Breaking Changes

Parametric Models

  • rank_regression(): For all distributions, the confidence intervals of the parameters are now computed on the basis of a heteroscedasticity-consistent (HC) covariance matrix. If the confidence intervals for the Weibull parameters are to be calculated according to Mock, this must be specified via the new argument options.
  • mixmod_regression(): Since this function uses rank_regression(), the changes regarding the confidence intervals also apply here.
  • plot_prob.wt_model(): Removed dysfunctional argument distribution. The distribution is inferred using the model x.

Confidence Intervals

Monte Carlo Simulation

New Features

Distributions

  • Implementation of one- and two-parametric exponential distribution ('exponential' and 'exponential2').

Non-Parametric Failure Probabilities

  • estimate_cdf(): Added option johnson_method to specify the formula which is used for determining cumulative failure probabilities.

Parametric Models

Confidence Intervals

Monte Carlo Simulation

Lifecycle changes

Minor Improvements and bug fixes

Reliability Data

  • Fixed bug in reliability_data(): Using !! syntax with arguments x and status resulted in an error.
  • estimate_cdf() preserves additional columns, that were returned from reliability_data(..., .keep_all = TRUE).
  • Improved print.wt_reliability_data().

Confidence Intervals

Monte Carlo Simulation

  • The object returned by mcs_mileage() now has class wt_mcs_mileage.
  • The object returned by mcs_delay() now has class wt_mcs_delay.
  • The object returned by dist_mileage() now has class wt_mileage_estimation.
  • The object returned by dist_delay() now has class wt_delay_estimation or wt_delay_estimation_list.

Documentation improvements

Breaking Changes

  • Package now depends on R(>= 3.5.0)

Non-Parametric Failure Probabilities

Parametric Models

Confidence Intervals

  • confint_betabinom.default() (former confint_betabinom()): Renamed event with status. Renamed loc_sc_params with dist_params. Added argument b_lives which allows the user to specify probabilities p for B_p-lives to be considered.
  • confint_fisher.default() (former confint_fisher()): Renamed event with status. Renamed loc_sc_params with dist_params. Renamed loc_sc_varcov with dist_varcov. Added argument b_lives which allows the user to specify probabilities p for B_p-lives to be considered.
  • delta_method(): Renamed loc_sc_params with dist_params. Renamed loc_sc_varcov with dist_varcov.
  • plot_conf.default() (former plot_conf()): Switched position of arguments direction and distribution.

Monte Carlo Simulation

New Features

  • Added support for ggplot2 in all plot functions. Plot method can be selected in plot_prob() or plot_pop() via argument plot_method.
  • Added reliability_data(): Create consistent reliability data.
  • Added estimate_cdf(): Unite functionality of mr_method(), johnson_method(), kaplan_method() and nelson_method(). Added option ties.method for method = "mr", which specifies how ties should be treated.
  • Support of multiple methods in estimate_cdf() and all functions that depend on the cdf_estimation (rank_regression(), plot_prob(), plot_mod(), plot_conf(), mixmod_regression()).
  • plot_prob() and plot_mod() are able to handle mixture models.
  • mixmod_regression() is now more flexible. Argument k can be used to control number of subgroups or to determine them in an automatic fashion. Argument control provides additional control over the segmentation procedure.
  • Added print.wt_rank_regression(), print.wt_ml_estimation(), print.wt_model_estimation(), print.wt_model_estimation_list(), print.wt_mixmod_regression() and print.wt_mixmod_regression_list().
  • Added vcov.wt_model_estimation().
  • Added dist_delay(): Generalizes the distribution-specific modeling of delays.
  • Added mcs_delay(): Generalizes the adjustment of operating times by delays and supports multiple delays at once.
  • Added lifecycle badges

Introduction of S3 interface

Documentation improvements

  • Revised README.
  • Revised vignettes.
  • Capitalized parameter documentation.

Lifecycle changes

Removed

  • calculate_ranks.
  • mixture_em_cpp.
  • plot_layout.

Minor improvements and bug fixes

  • Fixed installation error when using clang compiler

Prerequisite for Package Usage:

  • Since RcppArmadillo is used, the R version should be at least 3.3.0 (listed under Depends in DESCRIPTION file)

Changes

  • Vignettes for non-parametric probability estimation, parameter estimation using Median-Rank Regression and Maximum-Likelihood and mixture model estimation are provided.
  • Argument y in functions plot_prob_mix() and plot_mod_mix() is deprecated and not used anymore.
  • Argument reg_output in functions plot_prob_mix() and plot_mod_mix() is deprecated; use mix_output instead.
  • Function plot_mod_mix() was revised and updated in the way that the obtained results of the function mixmod_em() can be visualized.
  • Function plot_prob_mix() was revised and updated in the way that the obtained results of the function mixmod_em() can be visualized.
  • Implementation of EM-Algorithm using Newton-Raphson. The algorithm is written in c++ (mixture_em_cpp()) and is called in mixmod_em().
  • New method for the computation of Fisher’s Confidence Bounds regarding probabilities is used. These method is called “z-Procedure” and is more appropriate to manage the bend-back behavior. Therefore an adjustment of functions delta_method() and confint_fisher() was made.
  • Implementation of log-location-scale models with threshold parameter like three-parametric Weibull (“weibull3”), three-parametric lognormal (“lognormal3”) and three-parametric loglogistic (“loglogistic3”).
  • Implementation of location-scale models like smallest extreme value (“sev”), normal (“normal”) and logistic (“logistic”).
  • Implementation of Log-Likelihood Profiling for three-parametric models in function loglik_profiling(). In general this function is used inside ml_estimation() for the purpose of estimating threshold parameter of three-parametric models.
  • Implementation of R-Squared Profiling for three-parametric models in function r_squared_profiling(). In general this function is used inside rank_regression() for the purpose of estimating threshold parameter of three-parametric models.
  • Implementation of Log-Likelihood Function for all implemented models in function loglik_function(). In general this function is used inside ml_estimation() for the purpose of estimating the variance-covariance matrix of location-scale models “sev”, “normal” and “logistic”. The function is also used to estimate the variance-covariance matrix of log-location-scale models with a threshold parameter, i.e. “weibull3”, “lognormal3” and “loglogistic3”.
  • new argument in function ml_estimation(): wts for case weights.