@JustinWolfers and @NateSilver538, do any of the pollsters pre-specify what weighting procedure they will use? if so, then it’s harder to accuse them of herding. if not, we just don’t know if they’re doing it in a principled, pre-planned way or a post hoc way. right?
This counter-response essentially says that any form of weighting in survey research is herding. If so, I love herding!
He's right about the motivation: All weighting is done to ensure that you don't get crazy results. But that's a feature of a good poll, not a bug!
@SLKoole@lakens the “decline effect” as described in thread above does sound bonkers. but should we withhold claims of “conclusively falsified” until the editors have completed this review of criticisms? (i haven’t read the paper let alone the pre-reg so can’t make any assessment myself)
@JPAM_DC published an RCT examining the effect of NY City's Summer Youth Employment Program (SYEP) on youth crime. Quick take: Large, high-quality RCT finds negligible impact on youth crime over a 5-year follow-up (authors' claims notwithstanding). 1/5
We partnered with the NMHC on a national survey to help develop a Mental Health Stigma Reduction Strategy. We estimate over 4 million Australians experienced mental health-related stigma and discrimination in the prior year. Read about our findings here: https://t.co/njB0qkt7DP
@JoshuaGrubbsPhD i’m missing the joke. do you mean that economists are belatedly studying what other disciplines have already studied? if so, do you think this paper fails to add to what’s already known? (just curious)
I'm hiring a Chief of Staff to work with me and the leadership team @B_I_Tweets. https://t.co/ALERkWZwci I'm obviously biased, but I think it will be a rewarding, stretching and really fun job. Quick thread on the day to day below 1/n
If you teach students to work with data, you're doing them a great disservice if you just teach them how to run models/analyses and not how to clean and manipulate data. If you haven't tested them directly on this, you'll be surprised how unintuitive this is to new users!
Here's a piece I've done for Inside Story about what Alex Jones did to the parents of the Sandy Hook shootings and how, after nearly a decade, they have finally held him to account. Bearing the unbearable, on Inside Story https://t.co/lCV4yyTiaU
Congratulations to @TBGreenwell & Chris Bonnor who are longlisted for the 2022 #auspolbookaward for 'Waiting for Gonski,' published by @UNSW & @newsouthpub!
We teamed up with @ato_gov_au to inform the design of the YourSuper Comparison Tool conducting a survey & two survey experiments with over 2000 respondents. Read our final report - https://t.co/SJARcCIOcy
#yoursuper#superannuation
@sharpmelk @Karminker as an addendum to this, Charles Weston led a team that planted the trees that now populate Canberra. he and his team would never have seen the city’s treescape like it is now. for that matter, nor would the city’s designers, Marion Mahoney Griffin and Walter Burley Griffin
@bijurao@DaveEvansPhD as a “researcher consumer” in govt, i agree. take time to understand how govt works. don’t make glib policy conclusions without at least trying to understand whether they are feasible to implement.
We are excited to announce the ten books that have made it to the #auspolbookaward longlist!
The longlist are those books our judges believe provide the most compelling contribution to understanding Australian political events and debates, congratulations to our nominees!
another powerful reminder that meta-analyses aren’t much good if they don’t account for publication bias. this eg from ecology & evolutionary biology
Did you hear about #publicationbias? Wondering how it affects eco & evo findings?
📰Here is everything you ever wanted to know about "Publication bias impacts on effect size, statistical power, & magnitude (Type M) & sign (Type S) errors in Eco & Evo Bio" https://t.co/UWDpa7yjGW
Announcement and invitation! A new project that aims to improve the quality of research in applied microeconomics by examining researcher choices. I am hoping to recruit up to *200 researchers* of all kinds (with pay) and hope you will join me! (Thread) https://t.co/XAOflRxoBf