I have my own list of phrases that I think have reached the end of their useful life and should be retired. Personally, I’m finding that I use the term granular too much.
My top seven phrases to retire in 2024
Posted on
Author: Darren
Writing to clear your mind
Posted on
I’m kind of a sucker for self-help life-hacks. Many are worthless, but one that I find helpful is “journaling”. Of course keeping a journal is not novel, but I starting taking it more seriously after learning about Meditations by the Roman emperor Marcus Aurelius. I recommend the blog and podcast by Ryan Holiday called the…
Interaction effects require massive increase in sample size
Posted on
I gave a quick internet-read to this blogpost by Andrew Gelman. The core of the idea is that to estimate an interaction effect a huge increase in sample size is needed compared to estimating a main effect. That is, if you power a study on main effects you could be very underpowered if you want…
Podcast recommendation: 13 Days of Halloween
Posted on
With Halloween approaching, here is a fantastic Halloween podcast: 13 Days of Halloween All four seasons are good.
National Review Podcast
Posted on
I’ve been listening to the Editors podcast from the National Review (link here). I wanted to bring conservative podcasts into my feed, and this one seemed the most mainstream. It has been interesting to listen to more traditionally conservative (i.e., not Trump republican) view on current events. I recommend it. Episode 457 covered the Kansas…
P values are not transferable
Posted on
Of the many challenges I encounter in communicating statistical concepts to collaborators, a common one is that p-values are seen as “transferable.” Here is a simple example to illustrate what I mean. Consider the following table, where the rows are sex (Male and Female) and the columns are smoking status (Current, Former, Never). We are…
Another improvement in reporting statistics in science
Posted on
To add a little more to this post, I’ve read several papers where the authors add some details regarding the statistical methods/tests used with the results rather than just reporting a p-value. I think this approach really adds clarity. Here is an example. First, what I see as a typical approach: We found that the…
Brief example of interaction effects in regression
Posted on
Statistical interactions can be challenging to understand and interpret. This simple example illustrates a regression model with an interaction effect. First I generate some fake data, which allows us to know the underlying structure of the data. Let y be some generic response variable (e.g., weight). Corresponding to each y is a sex variable (M/F)…
When are colloquial uses of technical statistical terms OK?
Posted on
As someone trained in mathematics I tend to use words precisely, as I would in a mathematical proof. For example, the word “function” has a particular definition in mathematics that is related to but different from the common definition. Statistics has the same issue, where words that have careful mathematical definitions also have colloquial definitions….
Report more than just the p-value
Posted on
It is common in some academic fields to only report the p-value from a hypothesis test. For example, “We found a significant difference between the treatment group and control group (p=0.002)”. Some academic fields require including the test statistic value and other information, e.g., https://my.ilstu.edu/~jhkahn/apastats.html. As long as the hypothesis test was performed correctly reporting…