Paper link here! 13/13
papers.ssrn.com/sol3/papers....
#econsky #polisky #MetaScience #OpenScience #CausalInference #StatsTwitter #Econometrics #AcademicSky
2
0
0
0
#StatsTwitter
Latest posts tagged with #StatsTwitter on Bluesky
Trending
Posts tagged #StatsTwitter
yeah #StatsTwitter was a magical place. hasn’t quite all coalesced on bluesky, but lots of the greats are here anyway
2
0
0
0
Be careful. The RR vs OR wars were a hard time for #EpiTwitter and #StatsTwitter.
8
0
1
0
You are obviously too young to remember the #EpiTwitter vs #StatsTwitter wars.
5
1
1
0
One thing I like about #Bard is it shows different responses. This also shows how inconsistent answers can be (mixing affirmative and negative responses to y/n questions). #statstwitter
0
0
1
0
#StatsTwitter anyone noticed a huge double standard with respect to stats vs lab methods? Stats methods said to be "confusing" with request to "do something simpler" on papers where complex lab methods are inscrutable to anyone but a hard core expert in that narrow lab field?
0
0
0
0
On this calm Saturday afternoon cat decided to choose violence and remind #StatsTwitter about this:
I always thought 100 sounds pretty sensible, but prove me wrong #OverlySeriousEditor
0
0
0
0
#statstwitter any ideas on why I get such different results swapping the IV/DV here? I've used @rmkubinec ordered beta regression and have included measurement error on both variables. So I would have expected that order of them would have less impact.
0
0
0
0
Q for #statstwitter: what's a good read regarding analysis of a continuously collected outcome measure measured in a run-in before study inclusion and during an RCT?
0
0
0
0
#MedTwitter meet #StatsTwitter
0
0
0
0
#MedTwitter meet #StatsTwitter
0
0
0
0
#researchmethods #statstwitter #psychtwitter does anyone out there who teaches research methods and/or stats use item response theory-informed computerised adaptive testing for student summative assessment?
0
0
0
0
Question for #statstwitter about NHST... If I have a study powered for d=X but when I run it I find a significant effect d<X, should my inference about presence of an effect be limited to the presence of an effect of magnitude d=X? @lakens @statsepi @ADAlthousePhD @ExPhysStudent
0
0
0
0
Question for #StatsTwitter. I know that the normality assumption for most models seen in psych (e.g., linear models) is about residuals, not values, but are there exceptions where it's about values? I see some online (e.g., correlations, EFA) but unsure if this is misinformation
0
0
0
0
#statstwitter #rstats Whats your best resources for competing risk survival analyses?
0
0
0
1
#statstwitter I need some help! I'm supposed to deliver some content on a very broad PG Research Methods module for PhD students across a diverse range of areas (think from STEM topics to fashion/arts). I've been assigned a week to deliver 'Quantitative Methods' (yep, 1 week)...
0
0
0
0
I've seen a lot of people flaunt about how they don't use p-values and they avoid dichotomous thinking, but then their papers discuss how the 95% CI doesn't overlap with 0. #statstwitter
0
0
1
0
When your paired data fails Shapiro-Wilk #statstwitter #EpiTwitter
1
0
0
0
#epitwitter #statstwitter does anyone know of any good resources on comparative interrupted time series designs? In particular, when the 'interruption' is the introduction of an intervention to half the sample through randomisation?
0
0
0
0
If the average phone last 24 months, and yours has already lasted 22 months, how much longer does it have? On average, another 24 months. Welcome to the memorylessness property of exponential distributions. #statstwitter #math
0
0
0
0
Yeah - f***k you clinicians!! #statstwitter #MedTwitter #beef
0
0
0
0
Hey #statstwitter #epitwitter, can I get your input on this MMRM (mixed-effects model repeated measures) question?
For a clinical trial, an article reports MMRM as the primary approach for handling dropouts. (1/3)
0
0
2
0
Non-statistician academics of #medtwitter! I've been wondering, how much statstraining did you do during your PhD? #statstwitter #epitwitter
0
0
0
0
Trying to find a way to bootstrap bca confidence intervals for mixed models, but this doesnt seem to be implemented in e.g bootMer/boot? Am I missing something? #rstats #statstwitter
0
0
0
0
Need thoughts from #statstwitter #dataviz
For multiple response categorical variable (select all that apply) visualisation, do you think a balloonplot in essence showing each 2x2 contingency table is an intelligible way of presenting the data?
This is a MRCV taken pre/post
0
0
0
0
#StatsTwitter @gonen_mithat #UninformativeStatistics 3: Can anyone cite a paper where it was of value to show a graph of the ROC curve for a prediction model ? Remember that sensitivity and specific have little clinical meaning without incorporating prevalence.
0
0
0
0
#StatsTwitter #UninformativeStatistics 2: Can anyone cite a paper where showing the I-squared statistic in a metaanalysis told us more than the p-value for heterogeneity and the forest plot? Remember that I^2 is a hybrid of the degree of variation and the sample size
0
1
0
0
#StatsTwitter #UninformativeStatistics 1: Can anyone cite a paper where it was of value to show the Hosmer Lemeshow statistic for goodness of fit for a logistic regression? Remember the null hypothesis here is “good fit”.
0
0
0
0