Maximum Likelihood Estimation for Probability Functions from Data Sets
Expected value of a maxlogLreg model.
Expected value of a given function for any distribution
Numerical integration through Gaussian Quadrature
Half normal key function
Hazard functions for any distribution
Hazard rate key function
Hazard shape extracted from HazardShape objects
Integration
Internal functions for formula and data handle
Configure various aspects of interpolating function in `TTT_hazard_sha...
Is return of any object of EstimationTools?
Customize legend for plot.HazardShape outputs
Configure various aspects of LOESS in TTT_hazard_shape
Logarithmic link function (for estimation with maxlogL object)
Logit link function (for estimation with maxlogL object)
Maximum Likelihood Estimation for parametric distributions
Maximum Likelihood Estimation for parametric linear regression models
Negative inverse link function (for estimation with maxlogL object)
Plot method for EmpiricalTTT objects
Plot of HazardShape objects
Plot Residual Diagnostics for an maxlogL Object
Summation of One-Dimensional Functions
Hazard Shape estimation from TTT plot
Empirical Total Time on Test (TTT), analytic version.
Uniform key function
Cumuative hazard function of a maxlogLreg model.
Bootstrap computation of standard error for maxlogL class objects.
Extract Model Coefficients in a maxlogL Fits
Cumulative hazard functions for any distribution
Predict Method for maxlogL Fits
Print method for HazardShape objects
Extract Residuals from maxlogL model.
Set custom optimizer in maxlogLreg
Summarize Maximum Likelihood Estimation
Total Time on Test plot and routines for parameter estimation of any lifetime distribution implemented in R via maximum likelihood (ML) given a data set. It is implemented thinking on parametric survival analysis, but it feasible to use in parameter estimation of probability density or mass functions in any field. The main routines 'maxlogL' and 'maxlogLreg' are wrapper functions specifically developed for ML estimation. There are included optimization procedures such as 'nlminb' and 'optim' from base package, and 'DEoptim' Mullen (2011) <doi:10.18637/jss.v040.i06>. Standard errors are estimated with 'numDeriv' Gilbert (2011) <https://CRAN.R-project.org/package=numDeriv> or the option 'Hessian = TRUE' of 'optim' function.
Useful links