R/ffd_opt_caschool_input_il.R
df_opt_caschool_input_il.Rd\(\text{ID}_i\): individual id \(\text{ID}_{il}\): unique id for individual/allocation id \(D^{\text{max}}_{i}\): maximimum discrete allocation each person \(D_{il}\): lth discrete allocation level for ith person, if fully redistributing, then this is equal to toal allocation count, if this is distribution additional teachers, this is equal to the additional allocation of teachers for each school. \(A_{il}\): A when considering the lth allocation for ith person, expected outcome without the lth allocation \(\alpha_{il}\): marginal expected effect of the lth allocation \(\beta_{i}\): i specific preference
data(df_opt_caschool_input_il)csv
https://fmwww.bc.edu/ec-p/data/stockwatson/caschool.des https://fanwangecon.github.io/PrjOptiAlloc/articles/ffv_opt_sodis_rkone_casch_allrw.html
Stock, James H. and Mark W. Watson (2003) Introduction to Econometrics, Addison-Wesley Educational Publishers, chapter 4–7.
data(df_opt_caschool_input_il)
head(df_opt_caschool_input_il, 30)
#> # A tibble: 30 x 7
#> id_i id_il D_max_i D_il A_il alpha_il beta_i
#> <int> <int> <dbl> <int> <dbl> <dbl> <dbl>
#> 1 1 1 11 1 691. 1.29 0.00238
#> 2 1 2 11 2 692. 1.09 0.00238
#> 3 1 3 11 3 693. 0.932 0.00238
#> 4 1 4 11 4 694. 0.808 0.00238
#> 5 1 5 11 5 695. 0.707 0.00238
#> 6 1 6 11 6 696. 0.624 0.00238
#> 7 1 7 11 7 696. 0.554 0.00238
#> 8 1 8 11 8 697. 0.496 0.00238
#> 9 1 9 11 9 697. 0.446 0.00238
#> 10 1 10 11 10 698. 0.404 0.00238
#> # ... with 20 more rows