It solves quadratically constrained CRS generalized oriented DEA models (see Bolós et al. 2026), using alabama solver. By default, models are solved in a two-stage process (slacks are maximized).
model_qgo(datadea,
dmu_eval = NULL,
dmu_ref = NULL,
d_input = 1,
d_output = 1,
rts = c("crs", "vrs", "nirs", "ndrs", "grs"),
L = 1,
U = 1,
give_X = TRUE,
n_attempts_max = 5,
force_quad = FALSE,
maxslack = TRUE,
weight_slack_i = 1,
weight_slack_o = 1,
returnqp = FALSE,
...)A list of class dea with the results for the evaluated DMUs (DMU component,
we note that we call "targets" to the "efficient projections"
in the strongly efficient frontier),
along with any other necessary information to replicate the results, such as
the name of the model and parameters d_input, d_output, rts,
dmu_eval and dmu_ref.
A deadata object with n DMUs, m inputs and s
outputs.
A numeric vector containing which DMUs have to be evaluated.
If NULL (default), all DMUs are considered.
A numeric vector containing which DMUs are the evaluation
reference set.
If NULL (default), all DMUs are considered.
A value, vector of length m, or matrix m x ne
(where ne is the length of dmu_eval) with the input orientation parameters.
If d_input == 1 (default) and d_output == 0, it is equivalent
to input oriented.
A value, vector of length s, or matrix s x ne
(where ne is the length of dmu_eval) with the output orientation parameters.
If d_input == 0 and d_output == 1 (default), it is equivalent
to output oriented.
A string, determining the type of returns to scale, equal to "crs" (constant), "vrs" (variable), "nirs" (non-increasing), "ndrs" (non-decreasing) or "grs" (generalized).
Lower bound for the generalized returns to scale (grs).
Upper bound for the generalized returns to scale (grs).
Logical. If it is TRUE (default), it uses an initial vector (given by
the evaluated DMU) for the solver. If it is FALSE, the initial vector is given
internally by the solver and it is usually randomly generated.
A value with the maximum number of attempts if the solver does not converge. Each attempt uses a different initial vector.
Logical. If it is FALSE (default) it uses the linear
model model_lgo to get the results, in some particular cases in which
the results of model_qgo can be deduced from the results of model_lgo,
see V. J. Bolós et al. (2026).
Logical. If it is TRUE, it computes the max slack solution.
A value, vector of length m, or matrix m x ne
(where ne is the length of dmu_eval) with the weights of the input slacks
for the max slack solution.
A value, vector of length s, or matrix s x ne
(where ne is the length of dmu_eval) with the weights of the output
slacks for the max slack solution.
Logical. If it is TRUE, it returns the quadratic problems
(objective function and constraints) of stage 1.
Other parameters to be passed to the solver solvecop from package
optiSolve.
Vicente Coll-Serrano (vicente.coll@uv.es). Quantitative Methods for Measuring Culture (MC2). Applied Economics.
Vicente Bolós (vicente.bolos@uv.es). Department of Business Mathematics
Rafael Benítez (rafael.suarez@uv.es). Department of Business Mathematics
University of Valencia (Spain)
Bolós, V.J.; Benítez, R.; Coll-Serrano, V (2026). "A new family of models with generalized orientation in data envelopment analysis". International Transactions in Operational Research. tools:::Rd_expr_doi("10.1111/itor.70063")
model_basic, model_dir, model_lgo
data("PFT1981")
# Selecting DMUs in Program Follow Through (PFT)
PFT <- PFT1981[1:49, ]
PFT <- make_deadata(PFT,
inputs = 2:6,
outputs = 7:9 )
eval_pft <- model_qgo(PFT, dmu_eval = 1:5)
efficiencies(eval_pft)
Run the code above in your browser using DataLab