Working Paper: CEPR ID: DP15246
Authors: Morgan Kelly
Abstract: A large literature on persistence finds that many modern outcomes strongly reflect characteristics of the same places in the distant past. These studies typically combine unusually high t statistics with severe spatial autocorrelation in residuals, suggesting that some findings may be artefacts of underestimating standard errors or of fitting spatial trends. For 25 studies in leading journals, I apply three basic robustness checks against spatial trends and find that effect sizes typically fall by over half, leaving most well known results insignificant at conventional levels.Turning to standard errors, there is currently no data-driven method for selecting an appropriate HAC spatial kernel. The paper proposes a simple procedure where a kernel with a highly flexible functional form is estimated by maximum likelihood. After correction, standard errors tend to rise substantially for cross sectional studies but to fall for panels. Overall, credible identification strategies tend to perform no better than naive regressions. Although the focus here is on historical persistence, the methods apply to regressions using spatial data more generally.
Keywords: No keywords provided
JEL Codes: No JEL codes provided
Edges that are evidenced by causal inference methods are in orange, and the rest are in light blue.
| Cause | Effect |
|---|---|
| historical factors (B15) | modern socioeconomic variables (P36) |
| mortality of European settlers (J11) | modern socioeconomic variables (P36) |
| nature of colonial institutions (F54) | modern socioeconomic variables (P36) |
| historical events (like pogroms and slavery) (N33) | modern socioeconomic variables (P36) |
| spatial autocorrelation (C49) | inflated effect sizes of historical variables (C22) |
| controlling for regional characteristics (R23) | reduced effect sizes of historical variables (C22) |
| high level of spatial correlation (C49) | underestimated standard errors in spatial regressions (C21) |
| correcting standard errors (C20) | accurate interpretation of historical effects on modern outcomes (N30) |