diff --git a/docs/guide.Rmd b/docs/guide.Rmd index 8fd16534410bd17d1914b615bd67f0556e2d5ef4..43ac0de77deb5113d2e04a0217db7e275922fa71 100644 --- a/docs/guide.Rmd +++ b/docs/guide.Rmd @@ -372,6 +372,7 @@ We have very strong evidence for the model with no interaction. * *Psychonomic Bulletin & Review* special issue on [Bayesian methods for advancing psychological science](https://link.springer.com/journal/13423/25/1/page/1) * [`BayesFactor`](https://richarddmorey.github.io/BayesFactor/) package * [JASP](https://jasp-stats.org/) statistical software +* [Bayesian Spectacles](https://www.bayesianspectacles.org/) blog * [Understanding Bayes](https://alexanderetz.com/understanding-bayes/) blog *** diff --git a/docs/guide.pdf b/docs/guide.pdf index 857925d4124d02a785fabdaae603fbdc011e7a38..8335cd04c74a5db1eba6ce213c554550d9ddafc4 100644 Binary files a/docs/guide.pdf and b/docs/guide.pdf differ diff --git a/docs/presentation.Rmd b/docs/presentation.Rmd index 2f4429bbfb5caf4a58b8396442b212fa98331a52..a7d52b2d33289314d075701c27c318007c10aacc 100644 --- a/docs/presentation.Rmd +++ b/docs/presentation.Rmd @@ -255,8 +255,17 @@ $\frac{P(D|H_0)}{P(D|H_1)}$ ## Potential issues \pause -* Results can be sensitive to priors +* Rely on same assumptions as frequentist statistics \pause +* Results can be sensitive to priors + +\centering \includegraphics[height=1.5in]{../figures/jasp_priors_plot.png} + + +## Potential issues + +* Rely on same assumptions as frequentist statistics +* Results can be sensitive to priors * Still use cutoffs \pause * Not accepted in the field @@ -387,6 +396,7 @@ $BF_{interaction} = \frac{16}{14} = 1.14$ * *Psychonomic Bulletin & Review* special issue on [Bayesian methods for advancing psychological science](https://link.springer.com/journal/13423/25/1/page/1) * [`BayesFactor`](https://richarddmorey.github.io/BayesFactor/) package * [JASP](https://jasp-stats.org/) statistical software +* [Bayesian Spectacles](https://www.bayesianspectacles.org/) blog * [Understanding Bayes](https://alexanderetz.com/understanding-bayes/) blog * Anderson, D. R. (2008). [Model Based Inference in the Life Sciences]( http://www.springer.com/life+sci/ecology/book/978-0-387-74073-7). New York: Springer. * Gelman, A., Carlin, J. B., Stern, H. S., Dunson, D. B., Vehtari, A., & Rubin, D. B. (2013). [Bayesian Data Analysis](http://www.stat.columbia.edu/~gelman/book/) (Third Edition). Boca Raton, FL: CRC Press. diff --git a/docs/presentation.pdf b/docs/presentation.pdf index 9a60757e39528b11780205c9bdc4dbe9d635f4c2..df06762bec81366923afa984604a7d738115ecb9 100644 Binary files a/docs/presentation.pdf and b/docs/presentation.pdf differ diff --git a/figures/jasp_priors_plot.png b/figures/jasp_priors_plot.png new file mode 100644 index 0000000000000000000000000000000000000000..b5e2e2b10eb222557e15de58c789a5623ff797dc Binary files /dev/null and b/figures/jasp_priors_plot.png differ diff --git a/src/bf_analysis.R b/src/bf_analysis.R index 1b5af9726760d17c58929bb5f10281fab532d370..8fb653774a391d5d2aaf3d72f17fe4f890fdef25 100644 --- a/src/bf_analysis.R +++ b/src/bf_analysis.R @@ -151,21 +151,17 @@ ggplot(datafile, aes(x = rt, y = choice)) + geom_point() + # plot individual points in grey geom_smooth(method = "lm") + # plot regression line and CI labs(x = "Reaction time", y = "Choice proportion") -ggplot(datafile, aes(x = pre, y = choice)) + +ggplot(datafile, aes(x = age, y = choice)) + geom_point() + # plot individual points in grey geom_smooth(method = "lm") + # plot regression line and CI - labs(x = "Pre ratings", y = "Choice proportion") -ggplot(datafile, aes(x = post, y = choice)) + - geom_point() + # plot individual points in grey - geom_smooth(method = "lm") + # plot regression line and CI - labs(x = "Post ratings", y = "Choice proportion") + labs(x = "Age", y = "Choice proportion") ## Frequentist -summary(lm(choice ~ rt + pre + post, data = datafile)) # conduct frequentist linear regression +summary(lm(choice ~ rt + age, data = datafile)) # conduct frequentist linear regression ## Bayesian -regressionBF(choice ~ rt + pre + post, data = datafile) # conduct Bayesian linear regression -head(regressionBF(choice ~ rt + pre + post, data = datafile)) # order results by BF +regressionBF(choice ~ rt + age, data = datafile) # conduct Bayesian linear regression +head(regressionBF(choice ~ rt + age, data = datafile)) # order results by BF