transposed mu data.frame
debruine opened this issue · comments
Bug found by @doomlab
library(faux)
between <- list(where_bought = c(online = "online", store = "Store"),
who_bought = c(different = "Different", same = "Same"))
within <- list(rm_var = c("money", "time"))
how_many <- 100
# doesn't work
mu <- data.frame(
online = c(25, 2),
store = c(35, 10),
different = c(25, 1.5),
same = c(35, 12),
row.names = within$rm_var
)
# does work!?
mu2 <- t(mu)
lab4_update <- sim_design(within, between, n = how_many, mu = mu2,
sd = 3, r = .10,
empirical = FALSE, plot = TRUE)
Ok, so yeah, I think I was misunderstanding what you were doing. That code only worked because it had the right number of numbers. Here's what I should have done:
##simulated data
between <- list(where_bought = c(online = "Online",
store = "Store"),
who_bought = c(different = "Different",
same = "Same"))
within <- list(rm_var = c("money", "time"))
##pattern is money, then time, so keep the numbers larger in the first one
mu <- data.frame(
online_different = c(25, 10),
online_same = c(25, 10),
store_different = c(35, 15),
store_same = c(35, 20),
row.names = within$rm_var)
lab4_update <- sim_design(within, between,
n = how_many, mu = mu,
sd = 3, r = .10,
interactive = FALSE,
empirical = FALSE,
plot = TRUE,
seed = this_year_seed)
So maybe the bug is the user ;).