xxIRT (version 2.1.2)

estimate_gpcm: Estimate Generalizaed Partial Credit Model

Description

Estimate the GPCM using the maximum likelihood estimation

model_gpcm_eap_scoring scores response vectors using the EAP method

model_gpcm_map_scoring scores response vectors using maximum a posteriori

model_gpcm_estimate_jmle estimates the parameters using the joint maximum likelihood estimation (JMLE) method

model_gpcm_estimate_mmle estimates the parameters using the marginal maximum likelihood estimation (MMLE) method

Usage

model_gpcm_eap_scoring(u, a, b, d, D = 1.702, prior = c(0, 1),
  bound = c(-3, 3))
model_gpcm_map_scoring(u, a, b, d, D = 1.702, prior = NULL,
  bound = c(-3, 3), nr_iter = 30, nr_conv = 0.001)
model_gpcm_dv_Pt(t, a, b, d, D)
model_gpcm_dv_Pa(t, a, b, d, D)
model_gpcm_dv_Pb(t, a, b, d, D)
model_gpcm_dv_Pd(t, a, b, d, D)
model_gpcm_dv_jmle(ix, dvp)
model_gpcm_estimate_jmle(u, t = NA, a = NA, b = NA, d = NA,
  D = 1.702, iter = 100, nr_iter = 10, conv = 1, nr_conv = 0.001,
  scale = c(0, 1), bounds_t = c(-4, 4), bounds_a = c(0.01, 2),
  bounds_b = c(-4, 4), bounds_d = c(-4, 4), priors = list(t = c(0,
  1), a = c(-0.1, 0.2), b = c(0, 1), d = c(0, 1)), decay = 1,
  debug = FALSE, true_params = NULL)
model_gpcm_dv_mmle(u_ix, quad, pdv)
model_gpcm_estimate_mmle(u, t = NA, a = NA, b = NA, d = NA,
  D = 1.702, iter = 100, nr_iter = 10, conv = 1, nr_conv = 0.001,
  bounds_t = c(-4, 4), bounds_a = c(0.01, 2), bounds_b = c(-4, 4),
  bounds_d = c(-4, 4), priors = list(t = c(0, 1), a = c(-0.1, 0.2), b =
  c(0, 1), d = c(0, 1)), decay = 1, quad_degree = "11",
  scoring = c("eap", "map"), debug = FALSE, true_params = NULL)
model_gpcm_fitplot(u, t, a, b, d, D = 1.702, insert_d0 = NULL,
  index = NULL, intervals = seq(-3, 3, 0.5), show_points = TRUE)

Arguments

u

the observed response matrix, 2d matrix

a

discrimination parameters, 1d vector (fixed value) or NA (freely estimate)

b

difficulty parameters, 1d vector (fixed value) or NA (freely estimate)

d

category parameters, 2d matrix (fixed value) or NA (freely estimate)

D

the scaling constant, 1.702 by default

prior

the prior distribution

nr_iter

the maximum iterations of newton-raphson

nr_conv

the convegence criterion for newton-raphson

t

ability parameters, 1d vector (fixed value) or NA (freely estimate)

ix

the 3d indices

dvp

the derivatives of P

iter

the maximum iterations

conv

the convergence criterion of the -2 log-likelihood

scale

the scale of theta parameters

bounds_t

bounds of ability parameters

bounds_a

bounds of discrimination parameters

bounds_b

bounds of location parameters

bounds_d

bounds of category parameters

priors

a list of prior distributions

decay

decay rate

debug

TRUE to print debuggin information

true_params

a list of true parameters for evaluating the estimation accuracy

quad_degree

the number of quadrature points

scoring

the scoring method: 'eap' or 'map'

insert_d0

insert an initial category value

index

the indices of items being plotted

intervals

intervals on the x-axis

show_points

TRUE to show points

Examples

# NOT RUN {
with(model_gpcm_gendata(10, 40, 3), cbind(true=t, est=model_gpcm_eap_scoring(u, a, b, d)$t))
with(model_gpcm_gendata(10, 40, 3), cbind(true=t, est=model_gpcm_map_scoring(u, a, b, d)$t))
# }
# NOT RUN {
# generate data
x <- model_gpcm_gendata(1000, 40, 3)
# free calibration
y <- model_gpcm_estimate_jmle(x$u, true_params=x)
# no priors
y <- model_gpcm_estimate_jmle(x$u, priors=NULL, true_params=x)
# }
# NOT RUN {
# generate data
x <- model_gpcm_gendata(1000, 40, 3)
# free estimation
y <- model_gpcm_estimate_mmle(x$u, true_params=x)
# no priors
y <- model_gpcm_estimate_mmle(x$u, priors=NULL, true_params=x)
# }
# NOT RUN {
with(model_gpcm_gendata(1000, 20, 3), model_gpcm_fitplot(u, t, a, b, d, index=c(1, 3, 5)))
# }