Skip to primary content

Statistical Modeling, Causal Inference, and Social Science

Main menu

  • Home
  • Authors
  • Blogs We Read
  • Books
  • Sponsors

Post navigation

Zipfian Academy, A School for Data Science Do you ever have that I-just-fit-a-model feeling?

Recently in the sister blog

Posted on September 12, 2013 9:40 AM by Andrew

Don’t be so quick to place politicians’ views of “national interests” above the mood of the public

More on those pollsters who apparently throw away completed survey responses

A theory of the importance of Very Serious People in the Democratic Party

Mother–child conversations about pictures and objects: Referring to categories and individuals

This entry was posted in Miscellaneous Statistics, Political Science by Andrew. Bookmark the permalink.
  • Art
  • Artificial Intelligence
  • Bayesian Statistics
  • Causal Inference
  • Decision Analysis
  • Economics
  • Jobs
  • Literature
  • Miscellaneous Science
  • Miscellaneous Statistics
  • Multilevel Modeling
  • Obituaries
  • Papers
  • Political Science
  • Public Health
  • Sociology
  • Sports
  • Stan
  • Statistical Computing
  • Statistical Graphics
  • Teaching
  • Zombies
  1. shira on Survey Statistics: toy example for energy balancing weightsJuly 14, 2026 2:40 PM

    Thanks again, Jared ! I agree with you, it helps to think about the implied outcome model. I think this…

  2. shira on Survey Statistics: toy example for energy balancing weightsJuly 14, 2026 2:38 PM

    Thanks, Jared and Raphael ! Jared, it makes sense that energy balancing weights become a lot more variable than raking…

  3. shira on Survey Statistics: Big Changes in the Times/Siena PollJuly 14, 2026 2:35 PM

    Thanks again, Jared ! Starting to take a look at Barnard et al. (2025). I feel silly but I can't…

  4. Carlos Ungil on “Making Statistics Work: Information Theory and Bayesian Inference”July 14, 2026 1:28 PM

    > right on the second page they start talking about “prior beliefs,” which isn’t how I think of things at…

  5. Daniel Lakeland on Supplement that alphabetized display with another graph showing the states in a more informative order.July 14, 2026 10:25 AM

    >What I don’t think follows from it is that the order specifically, as opposed to the order-plus-everything-else bundle, is what…

  6. Priya Banerjee on It’s Harvard time, baby: “Kerfuffle” is what you call it when you completely botched your data but you don’t want to change your conclusions.July 14, 2026 8:23 AM

    The phrase "Academic kerfuffle" caught my attention, as it reminds me of the delicate balance between data-driven conclusions and the…

  7. Andrew on It’s all about the nonlinearity: An interesting statistical example of flaws in a voter impact indexJuly 14, 2026 2:56 AM

    Kj: Fair enough regarding primary elections. Similarly, Republicans in very Republican states have impact in the primaries. But that's not…

  8. Joshua on Supplement that alphabetized display with another graph showing the states in a more informative order.July 13, 2026 8:33 PM

    Lol. I always think of how to say things more clearly immediately after I hit "post comment." I started thinking…

  9. Joshua on Supplement that alphabetized display with another graph showing the states in a more informative order.July 13, 2026 7:50 PM

    Daniel – Ok, I'm still thinking about this and I really do want to add another comment, even though I…

  10. Mark Phariss on It’s all about the nonlinearity: An interesting statistical example of flaws in a voter impact indexJuly 13, 2026 6:51 PM

    As it turned out once all the votes were counted, even WA voted less for Harris than for Biden.

  11. kj on It’s all about the nonlinearity: An interesting statistical example of flaws in a voter impact indexJuly 13, 2026 5:20 PM

    I'm not sure I'd say voters in non-swing states lack voter impact, Andrew. NYC is solidly democrat, but look at…

  12. Ioannis on “More bad science from JAMA”July 13, 2026 4:15 PM

    Dear Andrew, in a previous post (I think it was in March) you wrote that you may publish the more…

  13. Joshua on Supplement that alphabetized display with another graph showing the states in a more informative order.July 13, 2026 2:11 PM

    Daniel – I agree we should bring this to a close but before doing so I wanted to address one…

  14. AAAnonymous on “More bad science from JAMA”July 13, 2026 1:34 PM

    I have an interest in wordplay, not so much in reading papers! I am also a pretty simple man in…

