gemmEst: Fit General Monotone Models.

In jchrszcz/gemmR: General Monotone Model

Description

gemmEst is called by gemm to fit general monotone models.

Usage

  gemmEst(input.data, output = "gemmr", n.beta = 8000, n.chains = n.chains,
  n.gens = 10, save.results = FALSE, k.pen = k.pen, seed.metric = TRUE,
  check.convergence = FALSE, roe = FALSE, fit.metric = fit.metric,
  correction = "knp", oclo = TRUE, isTauB = FALSE)

Arguments

input.data	must be data frame, first column is treated as dependent variable.
output	string argument for use in naming file output. gemmEst may write a .RData file in the current working directory each time the function is called.
n.beta	number of beta vectors to generate per generation.
n.chains	number of times the fitting process will be repeated.
n.gens	number of generations per chain.
save.results	logical value to determine whether the resulting gemm object is saved to a .RData file.
k.pen	penalty term for BIC, as calculated by gemm.formula.
seed.metric	logical value to control whether genAlg is seeded with OLS regression weights or random values.
check.convergence	logical value to indicate whether BIC for each generation is retained, mostly useful for checking performance of genAlg.
roe	logical value to determine whether region of equivalence data are retained.
fit.metric	value used to order models.
correction	placeholder for correction transformations on the fit statistic, (r or tau).
oclo	logical for Ordered Constrained Linear Optimization. If TRUE secondary sort based on r performed on matrix of beta weights in order to maximize linear fit, given the ordered fits determined by fit.metric.
isTauB	logical for whether to include ties in the denominator of the tau calculation.

Details

Formula syntax and interaction penalty terms can be avoided by fitting data directly using gemmEst.

Value

A list with class "gemm" containing the following components:

date	system time and date for model completion.
call	the matched call.
coefficients	matrix of best weights with one row for each chain.
fitted.values	model predictions for criterion generated from weights associated with best chain.
residuals	metric values for response minus fitted.
rank.residuals	rank response minus rank criterion.
bic	vector of Bayesian Information Criteria for estimation sample of each chain.
r	vector of Pearson's r values for estimation sample of each chain.
tau	vector of Kendall's tau for estimation sample of each chain.
tau.par	vector containing the correction, incorrect, criterion ties, predictor ties, and both between the weighted cues and outcome used for model fit.
metric.betas	regression weights derived using lm.
p.vals	p-values associated with ordinary least squares regression weights.
model	data frame including modeled data.
fit.metric	sorting metric used.
cross.val.bic	vector of Bayesian Information Criteria for cross-validation sample of each chain.
cross.val.r	vector of Pearson's r values for cross-validation sample of each chain.
cross.val.tau	vector of Kendall's tau for cross-validation sample of each chain.
cross.val.tau.par	vector containing the correction, incorrect, criterion ties, predictor ties, and both between the weighted cues and outcome used for crossvalidation.
converge.fit.metric	matrix of "fit.metric" values with generations by chains.
converge.beta	matrix derived weights for each generation within each chain, column for each predictor.
converge.r	generations by chains matrix of Pearson's r.
formula	formula object used.

References

Dougherty, M. R., & Thomas, R. P. (2012). Robust decision making in a nonlinear world. Psychological review, 119(2), 321.

See Also

gemm for normal use. genAlg for search, gemmFitRcppI for fitting routine, tauTest for O*(N log N) scale Kendall's tau, convergencePlot for the optional plot pane when check.convergence = TRUE.

Examples

  data(mtcars)
  gemm.model <- gemm(mpg ~ disp + cyl, data = mtcars,
    check.convergence = TRUE, n.chains = 3, n.gens = 3, n.beta = 200)
  print(gemm.model)
  plot(gemm.model)

jchrszcz/gemmR documentation built on May 18, 2019, 10:24 p.m.