## ── Attaching packages ─────────────────────────────────────── tidyverse 1.3.2 ──
## ✔ ggplot2 3.3.6     ✔ purrr   0.3.5
## ✔ tibble  3.1.8     ✔ dplyr   1.0.9
## ✔ tidyr   1.2.0     ✔ stringr 1.5.0
## ✔ readr   2.1.2     ✔ forcats 0.5.2
## ── Conflicts ────────────────────────────────────────── tidyverse_conflicts() ──
## ✖ dplyr::filter() masks stats::filter()
## ✖ dplyr::lag()    masks stats::lag()
## here() starts at /home/vboyce/Research/mia23
library(googledrive)


f <- googledrive::as_dribble("https://docs.google.com/spreadsheets/d/1muyH0Dw2tNPK5iQ3NyiwOAz7ISWi7KoKQd6uhQnf24Q/edit#gid=262186472")
googledrive::drive_download(f, path=here("data_2","stroop.xlsx"), overwrite=T)


stroop <- readxl::read_xlsx(here("data_2","stroop.xlsx"), 
                       sheet="Form Responses 1", skip=0) |> rename(easy_task=`Task 1: Copy & paste the amount of time (secs) elapsed it took you to complete "The easy practice test"`,
                                                                   hard_task=`Task 2: Copy & paste the amount of time (secs) elapsed it took you to complete "The real hard test"`) |> 
  filter(easy_task<200) |> 
  filter(hard_task<200)

These visualizations are based on 128 submissions.

stroop_long <- stroop |> pivot_longer(easy_task:hard_task) 

ggplot(stroop_long, aes(x=value, fill=name))+
  geom_histogram()+facet_grid(name~.)+
  scale_fill_solarized()+theme(legend.position="none")+labs(x="Time to complete task in seconds")

ggsave(here(images, "histogram.png"), dev="png")

The harder task takes longer than the easier task in general, although there is some overlap between the distributions.

ggplot(stroop_long, aes(x=name, y=value, color=name))+
  geom_jitter(alpha=.1, color="black", width=.1, height=0)+
  stat_summary(fun.data = "mean_cl_boot", size=.6)+
  labs(x="", y="seconds")+
  scale_color_solarized()+
  theme(legend.position="none")

ggsave(here(images,"dots.png"), dev="png")

On average, the easy task takes half as long as the hard task.

ggplot(stroop, aes(x=easy_task, y=hard_task))+geom_point(alpha=.5)+
  geom_smooth(method="lm")+geom_abline(slope=1, intercept=0)+
  coord_equal(xlim=c(0,70), ylim=c(0,70))+
  labs(x="Time to complete easy task (sec)", y="TIme to complete hard task (sec)")

ggsave(here(images,"scatter.png"), dev="png")

Everyone is taking longer on the hard task than the easy task. Times are correlated, so some people are faster to respond overall than others.

ggplot(stroop, aes(x=hard_task-easy_task))+labs(x="Difference in time to complete tasks")+geom_density()+geom_point(y=0, alpha=.5)

ggsave(here(images, "diff.png"), dev="png")