  15. Andrew on It’s all about the nonlinearity: An interesting statistical example of flaws in a voter impact indexJuly 13, 2026 1:13 PM

    Sam: No, I'm not talking about momentum. I'm talking about the probability that your vote will be decisive. For more…

  16. Sam on It’s all about the nonlinearity: An interesting statistical example of flaws in a voter impact indexJuly 13, 2026 1:00 PM

    Andrew: Oh, I see. You're implicitly defining momentum. Because Election_Current - Election_N-Periods_Ago = 0. That is, the likelihood of NY…

  17. John Richters on “More bad science from JAMA”July 13, 2026 12:35 PM

    Thanks. Interesting take. Given your interest in word play, you might find my 2021 Incredible utility … article of interest…

  18. Andrew on “Archaeology can’t give social scientists population or GDP, but here are some things we can measure that might be useful for social science.”July 13, 2026 12:24 PM

    Sean: That's an interesting point and it motivated me to follow up with a post which should appear in late…

  19. paul alper on It’s all about the nonlinearity: An interesting statistical example of flaws in a voter impact indexJuly 13, 2026 12:18 PM

    In my impoverished youth, which encompassed WWII, the example of "decorative statistics" had something to do with an argument between…

  20. Andrew on It’s all about the nonlinearity: An interesting statistical example of flaws in a voter impact indexJuly 13, 2026 12:11 PM

    Sam: From my above post: "For example, in the 2024 presidential race, Kamala Harris won the two-party in New York…

  21. Sam on It’s all about the nonlinearity: An interesting statistical example of flaws in a voter impact indexJuly 13, 2026 12:07 PM

    You wrote: "So if the “presidential election” contribution to this index is 100 for Wisconsin, Michigan, and Pennsylvania, and something…

  22. paul alper on It’s all about the nonlinearity: An interesting statistical example of flaws in a voter impact indexJuly 13, 2026 11:52 AM

    typo: "that would still only you to 18."

  23. Andrew on It’s all about the nonlinearity: An interesting statistical example of flaws in a voter impact indexJuly 13, 2026 11:50 AM

    OK, I fixed the link; it's here.

  24. AAAnonymous on “More bad science from JAMA”July 13, 2026 11:43 AM

    Thanks for the reply! I like wordplay and my mind just got activitated seeing the words "dust" and "sweeping". I…

  25. Raghuveer Parthasarathy on It’s all about the nonlinearity: An interesting statistical example of flaws in a voter impact indexJuly 13, 2026 11:29 AM

    This reminds me of your (Andrew & colleagues') concept of "decorative statistics," which I think is excellent. The web archive…

  26. Andrew on It’s all about the nonlinearity: An interesting statistical example of flaws in a voter impact indexJuly 13, 2026 11:19 AM

    Anon: When it comes to voting statistics, zip codes aren't so bad. Counties are much more granular than zip codes,…

  27. anonymous e mouse on It’s all about the nonlinearity: An interesting statistical example of flaws in a voter impact indexJuly 13, 2026 10:57 AM

    Another note, from a geographer, is that ZIP codes are almost never an appropriate unit of aggregation unless you don’t…

  28. Matt Skaggs on It’s all about the nonlinearity: An interesting statistical example of flaws in a voter impact indexJuly 13, 2026 10:55 AM

    It seems that scientists rarely consider variance loss to be a phenomenon unto itself, and so they don't really think…

  29. Andrew on It’s all about the nonlinearity: An interesting statistical example of flaws in a voter impact indexJuly 13, 2026 10:37 AM

    Raphael: I can't be sure. My vague impression is that they are some sort of civic-minded group that wants to…

  30. John Richters on “More bad science from JAMA”July 13, 2026 10:21 AM

    “Cleaning up statistical dust and sweeping claims about maternal warmth” Thanks for the idea, but here’s why I don’t think…

  31. Raphael K on It’s all about the nonlinearity: An interesting statistical example of flaws in a voter impact indexJuly 13, 2026 10:20 AM

    Reading through your post, I am still left wondering what they are even trying to measure and/or accomplish. When I…

  32. anonymous e mouse on “Archaeology can’t give social scientists population or GDP, but here are some things we can measure that might be useful for social science.”July 13, 2026 9:25 AM

    What’s also interesting to me about that quote is that archaeologists are (often not always) considered a subdiscipline of anthropology,…

