below the point estimate from the original sample when calculated using the normal approximation method. The BCP method yields endpoints that are 8.7% below to 13.1% above the point estimate. The wide intervals of the economic impacts shown in this study imply that policy decisions based solely upon the point estimates could be misled.