Generates a Design object with the given specifications.

Generate a randomized control treatment Design (rct_design()), or an observational Design (obs_design()), or a regression discontinuity Design (rd_design()).

Usage

rct_design(formula, data, subset = NULL, na.fail = TRUE)

rd_design(formula, data, subset = NULL, na.fail = TRUE)

obs_design(formula, data, subset = NULL, na.fail = TRUE)

Arguments

formula: a formula defining the Design components. See Details for specification.
data: the data set from which to build the Design. Note that this data need not be the same as used to estimate the treatment effect; rather the data passed should contain information about the units of treatment assignment (as opposed to the units of analysis).
subset: optional, subset the data before creating the Design object
na.fail: If TRUE (default), any missing data found in the variables specified in formula (excluding treatment) will trigger an error. If FALSE, non-complete cases will be dropped before the creation of the Design

Value

a Design object of the requested type for use in further analysis.

Details

The formula must include exactly one unit_of_assignment() to identify the units of assignment (one or more variables). (uoa, cluster, or unitid are synonyms for unit_of_assignment; the choice of which has no impact on the analysis.) If defining an rd_design, the formula must also include a forcing() entry. The formula may optionally include a block() as well. Each of these can take in multiple variables, e.g. to pass both a household ID and individual ID as unit of assignment, use uoa(hhid, iid) and not uoa(hhid) + uoa(iid).

The treatment variable passed into the left-hand side of formula can either be logical, numeric, or character. If it is anything else, it attempts conversion to one of those types (for example, factor and ordered are converted to numeric if the levels are numeric, otherwise to character). If the treatment is not logical or numeric with only values 0 and 1, in order to generate weights with ate() or ett(), the dichotomy argument must be used in those functions to identify the treatment and control groups. See ett() for more details on specifying a dichotomy.

Examples

data(simdata)
des <- rct_design(z ~ unit_of_assignment(uoa1, uoa2) + block(bid),
                  data = simdata)

data(schooldata)
des <- obs_design(treatment ~ unit_of_assignment(schoolid) + block(state),
                  data = schooldata)