Aaron Schwartz

@A_Schwa

MD-PhD tweeting on health, economics, and health economics. IM resident . Next, professing .

Boston, MA
Vrijeme pridruživanja: siječanj 2012.
78 fotografija ili videozapisa Fotografije i videozapisi

Tweetovi

Blokirali ste korisnika/cu @A_Schwa

Jeste li sigurni da želite vidjeti te tweetove? Time nećete deblokirati korisnika/cu @A_Schwa

  1. prije 33 minute

    Econs new to mendelian randomization IVs: this is a great paper to start learning from. Very good methods explanations. Unfortunately, the within-family analysis, which actually leverages the "randomization" part of "Mendelian randomization," is too imprecise for conclusions.

    In Volume 70 - Mendelian Randomization analysis of the causal effect of adiposity on hospital costs - Padraig Dixon, William Hollingworth, Sean Harrison, Neil M. Davies, George Davey Smith:
    1 reply 1 korisnik označava da mu se sviđa
    Poništi
  2. 4. velj

    ...it turns out that if the proportional hazard assumption holds in a model with covariate adjustment, it means the same assumption doesn't hold when covariates are not included in the model. That's all for now. I'll keep digging on this in the future.

    3 korisnika označavaju da im se sviđa
    Prikaži ovu nit
    Prikaži ovu nit
    Poništi
  3. 4. velj

    ...that power improvements in Cox do occur with covariate adjustment, but because Cox estimates are biased(!) toward null in the absence of including appropriate covariates. Also...

    1 reply
    Prikaži ovu nit
    Prikaži ovu nit
    Poništi
  4. 4. velj

    Novice here, but the more I'm reading, the more I'm concerned about Cox, which again is the current bedrock of clinical trial analysis. Readings like these are a bit sobering and seem to suggest...

    1 proslijeđeni tweet
    Prikaži ovu nit
    Prikaži ovu nit
    Poništi
  5. 3. velj

    Metrics/stats twitter: I'm seeking intuition for a puzzling aspect of Cox hazard models, nowadays the main method for assessing medical treatment effectiveness in trials. Adjusting for covariates doesn't improve power in balanced experiments. Why? (Formula from Stata manual)

    , , i još njih 3
    6 replies 5 proslijeđenih tweetova 21 korisnik označava da mu se sviđa
    Prikaži ovu nit
    Prikaži ovu nit
    Poništi
  6. proslijedio/la je Tweet
    24. sij

    Important work on overestimated surgical global period RVUs by Mulcahy Merrill Maybe spends too little on admin, leaving Medicare PFS susceptible to regulatory capture by interest groups (eg, RUC).

    5 replies 13 proslijeđenih tweetova 42 korisnika označavaju da im se sviđa
    Prikaži ovu nit
    Prikaži ovu nit
    Poništi
  7. 21. sij

    Behavioral economist on why you shouldn’t get AppleCare for your new iPhone.

    I bought a new phone this week. I thought I would tweet about how ridiculous it is to buy AppleCare. Price of 64g iPhone 11 Pro: $999 Price of full coverage (including theft/loss): $299 Yikes - the insurance coverage is nearly 1/3 the price of the phone!!
    Prikaži ovu nit
    1 reply 4 korisnika označavaju da im se sviđa
    Poništi
  8. 17. sij

    Nice example of RCTs yielding very different results. Two NEJM studies on smoking cessation interventions: Study #1: e-cigs -> 18% quit nicotine replacement -> 10% quit Study #2: e-cigs -> 1% quit nicotine replacement -> 0.5% quit

    1 reply 1 proslijeđeni tweet 2 korisnika označavaju da im se sviđa
    Poništi
  9. proslijedio/la je Tweet
    16. sij

    Harvard Alert: The individual has been apprehended and is in custody. The shelter in place is lifted.

    10 replies 168 proslijeđenih tweetova 599 korisnika označava da im se sviđa
    Prikaži ovu nit
    Prikaži ovu nit
    Poništi
  10. proslijedio/la je Tweet
    16. sij

    Harvard Alert HUPD and CPD officers responding to a report of a male with a gun in the area of Smith Campus Center. Shelter in place. If outside go inside a Harvard building. If in a building stay where you are.