  33. Jason Bosch on 18 Associate Editors resign from Statistics and Computing editorial board: Problems with commercial scholarly publishing, and what does this all mean?July 13, 2026 3:48 AM

    I recently made a blog post asking where I should publish and I made a list of almost 100 fully…

  34. AAAnonymous on “More bad science from JAMA”July 13, 2026 3:07 AM

    Quote from the blog post: "In an abstract entitled, “Statistical dust and sweeping claims about maternal warmth,” John Richters and…

  35. Sean on “Archaeology can’t give social scientists population or GDP, but here are some things we can measure that might be useful for social science.”July 12, 2026 11:00 PM

    Anoneuoid, Nicholas Taleb has a colourful simile for why this won't work in Fooled by Randomness: investors (and historians) are…

  36. Robin Blythe on “More bad science from JAMA”July 12, 2026 9:38 PM

    This makes the second time in a week that I have read a more thoughtful, articulate and appropriate interpretation of…

  37. Sean on “Archaeology can’t give social scientists population or GDP, but here are some things we can measure that might be useful for social science.”July 12, 2026 8:06 PM

    A lot of us hoped that the Internet would lead to more extended back-and-forth exchanges between academics in different fields.…

  38. Jonathan (another one) on “Archaeology can’t give social scientists population or GDP, but here are some things we can measure that might be useful for social science.”July 12, 2026 4:14 PM

    Hypothesis: A = .73 Data: B=.73 Important Handwaving Paragraphs: We expect A to be like B, or related to B,…

  39. Chris on “Archaeology can’t give social scientists population or GDP, but here are some things we can measure that might be useful for social science.”July 12, 2026 3:42 PM

    Often in social science there is tension between what we can measure and what we would like to know. Well…

  40. Dale Lehman on “Archaeology can’t give social scientists population or GDP, but here are some things we can measure that might be useful for social science.”July 12, 2026 11:49 AM

    I'm not sure that a model of income inequality in the Aztec Empire would be predictive of income inequality in…

  41. Anoneuoid on “Archaeology can’t give social scientists population or GDP, but here are some things we can measure that might be useful for social science.”July 12, 2026 10:45 AM

    The model would need to predict the US, etc values to prove itself THEN you can plug in the guesstimated…

  42. Dale Lehman on “Archaeology can’t give social scientists population or GDP, but here are some things we can measure that might be useful for social science.”July 12, 2026 10:18 AM

    Wait - are you dismissing this work unless it can predict future income inequality in the Aztec Empire? If so,…

  43. Dale Lehman on “Archaeology can’t give social scientists population or GDP, but here are some things we can measure that might be useful for social science.”July 12, 2026 10:16 AM

    The exchange between Smith (critique) and the authors is quite thorough and a good example of the kind of exchange…

  44. Anoneuoid on “Archaeology can’t give social scientists population or GDP, but here are some things we can measure that might be useful for social science.”July 12, 2026 9:41 AM

    You can apply models to the past, but you have to show it can predict the future first. This is…

  45. Daniel Lakeland on Supplement that alphabetized display with another graph showing the states in a more informative order.July 12, 2026 9:03 AM

    Joshua, Previously you had mentioned causes like being at different initial stages of the pandemic, having different age distributions, having…

  46. Andrew on A new episode in the Francesca Gino caseJuly 12, 2026 8:43 AM

    Hannah: Thanks for explaining. That makes sense. Being deposed for a single day could be annoying but it's not too…

  47. Joshua on Supplement that alphabetized display with another graph showing the states in a more informative order.July 12, 2026 8:32 AM

    Daniel – I think this comment reveals a hidden assumption in your argument. You're treating the range of outcomes across…

  48. Erling on “More bad science from JAMA”July 12, 2026 2:43 AM

    Just incredible that such extravagant claims aren't stopped in peer review. The "finding" is of course one that many in…

  49. Daniel Lakeland on Supplement that alphabetized display with another graph showing the states in a more informative order.July 12, 2026 12:53 AM

    Joshua, the part you seem to continue to fail to acknowledge is that yes there are heterogeneities that I agree…

  50. Joshua on Supplement that alphabetized display with another graph showing the states in a more informative order.July 11, 2026 10:30 PM

    Daniel – Here’s an analogy for how your comment reads to me: Person A: “I agree aspirin is probably the…

Proudly powered by WordPress