Same data, different conclusions: Radical dispersion in empirical results when independent analysts operationalize and test the same hypothesis
- Authors:
- ; ; ; ; ; ; ; ; ; ; ; ; ; ; ; ; ; ; ; more »
- Award ID(s):
- 1901386
- Publication Date:
- NSF-PAR ID:
- 10293112
- Journal Name:
- Organizational Behavior and Human Decision Processes
- Volume:
- 165
- Issue:
- C
- Page Range or eLocation-ID:
- 228 to 249
- ISSN:
- 0749-5978
- Sponsoring Org:
- National Science Foundation
More Like this
-
Abstract The COVID-19 pandemic imposed new norms on human interactions, perhaps best reflected in the widespread application of social distancing. But social distancing is not a human invention and has evolved independently in species as dissimilar as apes and lobsters. Epidemics are common in the wild, where their spread is enhanced by animal movement and sociality while curtailed by population fragmentation, host behavior, and the immune systems of hosts. In the present article, we explore the phenomenon of behavioral immunity in wild animals as compared with humans and its relevance to the control of disease in nature. We start by explaining the evolutionary benefits and risks of sociality, look at how pathogens have shaped animal evolution, and provide examples of pandemics in wild animal populations. Then we review the known occurrences of social distancing in wild animals, the cues used to enforce it, and its efficacy in controlling the spread of diseases in nature.
-
We prove that local projections (LPs) and Vector Autoregressions (VARs) estimate the same impulse responses. This nonparametric result only requires unrestricted lag structures. We discuss several implications: (i) LP and VAR estimators are not conceptually separate procedures; instead, they are simply two dimension reduction techniques with common estimand but different finite‐sample properties. (ii) VAR‐based structural identification—including short‐run, long‐run, or sign restrictions—can equivalently be performed using LPs, and vice versa. (iii) Structural estimation with an instrument (proxy) can be carried out by ordering the instrument first in a recursive VAR, even under noninvertibility. (iv) Linear VARs are as robust to nonlinearities as linear LPs.