No packages match

natstrat - Obtain Unweighted Natural Strata that Balance Many Covariates

Natural strata can be used in observational studies to balance the distributions of many covariates across any number of treatment groups and any number of comparisons. These strata have proportional amounts of units within each stratum across the treatments, allowing for simple interpretation and aggregation across strata. Within each stratum, the units are chosen using randomized rounding of a linear program that balances many covariates. For more details, see Brumberg et al. (2022) <doi:10.1111/rssa.12848> and Brumberg et al.(2023) <doi:10.1093/jrsssc/qlad010>. To solve the linear program, the 'Gurobi' commercial optimization software is recommended, but not required. The 'gurobi' R package can be installed by following the instructions at <https://docs.gurobi.com/projects/optimizer/en/current/reference/r/setup.html> after claiming your free academic license at <https://www.gurobi.com/academia/academic-program-and-licenses/>.

Last updated

3.70 score 3 scripts 192 downloads

optrefine - Optimally Refine Strata

Splits initial strata into refined strata that optimize covariate balance. For more information, please see Brumberg, Small, and Rosenbaum (2024) <doi:10.1093/biomtc/ujae061>. To solve the linear program, the 'Gurobi' commercial optimization software is recommended, but not required. The 'gurobi' R package can be installed following the instructions at <https://docs.gurobi.com/projects/optimizer/en/current/reference/r/setup.html> after claiming your free academic license at <https://www.gurobi.com/academia/academic-program-and-licenses/>.

Last updated

3.00 score 2 stars 1 scripts 152 downloads

triplesmatch - Match Triples Consisting of Two Controls and a Treated Unit or Vice Versa

Attain excellent covariate balance by matching two treated units and one control unit or vice versa within strata. Using such triples, as opposed to also allowing pairs of treated and control units, allows easier interpretation of the two possible weights of observations and better insensitivity to unmeasured bias in the test statistic. Using triples instead of matching in a fixed 1:2 or 2:1 ratio allows for the match to be feasible in more situations. The 'rrelaxiv' package, which provides an alternative solver for the underlying network flow problems, carries an academic license and is not available on CRAN, but may be downloaded from 'GitHub' at <https://github.com/josherrickson/rrelaxiv/>. The 'Gurobi' commercial optimization software is required to use the two functions [infsentrip()] and [triplesIP()]. These functions are not essential to the main purpose of this package. A free academic license can be obtained at <https://www.gurobi.com/features/academic-named-user-license/>. The 'gurobi' R package can then be installed following the instructions at <https://www.gurobi.com/documentation/9.1/refman/ins_the_r_package.html>.

Last updated

2.70 score 3 scripts 144 downloads

observationalBlocks - Block Designs for Observational Studies

Creates block designs of fixed size J with at least one treated and control unit per block. Blocks larger than pairs better distinguish effects caused by a treatment from unmeasured confounding in assignment of individuals to treatment. Somewhat counterintuitively, blocks larger than pairs can use more units while attaining better covariate balance and block homogeneity. A forthcoming manuscript by Brumberg and Rosenbaum details the design.

Last updated

2.70 score 1 scripts 499 downloads