Statisticians want to abandon science’s standard measure of ‘significance’
1–10 of 142 posts
Re: Statisticians want to abandon science’s standard measure of ‘significance’
#2At the very least, Romain Brette suggests to change the wording to "statistically detectable".
I 'm not sure if abandoning tests altogether is good though. What does it mean "it's detectable but not clear" for communication? How do you e.g. communicate global warming like that?
Re: Statisticians want to abandon science’s standard measure of ‘significance’
#3tl;dr:
> Is there a better way to judge if a study is solid?
> Unfortunately, there is no single alternative that everyone agrees would be better for all experiments.
Re: Statisticians want to abandon science’s standard measure of ‘significance’
#4tl;dr: > Is there a better way to judge if a study is solid? > Unfortunately, there is no single alternative that everyone agrees would be better for all experiments.
That may not be a bad thing. Having different solutions for different categories of experiments, or even just alternatives to select from could be useful.
Re: Statisticians want to abandon science’s standard measure of ‘significance’
#5At the very least, Romain Brette suggests to change the wording to "statistically detectable". I 'm not sure if abandoning tests altogether is good though. What does it mean "it's detectable but not clear" for communication? How do you e.g. communicate global warming like that?
I usually don't see climate science being communicated with p-values and poor significance cutoffs. The place where you usually see this used is for communicating single study results (which often enough are things that you probably shouldn't communicate at all).
To get an idea how climate science is trying to communicate look at the summary for policymakers of the SR15 report: https://report.ipcc.ch/sr15/pdf/sr15_spm_final.pdf
They have different confidence levels they indicate instead of a single cutoff.
Re: Statisticians want to abandon science’s standard measure of ‘significance’
#6tl;dr: > Is there a better way to judge if a study is solid? > Unfortunately, there is no single alternative that everyone agrees would be better for all experiments.
How about replication?
Re: Statisticians want to abandon science’s standard measure of ‘significance’
#7At the very least, Romain Brette suggests to change the wording to "statistically detectable". I 'm not sure if abandoning tests altogether is good though. What does it mean "it's detectable but not clear" for communication? How do you e.g. communicate global warming like that?
I usually don't see climate science being communicated with p-values and poor significance cutoffs. The place where you usually see this used is for communicating single study results (which often enough are things that you probably shouldn't communicate at all). To get an idea how climate science is trying to communicate look at the summary for policymakers of the SR15 report: https://report.ipcc.ch/sr15/pdf/sr15_sp…
That's not different than communicating significance with p < 0.05 , p < 0.01, p < 0.001 etc as is usually done in paper. There is again a cutoff.
Re: Statisticians want to abandon science’s standard measure of ‘significance’
#8Re: Statisticians want to abandon science’s standard measure of ‘significance’
#9Earlier quoted context omitted.
I usually don't see climate science being communicated with p-values and poor significance cutoffs. The place where you usually see this used is for communicating single study results (which often enough are things that you probably shouldn't communicate at all). To get an idea how climate science is trying to communicate look at the summary for policymakers of the SR15 report: https://report.ipcc.ch/sr15/pdf/sr15_sp…
That's not different than communicating significance with p < 0.05 , p < 0.01, p < 0.001 etc as is usually done in paper. There is again a cutoff.
It's different in that the cut-offs are communicated with careful wording, rather than a figure.
Re: Statisticians want to abandon science’s standard measure of ‘significance’
#10Earlier quoted context omitted.
How about replication?
Replication until statistically significance is found?
In a way yes, because replication lowers the risk that the findings in a single experiment are due to random luck. Anyway there's no way around avoiding replication when you want to prove something.