BLUE
Profile banner
JH
Jouni Helske
@jounihelske.bsky.social
Academy Research Fellow at INVEST (University of Turku), PI of CAUSALTIME project and partner in PREDLIFE consortium. Bayesian statistics, causal inference, state space and hidden Markov models, and computational statistics in general.
157 followers185 following28 posts
Reposted by Jouni Helske
FBkenwhite.bsky.social

The winter is dark Until I remember the Leftover pizza

10
JHjounihelske.bsky.social

Had to create some additional variables in #rstats with data.table, which involved multiple equality comparisons of a factor variable x within each group (e.g., x[1:n] == x[n]). Took 5 hours for about 200,000 rows. Same thing after first converting x to integer: 5 minutes.

0
JHjounihelske.bsky.social

Yeah, no fixing to zero, just show the point estimates with some kind of measure of uncertainty such as confidence/prediction/posterior intervals depending on what the point estimates are and how they were estimated.

0
JHjounihelske.bsky.social

Oh my. Rounding by statistical significance: Significant estimates are exactly correct, but those with large p-values are just random noise and are actually zero... #metasci#stats 📉📈

A line graph starting below zero, with some points exactly zero and ending above zero. Below figure there is a text "Note: Statistically insignificant effects are set to zero."
1
Reposted by Jouni Helske
JMdingdingpeng.the100.ci
JHjounihelske.bsky.social

Also, maybe some reviewers are less prone to openly endorse acceptance of more controversial papers (and these might also have more reviewers -> less likely to get consent for everyone). On the other hand, these papers might be get more citations than "basic papers"?

0
JHjounihelske.bsky.social

Maybe bigger names only want their names associated with papers which they find very significant, so giving consent for open review depends on the quality of the paper, and quality also affects the future citations.

1
JHjounihelske.bsky.social

Looks interesting, but I wouldn't put too much weight on this paper. 1) this is only about naming reviewers after reviews, not actually open comments. 2) There is likely still selection bias and confounding present, for example, authors might be more interested in naming bigger names as reviewers.

Screenshot of Nature's policy on open review: After acceptance, authors can opt to include the names of the reviewers with their consent.
2
Profile banner
JH
Jouni Helske
@jounihelske.bsky.social
Academy Research Fellow at INVEST (University of Turku), PI of CAUSALTIME project and partner in PREDLIFE consortium. Bayesian statistics, causal inference, state space and hidden Markov models, and computational statistics in general.
157 followers185 following28 posts