But we must also bear in mind that some of the greatest scientific advances are the results of contestation of what was established science at that point. Science cannot assume fundamentalism - it becomes religion.

Indeed. If CIs are interpreted based on whether they cross the null or not, they are the same as p-values.

Given large sample sizes, p values and, to an extend, CIs become obsolete.

There is also the issue of misinterpretations of CIs

Confidence intervals are a bit better but I find that people tend to use them like p values and consider an effect as real if they include the null.

People in my field us confidence intervals or p-values more and more frequently, precisely for this reason (public health). Those of us in the field certainly know what it means, but it does confuse things.

Absolutely 💯

💙

Saw it now. Just blocked the account too. Terrible.

Thanks 🙏

But we must also bear in mind that some of the greatest scientific advances are the results of contestation of what was established science at that point. Science cannot assume fundamentalism - it becomes religion.

We have to start with the assumption that there is a group of people who are attracted to conspiracy theories because of their search for (true) knowledge. If we can explain and show the results of sciences clearly to them, we may move the needle a bit.

That’s a good question!

Statistical significance is an unfortunate term because it has nothing to do with actual significance. We should really be using a term more like null probability.

Can you share the handle please

Hi @ericmcinty.bsky.social - could you please add me as a contributor. Here is a link to my scholar profile

scholar.google.co.za/scholar?hl=e...

Thanks 🙏