ERIM2020_intro_tidyverse_exercises_solutions.Rmd

---
title: '<center> <h1> Reproducible data analysis using R and the ```tidyverse``` -- Solutions </h1> </center>'
author: '[Antonio Schettino](https://asch3tti.netlify.com/ "Antonio Schettino")'
date: 'March 4th, 2020'
output:
  html_document:
    df_print: paged
    theme: spacelab
    highlight: tango
    code_folding: show
    toc: true
    toc_float: true
    toc_depth: 4
    includes:
      after_body: footer.html
editor_options: 
  chunk_output_type: console
---

```{r setup, include = FALSE}

### to reproduce the .html
# # install packages
# install.packages("knitr")
# install.packages("devtools")
# install.packages("here")
# install.packages("tidyverse")
# install.packages("viridis")
# devtools::install_github("mikabr/ggpirate")
# install.packages("yarrr")
# install.packages("afex")
# install.packages("bootES")

# load packages
library(knitr)
library(devtools)
library(here)
library(tidyverse)
library(viridis)
library(ggpirate)
library(yarrr)
library(afex)
library(emmeans)
library(bootES)
library(broom)

```

# Exercise 1

Install and load the ```tidyverse```.

```{r install_load_tidyverse, eval = FALSE}

install.packages("tidyverse")
library(tidyverse)

```

# Exercise 2

## Exercise 2.1

Do the following operations _**in one go**_:

* load the original data (```MixedAttitude.dat```)
* convert ```sex``` to a **categorical** variable (named ```gender```) with 2 levels:
    - 1 --> female
    - 2 --> male
* eliminate from the data set the following variables: ```sex```, ```beerpos```, ```beerneg```, ```beerneut```, ```winepos```, and ```waterpos```
* using the function ```rename```, rename the variables you kept:
    - ssj --> participant
    - wineneg --> wine_negative
    - wineneut --> wine_neutral
    - waterneg --> water_negative
    - waterneu --> water_neutral
* filter out outlier participants as well as all participants who rated *water* after *neutral* imagery as _**lower than -10**_
* convert the data set to **long** format
* separate conditions into 2 variables (```drink``` and ```imagery```)
* convert ```participant```, ```gender```, ```drink```, and ```imagery``` to factors

When you have completed these operations, save the data set as ```data_attitude_wine.csv``` in the subfolder ```tidy-data```.

```{r exercise_2_1, message = FALSE}

library(here)
library(tidyverse)

data_attitude_wine <-
  read_csv(
    here(
      "raw-data",
      "MixedAttitude.dat"
    )
  ) %>%
  mutate(
    gender = recode(
      factor(sex),
      "1" = "female", "2" = "male"
    )
  ) %>%
  select(-c(
    sex,
    beerpos,
    beerneg,
    beerneut,
    winepos,
    waterpos
  )) %>%
  rename(
    participant = ssj,
    wine_negative = wineneg,
    wine_neutral = wineneut,
    water_negative = waterneg,
    water_neutral = waterneu
  ) %>%
  filter(
    water_neutral >= -100 & water_neutral <= +100 &
      water_neutral >= -10
  ) %>%
  pivot_longer(
    cols = c(wine_negative, wine_neutral, water_negative, water_neutral),
    names_to = "condition",
    values_to = "ratings",
  ) %>%
  separate(
    condition, c("drink", "imagery"),
    remove = TRUE
  ) %>%
  mutate(
    participant = as_factor(participant),
    gender = as_factor(gender),
    drink = as_factor(drink),
    imagery = as_factor(imagery)
  )

write_csv(
  data_attitude_wine,
  here("tidy-data", "data_attitude_wine.csv")
)

```

## Exercise 2.2

Using the output of **Exercise 2.1**:

* separately for ```gender```, ```drink```, and ```imagery```, calculate the following summary statistics:
    - number of observations
    - median
    - median absolute deviation
    - minimum value
    - maximum value
* display the results in console

```{r exercise_2_2, message = FALSE}

summary_data_attitude_wine <-
  data_attitude_wine %>%
  group_by(gender, drink, imagery) %>%
  summarize(
    n = n(),
    median = median(ratings),
    mad = mad(ratings),
    min = min(ratings),
    max = max(ratings)
  ) %>%
  ungroup() %>%
  print()

```

# Exercise 3

## Exercise 3.0

Load ```data_attitude_wine.csv```.

```{r exercise_3_0, message = FALSE}

data_attitude_wine <-
  read_csv(
    here(
      "tidy-data",
      "data_attitude_wine.csv"
    )
  )

```

## Exercise 3.1

```{r plot, echo = FALSE, out.width = "80%", fig.cap = "*RDI plot generated during the workshop.*"}

include_graphics("images/RDIplot.png")

