Bjørn Sætrevik

I hadn't visited this area before, and was mostly alone in this tranquil and almost mysterious area. It was all very green mossy due to all the recent rain, but mostly good hiking conditions. #FootpathFriday #mosstodon #hiking

Followed a small, steep trail down towards Våkendalen, and found ruins of the farmsteds abandoned in the early 1900s. #FootpathFriday #mosstodon #hiking

I inquired about the status of a manuscript I submitted to a regional journal 170 days ago. Apparently they are still looking for a second reviewer! #AcademicChatter #AcademicPublishing

@miaholte@snabelen.no Jeg er ikke svaksynt (ennå), men måtte levere tilbake en ny komfyr fordi touch-knappene var designet med matt svarte symboler på blank svart bakgrunn. Det fungerer bare i flombelyste butikklokaler.

@tanketom@tutoteket.no Om ingen syklar står på sykkelparkeringa, er det då framleis ein sykkelparkering?

@MikeBolam #LichenSubscribe

@saarmuller@mastodon.social Our temporary offices will be in this building: https://en.wikipedia.org/wiki/Natural_Science_Building_(University_of_Bergen) I don't think it's typically referred to as being "nice".

@condalmo@mstdn.social I was skeptical coming in, but it was actually quite good! Mostly critical perspectives, and well presented (@jilltxt@aoir.social among them).

@Steve_Lindsay It sounds like a good idea, as long as it is applied cautiously (the editor / peer-reviewer will have considerable power to make the authors redo the study as they would have preferred it). Also note that early career researchers may not be able to collect more data (due to e.g. thesis deadline or lacking funds), and this may force them to redraw rather than revise.

@auzdavenice@mastodon.social Agree to report both (and to report absolute p-values). But I'm not sure if you could justify giving more weight to test B if there is nothing a priori to indicate that it is a "better" test... I'm curious to see how people would interpret such a situation in terms of reaching significance cut-off, and supporting hypothesis or not.

My own two cents (that may diverge from common practice): Option 1 is a valid and probably preferable approach. With a preregistered directed hypothesis, this is a more severe test of the hypothesis (but would have been better if the one-tailed testing was preregistered). Option 2 may be valid, if the preregistration doesn't make it sufficiently clear that the hypothesis was directional. Option 3 I would say is not a valid approach. Two-tailed testing should be used to test whether there is ANY association between variables (positive or negative). A significant effect in one of the tested direction should thus not be used to argue against a directional hypothesis (which you are not testing).

@olibrendel@scicomm.xyz Also relevant: https://sites.stat.columbia.edu/gelman/research/published/retropower_final.pdf #TypeSError #TypeMError

Across the valley I crossed the small Mikkelsbroen bridge and climbed a bit again to reach the goal for my hike, the small Bogstifossen waterfall. #FootpathFriday #mosstodon #hiking

@mdziemann@genomic.social This project supervised by @lakens@mastodon.social may be relevant: https://mastodon.social/@lakens/116596910605049412

@olibrendel@scicomm.xyz I would say it's fairly realistic for social sciences, at least. Here effects are often small and measurements noisy. With large survey samples a test may indicate a small effect to be significant at a 5% level, while there may actually be a such effect (a true positive), no real effect (a false positive), or a false positive where the true effect goes in the opposite direction of what's indicated. Related: https://en.wikipedia.org/wiki/Simpson%27s_paradox I was thinking of a situation where test A and test B both test the same hypothesis with e.g. different operationalizations of the outcome variable. In social science a given study often make several tests/measurements of a given phenomenon, and compare the results.