randomized_rounding: Sample integer solution from linear programming solution with...
In natstrat: Obtain Unweighted Natural Strata that Balance Many Covariates

The linear programming solution of balance_LP() that is used within optimize_controls() sometimes selects fractional units. Here, we select any unit the linear programming solution chose with coefficient 1. Then, we select the remaining required number of units from those that have fractional solutions by sampling with probabilities equal to the linear programming solution and fixed sample size. Used within optimize_controls() if correct_sizes = TRUE.

1	randomized_rounding(o, N, st, st_vals, S, z)

`o`	linear programming results, as found in the 'o' element of the returned list from `balance_LP()`.
`N`	the total number of available controls in the data.
`st`	a stratum vector with the `i`th entry equal to the stratum of unit `i`. This should have the same order of units and length as `z`.
`st_vals`	the unique stratum levels contained in `st`.
`S`	the number of unique stratum levels contained in `st`.
`z`	a factor with the `i`th entry equal to the treatment of unit `i`.

Dataframe with two columns: pr, which contains the coefficient determined for that unit from the linear programming solution, and select, a boolean vector stating whether that unit was selected for inclusion by randomized rounding.

natstrat documentation built on Oct. 15, 2021, 5:12 p.m.