```

Create a plot similar to what is shown above (with ```wine``` instead of ```beer```) and save it in the subfolder ```doc/images```.

```{r exercise_3_1}

library(viridis)
library(ggpirate)

RDIplot_ex_3_1 <-
  data_attitude_wine %>%
  ggplot(aes(
    x = imagery,
    y = ratings,
    color = drink,
    fill = drink
  )) +
  geom_pirate(
    bars = FALSE,
    cis = TRUE,
    lines = TRUE, lines_params = list(color = "black"),
    points = TRUE, points_params = list(shape = 21, color = "black", size = 5, alpha = .4),
    violins = TRUE, violins_params = list(size = 1),
    show.legend = TRUE
  ) +
  scale_y_continuous(
    limits = c(-100, 100),
    breaks = seq(-100, 100, 10)
  ) +
  coord_cartesian(ylim = c(-40, 40)) +
  geom_hline(
    yintercept = seq(-100, 100, 10),
    linetype = "dotted",
    colour = "#999999",
    size = .8,
    alpha = .5
  ) +
  scale_fill_viridis(
    option = "viridis",
    discrete = TRUE
  ) +
  ggtitle("Plot Exercise 3.1") +
  theme_minimal(base_size = 18) +
  theme(
    panel.grid = element_blank(),
    legend.box.background = element_rect(color = "transparent"),
    legend.position = c(.9, .2),
    plot.title = element_text(size = 26, hjust = .5)
  )

ggsave(
  filename = "plot_ex_3_1.png",
  plot = RDIplot_ex_3_1,
  path = here("doc/images"),
  width = 7, height = 7, units = "in",
  dpi = 600
)

RDIplot_ex_3_1

```

## Exercise 3.2

The same as above, separately for female and male participants.

```{r exercise_3_2}

RDIplot_ex_3_2 <-
  RDIplot_ex_3_1 +
  ggtitle("Plot Exercise 3.2") +
  facet_wrap(. ~ gender)

ggsave(
  filename = "plot_ex_3_2.png",
  plot = RDIplot_ex_3_2,
  path = here("doc/images"),
  width = 9, height = 7, units = "in",
  dpi = 600
)

RDIplot_ex_3_2

```

## Exercise 3 BONUS

Recreate a plot similar to #2 using the [```yarrr```](https://cran.r-project.org/web/packages/yarrr/vignettes/pirateplot.html) package.

```{r exercise_3_bonus}

library(yarrr)

# following https://bookdown.org/ndphillips/YaRrr/saving-plots-to-a-file-with-pdf-jpeg-and-png.html
# this plot is saved as pdf to avoid 'Error in plot.new() : figure margins too large'
# displayed when using the functions 'png' or 'jpeg'
pdf(
  file = here("doc/images/plot_ex_3_bonus.pdf"), # directory + file name
  width = 9, # width (in inches)
  height = 7 # height (in inches)
)

pirateplot(
  formula = ratings ~ imagery + drink + gender, # dependent ~ independent variables
  data = data_attitude_wine, # data frame
  main = "Bonus Plot Exercise 3", # plot title
  ylim = c(-25, 25), # y-axis: axis limits
  ylab = "", # y-axis: no label
  inf.method = "ci", # type of inference: 95% confidence interval
  inf.within = participant, # ID variable
  # theme settings
  pal = "espresso", # color palette: see piratepal("all")
  point.o = .5, # data points: opacity (0-1)
  point.cex = 1.3, # data points: size
  inf.f.o = .3, # 95% CI box filling: opacity (0-1)
  bean.b.o = .6, # bean border: opacity (0-1)
  bean.f.o = .6, # bean filling: opacity (0-1)
  cap.beans = TRUE, # bean densities are capped at the data limits
  bty = "n", # no box around the plot
  gl.col = "gray", # background line color (major and minor lines)
  gl.lwd = 1, # background line width
  gl.lty = 2 # background line type (dashed)
)

dev.off()

```

![](images/plot_ex_3_bonus.pdf){width=100% height=700}

## Exercise 4

### Exercise 4.1

Load ```data_attitude_wine.csv```.

```{r exercise_4_1, message = FALSE}

data_attitude_wine <-
  read_csv(
    here(
      "tidy-data",
      "data_attitude_wine.csv"
    )
  )

```

#### Exercise 4.1.1

Run a 2 (**drink**) x 2 (**imagery**) repeated measures ANOVA on likeness ratings and display the results in console.

```{r exercise_4_1_1}

library(afex)

rmANOVA_att_wine <- aov_ez(
  "participant",
  "ratings",
  data_attitude_wine,
  within = c("drink", "imagery"),
  type = 3
)

rmANOVA_att_wine

