• Sorting out your RStudio working environment.
• Getting you ready to produce reproducible reports in RMarkdown.

• Results are communicated through reports such as peer reviewed scientific articles.
• Reported results should be reproducible!
• Data and code should be made available to others!
• It is difficult to relate code to figures, tables, numbers etc. especially where numbers were copy-pasted from software.

• What it is: A special folder for your work in R.
• What it does: Keeps your scripts, data, and results together.
• Why it helps:
  • Sets the folder as your working directory automatically.
  • No setwd() headaches.
  • Easy to share or move your whole project.
• Works well with Git/GitHub for teamwork and version control.
• Everything for one analysis stays neatly in one place.
• Create R Project for psyc40940 with sub-directories: “data”, “exercises”, “plots”
• Download blomkvist.csv from NOW and move it into the “data” folder.

From the RStudio menu …

• Click on File > New File > R Markdown
• Document (PDF, WORD, HTML)
• output: html_document: we will use html for simplicity
  
• Name your RMarkdown: basics.Rmd
• Save in same directory as .Rproj file.
• Compile (Knit) document
• Inspect features of RMarkdown document: YAML preamble, text, markdown code (section headers, italics, bold font), chunks with R code, inline code.

• Create a new R chunk: CTRL+ALT+I or OPTION+ALT+I (i.e. the letter “i”) called packages and load libraries needed:

library(tidyverse)
library(psyntur)

• Create a new chunk called loaddata and load the blomkvist.csv data published in Blomkvist et al. (2017)

# Load data
bk_alldata <- read_csv("data/blomkvist.csv") 

# Select a few variables
bk_selected <- select(blomkvist_alldata, id, smoker, age, rt = rt_hand_d)

# Remove missing data
blomkvist <- drop_na(bk_selected)

• Note ```{r setup, echo=FALSE}
• setup is a label of this chunk (optional; useful for cross-referencing of figures and tables).
• Chunk configuration option echo = FALSE: don’t display chunk in output; echo = TRUE: display chunk.

knitr::opts_chunk$set(message = FALSE, # don't return messages
                      warning = FALSE, # don't return warnings
                      comment = NA, # don't comment output
                      echo = TRUE, # display chunk (is default)
                      eval = TRUE, # evaluate chunk (is default)
                      out.width = '45%',  # figure width
                      fig.align='center') # figure alignment

• Create a new R chunk with label myscatterplot
• Set echo = F cause we only need the figure.
• Add a figure caption fig.cap = "A scatterplot." in the chunk configurations.

library(psyntur)
scatterplot(x = age, y = rt, data = blomkvist)

• Change the default size to out.width = 75%.
• Cross-reference figure using \@ref(fig:myscatterplot) in the text.

"A scatterplot of age and reaction time can be found in Figure \@ref(fig:myscatterplot)."

In the YAML preamble change

output: html_document

to

output: bookdown::html_document2

• Reporting results in tables formatted to a high standard.
• Calculate descriptive statistics:

(smoker_rt <- summarise(blomkvist, mean = mean(rt), sd = sd(rt), .by = smoker))

# A tibble: 3 × 3
  smoker  mean    sd
  <chr>  <dbl> <dbl>
1 former  653.  152.
2 no      635.  203.
3 yes     633.  217.

library(knitr)
kable(smoker_age,
      booktabs = TRUE,
      digits = 2,
      align = 'c', # centre value in each column
      caption = 'Descriptives of age by smoker.') 

• Label the chunk “smoker” and cross-reference the table in the text using Table \@ref(tab:smoker).

# Fit the model and get the summary
model <- lm(rt ~ sex, data = blomkvist)
model_summary <- summary(model)

# Extract R^2
r2 <- model_summary$r.sq

The $R^2$ for this model is `r round(r2, 2)`.

Renders “The \(R^2\) for this model is 0.03.”

# Extract F statistic
f_stat <- model_summary$fstatistic
p_value <- pf(f_stat[1], f_stat[2], f_stat[3], lower.tail = FALSE)

The model summary can be summarised like so: $F(`r round(f_stat[2])`, `r round(f_stat[3])`) =
`r round(f_stat[1],2)`$, $p `r format.pval(p_value, eps = 0.01)`$.

Renders “The model summary can be summarised like so: \(F(1, 263) = 7.48\), \(p <0.01\).”

p <- c(0.05, 0.02, 0.011, 0.005, 0.001)
format.pval(p, eps = 0.01)

[1] "0.05"  "0.02"  "0.01"  "<0.01" "<0.01"

• Strings are parsed using \(\LaTeX\) and typeset accordingly when used between '$' symbols for inline mode.
• For example $\beta$ renders \(\beta\).
• Subscripts: $\beta_0$ is \(\beta_0\) and using '{}' for more than one symbol as in $\beta_{01}$ which is \(\beta_{01}\)
• How would you write \(\beta_{0_1}\)?
• Superscripts: '^' as in $\sigma^2$ which is \(\sigma^2\).
• How would you write \(\sigma^{2^2}\)?
• How about \(\sigma_e^2\)?

install.packages("rmdformats")

• Create from template:
  • File > New File > R Markdown (e.g. readthedown or robobook for documents)
  • rmdshower::shower_presentations and ioslides_presentation for slides
• RMarkdown example
• Online sharing on RPubs (“Publish”)

• Example: https://osf.io/vayhq/ published in Roeser et al. (2024)
• Installation: https://github.com/crsh/papaja

Next week we will start with data visualisation, so make sure you understand RMarkdown and R code.

• See materials on R programming and RMarkdown in Week 1 NOW folder.
• For an introduction to R programming read Chapter 2 of Andrews (2021).
• For a more information about RMarkdown (also how to create APA7 style documents) read Chapter 7 of Andrews (2021)
• And chapter 27 of Wickham & Grolemund (2016).
• Check the rmarkdown website.