markdly
commented
6 years ago cq_show() is now flexible enough to import tables from show files when a dif analysis was requested (e.g. model: item + gender + item*gender). Added in 7994b3768e26acf1be4ac20821da66ba7f564deb
Example usage:
library(conquestr)
x <- system.file("extdata", "dif.shw", package = "conquestr")
df <- cq_show(x, fit = FALSE)
df
#> # A tibble: 3 x 2
#> term data
#> <chr> <list>
#> 1 grp <tibble [2 × 13]>
#> 2 item <tibble [20 × 13]>
#> 3 item*grp <tibble [40 × 15]>
df$data[[1]]
#> # A tibble: 2 x 13
#> grp_index grp est err uw_mnsq uw_ci_lo uw_ci_hi uw_t mnsq ci_lo
#> <int> <int> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl>
#> 1 1 1 0.258 0.019 1 0.88 1.12 0 1 0.88
#> 2 2 2 -0.258 0.019 1.04 0.88 1.12 0.7 1.04 0.88
#> # ... with 3 more variables: ci_hi <dbl>, t <dbl>, section_index <chr>Created on 2018-09-12 by the reprex package (v0.2.0).
I think the other features such as labelling for 'favouring' etc are not really a good fit for conquestr at this stage. E.g. the 'rules' are likely to change depending on the context so I'm inclined to leave those out for now (and implement on a project basis instead). Let me know if you feel strongly otherwise though! 😄
cqc_Show to read in the gender result. I need item index, Chi Sqr results, and if item favours a gender