A non-technical guide to performing power analysis in R

I walk you through how to perform power analysis using the "pwr" package in R and discuss ways to determine the effect size that you would expect to observe.
Here are some links to a few things I mentioned:
1. "pwr" package: cran.r-project.org/web/packag...
2. "ANOVApower" package: github.com/Lakens/ANOVApower
3. TOSTER package: cran.r-project.org/web/packag...
4. Why you shouldn't use pilot data for calculating power: psyarxiv.com/b7z4q
5. My Effect size distribution paper: www.ncbi.nlm.nih.gov/pubmed/2... and preprint osf.io/5y55v/
6. Registered Reports: cos.io/rr/
7. Equivalence testing primer: journals.sagepub.com/doi/pdf/...

[@stepht7805]

Great video thanks for sharing. It's amazing what you can learn with easy explanations!

[@HunterKayGames]

So nice video ! You saved my experiment design man (and my PhD) !

[@therealslinshadyaka.unicow2208]

Wow, I really appreciate your video! You have a very nice way of explaining this. For my master Thesis I will be doing linear mixed models though and I wanted to ask you, if you could maybe cover the "simr" package in another video? I really cannot find any simple tutorial/walkthrough for analyzing power in linear mixed models :(

[@purpledoo]

Great video! I have a question: since with ANOVA I have to do post-hoc corrections, do I have to lower the alpha value based on the correction that I want to make? Does R do it itself? Is actually not needed?

[@sushmitapoudel3752]

Hi daniel, awesome video. I have 5 groups and 3 treatments with unequal seedlings number, how do I do my power analysis?

[@nedabt1327]

Hi Daniel, thanks for the tutorials. what is the appropriate test for sample size calculation for multiple proportion comparison?

[@CanObeyComedy]

If possible, I would love an update with the Superpower package!

[@dsquintana]

Thanks for the suggestion! I've had a look at this package but need a bit more time to better understand its functions, so I hope to make a screencast with Superpower in the future

[@balasiddu]

Hi Daniel, Thanks for you video. I have a question. How to perform power analysis for logistic regression with an interaction between continuous and binary categorical predictor? In one of my studies, I need to assess the sample size. The study aims to predict the choice of participants with a continuous predictor and a categorical predictor (control vs. experimental). Here we hypothesize that the choice of the participants will be significantly predicted by the interaction between the predictors taken for the study. In this case, how to conduct a power analysis to find out the sample size required for the study.

[@treoencitrus765]

Hi did you got an answer? And if so, do you have an do-file?

[@balasiddu]

@@treoencitrus765 Yes, I got the answer. Please write to me at [e-mail]

[@treoencitrus765]

@@balasiddu I will (Y)

[@taraboyd1415]

Just discovered your videos! Can you conduct a power analysis for fMRI data that you've conducted a within-group repeated measures ANOVA for? Struggling to find any info

[@dsquintana]

Check out the "superpower" r package cran.r-project.org/web/packages/S… There's also a web app available shiny.ieis.tue.nl/anova_power/

[@adoi]

2-sample t-test doesn't differentiate between equal and unequal variances, right?

[@Hamedsaid_CGH]

unfortunately the pwr package doesn't have an option for hotelling t2 test