BLUE
Login
Profile banner
AH
Andrew Heiss 🍂🎃
@andrew.heiss.phd
Assistant professor at Georgia State University, formerly at BYU. 6 kids. Study NGOs, human rights, #PublicPolicy, #Nonprofits, #Dataviz, #CausalInference. #rstats forever. #LDSforHarris andrewheiss.com
3.3k followers2k following1.9k posts
AHandrew.heiss.phd

Oh man, this new JOP paper by Arthur Spirling and @bstewart.bsky.socialgithub.com/ArthurSpirli...

What Good is a Regression? Inference to the Best Explanation and the Practice of Political Science Research* Arthur Spirling„ Brandon M. Stewart… Abstract We argue that almost all empirical social science research should employ a mode of argumentation called “Inference to the Best Explanation” (IBE). While elements of IBE appear widely, it is seldom consciously described, leading to confusion about the role that evidence plays in social science claims. We describe what IBE is and its implications for the evaluation of studies of various types—from quantitative description, to traditional regression studies, to work with modern causal identification. We contend that debates over the merits of these approaches should be understood as debates over the relative weight scholars place on quality of explanations, the quality of evidence and the bridge between the two. Seeing the process this way helps highlight the merits of different research traditions and explains common pathologies of the
All told, the answer to “what good is a regression?” depends on what you want from it. There are reasonable answers that arise from the same philosophical framework being used (implicitly) by those that particularly promote causal inferences. But to reiterate: a regression can still be useful for evaluating an explanation whether the relevant coefficient is tightly causally identified or not. This does not mean anything goes. Authors should be clear about their explanations, what those explanations imply about the world and what their evidence actually tells us about those implications. The pitfall to avoid is the misrepresentation of explanation or evidence. Our view is that the standard for an empirical paper should be whether an interesting argument is well-advanced. We should evaluate arguments in the light of IBE. This still leaves open important questions such as the difficulty of making arguments with only descriptive evidence or the optimal aggregate balance of explanation and
4
DCdevincaughey.bsky.social

Looks great! And just in time to make my syllabus for the fall.

0
MFmatzefrey.bsky.social

📌

0
JMdingdingpeng.the100.ci

Ooooh now you got me excited!

1
KPklauspforr.bsky.social

📌

0
Profile banner
AH
Andrew Heiss 🍂🎃
@andrew.heiss.phd
Assistant professor at Georgia State University, formerly at BYU. 6 kids. Study NGOs, human rights, #PublicPolicy, #Nonprofits, #Dataviz, #CausalInference. #rstats forever. #LDSforHarris andrewheiss.com
3.3k followers2k following1.9k posts
HomePopularExplore