```

#### Exercise 4.1.2

Run paired contrasts and display the results in console.

```{r exercise_4_1_2}

library(emmeans)

afex_options(emmeans_model = "multivariate")

posthoc_att_wine <-
  emmeans(rmANOVA_att_wine, ~ imagery * drink) %>%
  pairs(.,
    test = adjusted("free")
  ) %>%
  as.glht() %>%
  summary() %>%
  print()

```

#### Exercise 4.1.3

Run bootstrapped effect sizes (calculate **Pearson's _r_** instead of Hegdes' *g*) and display the results in console.

```{r exercise_4_1_3}

att_wine_prep_bootES <-
  data_attitude_wine %>%
  pivot_wider(
    id_cols = c("participant", "gender"),
    names_from = c("drink", "imagery"),
    values_from = "ratings",
    names_sep = "_"
  ) %>%
  mutate(
    wine_negativeVSwine_neutral = wine_negative - wine_neutral,
    wine_negativeVSwater_negative = wine_negative - water_negative,
    wine_negativeVSwater_neutral = wine_negative - water_neutral,
    wine_neutralVSwater_negative = wine_neutral - water_negative,
    wine_neutralVSwater_neutral = wine_neutral - water_neutral,
    water_negativeVSwater_neutral = water_negative - water_neutral
  ) %>%
  dplyr::select(-c(wine_negative:water_neutral)) %>%
  pivot_longer(
    cols = wine_negativeVSwine_neutral:water_negativeVSwater_neutral,
    names_to = "diff_conds",
    values_to = "ratings"
  )

library(bootES)

set.seed(20200304)

att_wine_bootES <-
  att_wine_prep_bootES %>%
  group_by(diff_conds) %>%
  nest() %>%
  rename(diff_ratings = data) %>%
  mutate(
    bootstrap = map(
      diff_ratings,
      ~ bootES(
        .,
        data.col = "ratings",
        R = 5000,
        effect.type = "r",
        ci.type = "bca",
        ci.conf = .95
      ),
      data = .
    ),
    tidy = map(bootstrap, broom::tidy, conf.int = TRUE)
  ) %>%
  ungroup()

att_wine_Pearson <-
  att_wine_bootES %>%
  unnest(tidy) %>%
  dplyr::select(
    diff_conds,
    "Pearson_r" = statistic,
    "CI95_low" = conf.low,
    "CI95_high" = conf.high,
    bias,
    "std_error" = std.error
  ) %>%
  print()

```

### Exercise 4.2

#### Exercise 4.2.1

Run a 2 (**gender**) x 2 (**drink**) x 2 (**imagery**) mixed ANOVA on likeness ratings. **Remember**: ```gender``` is a between-subject factor!

```{r exercise_4_2_1, message = FALSE}

rmANOVA_att_wine_gender <- aov_ez(
  "participant",
  "ratings",
  data_attitude_wine,
  within = c("drink", "imagery"),
  between = "gender",
  type = 3
)

rmANOVA_att_wine_gender

```

#### Exercise 4.2.2

Paired contrasts: test **only** difference ratings between *female* and *male* participants (**hint**: see example [here](https://cran.r-project.org/web/packages/afex/vignettes/afex_anova_example.html#post-hoc-contrasts-and-plotting)).

```{r exercise_4_2_2}

posthoc_att_wine_gender <-
  emmeans(rmANOVA_att_wine_gender, ~ gender | imagery | drink) %>%
  pairs(.,
    test = adjusted("free")
  ) %>%
  as.glht() %>%
  summary() %>%
  print()

```

#### Exercise 4.2.3

Bootstrapped effect sizes (**Cohen's _d_**) of the paired comparisons above.

```{r exercise_4_2_3}

att_wine_gender_prep_bootES <-
  data_attitude_wine %>%
  unite(condition, c(drink, imagery), sep = "_", remove = TRUE)

att_wine_gender_bootES <-
  att_wine_gender_prep_bootES %>%
  group_by(condition) %>%
  nest() %>%
  rename(all_ratings = data) %>%
  mutate(
    bootstrap = map(
      all_ratings,
      ~ bootES(
        .,
        data.col = "ratings",
        group.col = "gender",
        contrast = c("female", "male"),
        R = 5000,
        effect.type = "cohens.d",
        ci.type = "bca",
        ci.conf = .95
      ),
      data = .
    ),
    tidy = map(bootstrap, broom::tidy, conf.int = TRUE)
  ) %>%
  ungroup()

att_wine_gender_Cohen <-
  att_wine_gender_bootES %>%
  unnest(tidy) %>%
  dplyr::select(
    condition,
    "Cohen_d" = statistic,
    "CI95_low" = conf.low,
    "CI95_high" = conf.high,
    bias,
    "std_error" = std.error
  ) %>%
  print()

```

# Session Info

```{r sesson_info}

sessionInfo()

```


***
***