http:\/\/www.nber.org\/papers\/w23144?utm_campaign=ntw&utm_medium=email&utm_source=ntw<\/a><\/p>\nThis paper advocates a pedagogical paradigm shift\u00a0that has methodological ramifications beyond econometrics instruction;\u00a0As I understand it, the shift stands contrary to the traditional\u00a0teachings of causal inference, as defined by Sewall Wright (1920),\u00a0Haavelmo (1943), Marschak (1950), Wold (1960), and other\u00a0founding fathers of econometrics methodology.<\/p>\n
In a nut shell, Angrist and Pischke\u00a0 start with a set of favorite\u00a0statistical routines such as IV, regression, differences-in-differences\u00a0among others, and then search for “a set of control variables needed\u00a0to insure that the regression-estimated effect of the variable of\u00a0interest has a causal interpretation”. Traditional causal inference (including economics)\u00a0teaches us that asking whether the output of a statistical routine\u00a0“has a causal interpretation” is the wrong question\u00a0to ask, for it misses the direction of the analysis.\u00a0Instead, one should start with the target\u00a0causal parameter itself, and asks whether it is\u00a0ESTIMABLE (and if so how), be it by IV, regression,\u00a0differences-in-differences, or perhaps by some new routine\u00a0that is yet to be discovered and ordained by name.\u00a0Clearly, no “causal interpretation” is needed for parameters\u00a0that are intrinsically causal; for example, “causal effect”, “path coefficient”, “direct effect”, “effect of treatment on the treated”, or “probability of causation”.<\/p>\n
In practical terms, the difference between the two\u00a0paradigms is that estimability requires a substantive model\u00a0while interpretability appears to be model-free. A model exposes its assumptions explicitly, while\u00a0statistical routines give the deceptive impression that\u00a0they run assumptions-free (hence their popular appeal).\u00a0The former lends itself to judgmental and statistical tests,\u00a0the latter escapes such scrutiny.<\/p>\n
In conclusion, if an educator needs to choose between\u00a0the “interpretability” and “estimability” paradigms, I would go\u00a0for the latter. If traditional econometrics education
\nis tailored to support the estimability track, I do not\u00a0believe a paradigm shift is warranted towards\u00a0an “interpretation seeking” paradigm as the one\u00a0proposed by Angrist and Pischke,<\/p>\n
I would gladly open this blog for additional discussion on\u00a0this topic.<\/p>\n
I tried to post a comment on NBER (National\u00a0Bureau of Economic Research), but was rejected\u00a0for not being an approved “NBER family member”.\u00a0If any of our readers is a “”NBER family member”\u00a0feel free to post the above. Note: “NBER working papers are circulated for discussion and\u00a0comment purposes.” (page 1).<\/p>\n","protected":false},"excerpt":{"rendered":"
Dear friends in causality research, In this brief greeting I would like to first\u00a0call attention to an approaching deadline and then\u00a0discuss a couple of recent articles. 1. Causality in Education Award – March 1, 2017 We are informed that the deadline for submitting a\u00a0nomination for the ASA Causality in Statistics\u00a0Education Award is March 1, 2017. […]<\/p>\n","protected":false},"author":6,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[2,5,13,22],"tags":[],"class_list":["post-1777","post","type-post","status-publish","format-standard","hentry","category-announcement","category-causal-effect","category-economics","category-linear-systems"],"_links":{"self":[{"href":"https:\/\/causality.cs.ucla.edu\/blog\/index.php\/wp-json\/wp\/v2\/posts\/1777","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/causality.cs.ucla.edu\/blog\/index.php\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/causality.cs.ucla.edu\/blog\/index.php\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/causality.cs.ucla.edu\/blog\/index.php\/wp-json\/wp\/v2\/users\/6"}],"replies":[{"embeddable":true,"href":"https:\/\/causality.cs.ucla.edu\/blog\/index.php\/wp-json\/wp\/v2\/comments?post=1777"}],"version-history":[{"count":5,"href":"https:\/\/causality.cs.ucla.edu\/blog\/index.php\/wp-json\/wp\/v2\/posts\/1777\/revisions"}],"predecessor-version":[{"id":1782,"href":"https:\/\/causality.cs.ucla.edu\/blog\/index.php\/wp-json\/wp\/v2\/posts\/1777\/revisions\/1782"}],"wp:attachment":[{"href":"https:\/\/causality.cs.ucla.edu\/blog\/index.php\/wp-json\/wp\/v2\/media?parent=1777"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/causality.cs.ucla.edu\/blog\/index.php\/wp-json\/wp\/v2\/categories?post=1777"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/causality.cs.ucla.edu\/blog\/index.php\/wp-json\/wp\/v2\/tags?post=1777"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}