aic()

Calculates Aikike Inforation Criteria for fitted FCR model, used for selecting optimal number of groups

bic()

Calculates Bayesian Inforation Criteria for fitted FCR model, used for selecting optimal number of groups

coef()

Extract coefficients from fitted model

coefnames()

Returns names of coefficients from fitted model

distribution()

Calculates distribution of weighted coefficients from fitted model

Arguments

• results::Model Model type from fcr output
• index::Integer Column index of variable in X matrix to calculate coefficient distibution for (defaults to 1)

fit()

Implements fuzzy clustering regression estimator from Lewis, Melcangi, Pilossoph, and Toner-Rodgers (2022)

Arguments

• y::Vector dependent var
• x::Matrix variables with heterogeneous coefficients (defaults to vector of 1's for FEs)
• Z:matrix matrix of controls
• unit:Vector vector of unit IDs
• t::Vector time vector (optional)
• G::Integer number of groups (default = 2)
• m::Real fuzzy tuning parameter
• startvals::Integer number of starting values (default = 1,000)
• cores::Integer number of cores (default = 1)

Returns:

struct with the following methods:

• coefficients::Vector: vector of coefficients
• weights::Matrix: group weights
• SE::Vector: standard errors (optional)
• objective::Number value of objective function at minimum

predict()

Obtain predicted values of the dependent variable from the fitted model, using modal group membership

residuals()

Get the vector of residuals from the fitted model

stderror()

Standard errors from fitted model

summarize()

Summarizes results from fitted model

vcov()

Variance covariance matrix from fitted model

weights()

Calculate group weights from fitted model, using modal group membership