# data science

## How to calculate contrasts from a fitted brms model

Models and contrasts Example data Model Interpreting the model’s parameters hypothesis() More contrasts Directional hypotheses and posterior probabilities Multiple hypotheses Hierarchical hypotheses Conclusion brms (Bayesian Regression Models using Stan) is an R package that allows fitting complex (multilevel, multivariate, mixture, …) statistical models with straightforward R modeling syntax, while using Stan for bayesian inference under the hood. You will find many uses of that package on this blog.

## rpihkal: Combine ggplots with patchwork

patchwork is an R package with a powerful syntax for combining different ggplots into a single figure.

## rpihkal: Stop pasting and start gluing

How to use the glue R package to join strings.

## Quantitative literature review with R: Exploring Psychonomic Society Journals, Part II

In this tutorial, I'll show how to use R to quantitatively explore, analyze, and visualize a research literature, using Psychonomic Society publications. This post directly continues from [part I of Quantitative literature review with R](https://mvuorre.github.io/post/2017/quantitative-literature-review-with-r-part-i/). Please read that first for context. Part I focused on data cleaning and simple figures, but here we will look at relational data by visualizing some network structures in the data.

## Quantitative literature review with R: Exploring Psychonomic Society Journals, Part I

In this tutorial, I'll show how to use [R](https://www.r-project.org/) to quantitatively explore, analyze, and visualize a research literature, using [Psychonomic Society's](http://www.psychonomic.org/) publications

## GitHub-style waffle plots in R

In this post, I’ll show how to create GitHub style “waffle” plot in R with the ggplot2 plotting package. Simulate activity data First, I’ll create a data frame for the simulated data, initializing the data types: library(dplyr) d <- data_frame( date = as.Date(1:813, origin = "2014-01-01"), year = format(date, "%Y"), week = as.integer(format(date, "%W")) + 1, # Week starts at 1 day = factor(weekdays(date, T), levels = rev(c("Mon", "Tue", "Wed", "Thu", "Fri", "Sat", "Sun"))), hours = 0) And then simulate hours worked for each date.