    34 proslijeđena tweeta 14 korisnika označava da im se sviđa
    Poništi
  11. proslijedio/la je Tweet
    15. sij

    🚨Very happy to finally post a version of a WP with Maxim Pinkovskiy and , studying the impact of Medicare of consumer finances across the United States. There's a lot in this paper, and we'd love feedback. Especially on the methods! Thread👇

    6 replies 53 proslijeđena tweeta 179 korisnika označava da im se sviđa
    Prikaži ovu nit
    Prikaži ovu nit
    Poništi
  12. proslijedio/la je Tweet
    13. sij

    Our new paper (w/ + ): patterns of turnover in the physician workforce likely contribute to provider consolidation. (1/7)

    28 proslijeđenih tweetova 67 korisnika označava da im se sviđa
    Prikaži ovu nit
    Prikaži ovu nit
    Poništi
  13. proslijedio/la je Tweet
    6. sij

    Deaths of despair? 5 years after auto assembly plant closures, affected counties saw an 85% relative increase in overdose mortality rates. Disproportionate effect on young, non-Hispanic white men. Findings from in . More➡️

    1 reply 5 proslijeđenih tweetova 7 korisnika označava da im se sviđa
    Poništi
  14. proslijedio/la je Tweet
    11. sij

    Really nice write-up of our recent paper on low-value care in children - with lots of tips on how parents can minimize the chance their children receive this care.

    1 reply 6 proslijeđenih tweetova 16 korisnika označava da im se sviđa
    Prikaži ovu nit
    Prikaži ovu nit
    Poništi
  15. 9. sij

    PS- this is general speculation about interventions for complex patients. On the specific question of whether targeting the tail of the spending distribution is the best way to reduce wasteful spending, Michael and I wrote on this earlier.

    Important study by Amy Finkelstein et al on hot-spotting & readmissions: A myth that never had a sound conceptual basis (eg see w/ ) but rode mean reversion to the top. Nice take by :
    Prikaži ovu nit
    12 korisnika označava da im se sviđa
    Prikaži ovu nit
    Prikaži ovu nit
    Poništi
  16. 9. sij

    Who knows whether this phenomenon explains the null result for the Camden hot-spotting study, or explains the many high profile nulls in ICU medicine. But, I do think it's something we should keep in mind in designing and evaluating interventions for complex patients. (End)

    1 proslijeđeni tweet 26 korisnika označava da im se sviđa
    Prikaži ovu nit
    Prikaži ovu nit
    Poništi
  17. 9. sij

    Even interventions that help produce a "win" will fail to improve patient outcomes if the desired outcome depends on everything else going right. (6/7)

    19 korisnika označava da im se sviđa
    Prikaži ovu nit
    Prikaži ovu nit
    Poništi
  18. 9. sij

    When caring for very sick patients, or reading about randomized trials for very complex patients, I often think about this paper. For these patients to succeed, they need a series of "wins" without any "loss". (5/7)

    1 reply 2 proslijeđena tweeta 22 korisnika označavaju da im se sviđa
    Prikaži ovu nit
    Prikaži ovu nit
    Poništi
  19. 9. sij

    The paper was named for the faulty component causing the Challenger spaceship disaster. The model described economic output as depending on a series of complement tasks, any one of which could fail, rendering the others useless. (4/7)

    1 reply 10 korisnika označava da im se sviđa
    Prikaži ovu nit
    Prikaži ovu nit
    Poništi
  20. 9. sij

    These discussions remided me of the work of Michael Kremer, who won the econ Nobel this year. In 1993, just out of grad school, he published a paper on what he called "The O-Ring Theory of Economic Development". (3/7 )

    1 reply 9 korisnika označava da im se sviđa
    Prikaži ovu nit
    Prikaži ovu nit
    Poništi

@A_Schwa još nije objavio nijedan Tweet.

Čini se da učitavanje traje već neko vrijeme.

Twitter je možda preopterećen ili ima kratkotrajnih poteškoća u radu. Pokušajte ponovno ili potražite dodatne informacije u odjeljku Status Twittera.

    Možda bi vam se svidjelo i ovo:

    ·