lindeloev / shiny-rt Goto Github PK

Hi!

I tried to run the interactive version through the link in the non-interactive one and it seems to be crashing. Could you fix that?

Thank you.

This repository is an incredible resource! I wanted to ask about line 917 of index.Rmd, which currently reads as:

Because $\mu$ and $\sigma$ define the log-normal distribution, they are on a log scale. This means that we expect a median RT of $ndt + exp(\mu) = 0.17 + exp(-0.69) = 0.50$ seconds for condition "accuracy" (the intercept), and a median RT of exp(-0.69 -0.40) = 0.34 seconds for condition "speed". If you get confused about these transformations, worry not. brms has you covered, no matter the distribution:

I just wanted to double check about the equations-- specifically that .50 should be the sum of the first equation, and the second equation shouldn't instead equal .17 + exp(-0.69 -0.40). Thanks for such a great job already!

Thanks for this great tutorial! I tried running the applied code example on my local machine, but I get a very unspecific error:

> fit <- brm(formula=rt ~ condition + (1|id),
+            dat=data, 
+            family=shifted_lognormal(),
+            file='fit_slog')
Compiling the C++ model
Start sampling

SAMPLING FOR MODEL 'e07756ee2fd6b5fa71a0e4c57facb23a' NOW (CHAIN 1).
Chain 1: 
Chain 1: Gradient evaluation took 0.006012 seconds
Chain 1: 1000 transitions using 10 leapfrog steps per transition would take 60.12 seconds.
Chain 1: Adjust your expectations accordingly!
Chain 1: 
Chain 1: 
[1] "Error in sampler$call_sampler(args_list[[i]]) : " "  c++ exception (unknown reason)"                
error occurred during calling the sampler; sampling not done

Maybe I'm missing some required packages, but I couldn't find what I need to install (in addition to brms, tidyverse, and rtdists).