In my study a control group © is pretested (pre.c) and post-tested (pos.c). Similarly a treatment group (t) is prettested (pre.t) and post-tested (pos.t). So I have two groups (group factor) tested at two time points (time factor).

I have fit a linear regression using stan_glm() from rstanarm package. I’m wondering though how to interpret the results without any effect sizes reported in the output (see below)?

Is it possible to obtain effect sizes for the main and interaction effects in rstanarm package?

pre.c = c(0.2521539, -0.8839510, 1.0106639, 1.2189900, -2.5187683, 0.1119494, 1.1506801, 1.2056992, 1.7262407, 3.1810580)

pos.c = c(1.5293298, 0.6043102, 0.5317992, 2.4416711, -2.6809858, 0.4981319, 4.0499866, 0.5683203, 4.0376835, 2.6794024)

pre.t = c(-1.0432592, 4.4818748, 3.5557269, 0.5164588, 3.3919210, 3.9045262, -0.6085360, 2.1122688, -0.2043023, 4.6272319)

pos.t = c(6.451760, 10.089001, 8.472512, 5.555241, 8.743465, 9.036619, 7.050737, 9.584346, 5.852163, 8.372967)

data <- data.frame(y = c(pre.c, pos.c, pre.t, pos.t),

time = rep(0:1, 20),

group = rep(c(0, 1), each = 20))

library(rstanarm) #### The R package ####

fit <- stan_glm(y ~ group * time, data = data,

prior_intercept = normal(0, 10),

prior = normal(0, 2.5),

prior_aux = normal(0, 10))

Output:

```
Estimates:
mean sd 2.5% 25% 50% 75% 97.5%
```

(Intercept) 0.9 0.9 -0.9 0.3 0.9 1.6 2.7

group 3.2 1.3 0.6 2.4 3.2 4.0 5.7

time 0.2 1.3 -2.3 -0.7 0.3 1.1 2.8

group:time 1.4 1.8 -2.3 0.2 1.5 2.6 5.0