Instrumental variables based on twin births are by definition not valid (v.3.0)

No zux9s, SocArXiv from Center for Open Science

Abstract: Twin births are a well-known and widespread example of a so-called “natural experiment”. Instrumental variables based on twin births have been used in many studies to estimate the causal effect of the number of children on the parents or siblings. I use the potential outcomes framework to show that these instrumental variables do not work as intended. They are fundamentally flawed and will always lead to severely biased estimates without any meaningful interpretation. This has been overlooked in previous research because too little attention has been paid to defining the treatment in this natural experiment. I analyze three different possible interpretations of the treatment and show that they all lead to inherent violations of the necessary assumptions. The effect of the number of on the parents or siblings is a policy relevant and theoretically important issue. The scientific record should therefore be corrected to not lead to misguided decisions.

Date: 2018-03-27
References: View references in EconPapers View complete reference list from CitEc
Citations: View citations in EconPapers (2) Track citations by RSS feed

Downloads: (external link)
https://osf.io/download/594e98af6c613b0229e383e2/

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:osf:socarx:zux9s

DOI: 10.31219/osf.io/zux9s

Access Statistics for this paper

More papers in SocArXiv from Center for Open Science
Bibliographic data for series maintained by OSF ().