Assignment 2

Parameter estimation in clustered data

library(tidyverse)
library(brms)

theme_set(theme_grey(base_size = 14) +
            theme(panel.grid = element_blank()))

Exercise 1

Use the simulate_treament() function to generate data. Vary the parameter settings, and then attempt to recover the known parameters using brm().

Exercise 2

Use the simulate_treament() function to generate data. Give your data to a colleague and they will give you theirs in return. Try to recover the (unknown to you) parameters using brm().

Exercise 3

Load the dataset sleepstudy from the lme4 package. These are data from a sleep deprivation study, in which the average reaction time per day (in milliseconds) was recorded.

Have a look at the data, and then try to estimate the effect of day on reaction time.

It’s always a good idea to plot the data before you do anything else.

library(lme4)
glimpse(sleepstudy)

Rows: 180
Columns: 3
$ Reaction <dbl> 249.5600, 258.7047, 250.8006, 321.4398, 356.8519, 4…
$ Days     <dbl> 0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 0, 1, 2, 3, 4, 5, 6, …
$ Subject  <fct> 308, 308, 308, 308, 308, 308, 308, 308, 308, 308, 3…