Lindley Approximation Method for Generalized Process Capability Indices under Progressive Type-II Censoring

The hardware and bandwidth for this mirror is donated by dogado GmbH, the Webhosting and Full Service-Cloud Provider. Check out our Wordpress Tutorial.
If you wish to report a bug, or if you are interested in having us mirror your free-software or open-source project, please feel free to contact us at mirror[@]dogado.de.

Shikhar Tyagi, Sumit Kumar, Arvind Pandey, Bhupendra Singh, Vrijesh Tripathi

Introduction

The gpciLindApproxProgII package provides a Bayesian statistical framework for computing Generalized Process Capability Indices (GPCIs) under Progressive Type-II Censored Data using Lindley’s 3rd-order Approximation Method.

Progressive Type-II Censoring Model

Let \(n\) units be placed on test and \(m\) failure times \(X = (x_1, x_2, \dots, x_m)\) be observed under progressive removal scheme \(R = (R_1, R_2, \dots, R_m)\). The progressive log-likelihood function is:

\[\ell(\theta) = \sum_{i=1}^m \log f(x_i; \theta) + \sum_{i=1}^m R_i \log S(x_i; \theta)\]

Example Analysis

Below is a demonstration of fitting progressive Type-II failure data with custom user functions or built-in distributions.

# Failure times and progressive removal scheme
x <- c(0.5, 1.2, 2.1, 3.4, 4.8)
r <- c(1, 0, 2, 0, 1)

# Fit model using Lindley approximation and chain generation
fit <- lindley_prog_gpci(
  x = x,
  r_removals = r,
  distribution = dist_weibull(),
  USL = 6, LSL = 0,
  chain_length = 200,
  burn_in = 50,
  thinning = 1,
  B = 50
)

# Print Summary Table
summary(fit)
#>     Index MLE_Estimate Lindley_Estimate    Chain_Mean          Bias
#> 1     Cpy 4.953015e-01     4.247116e-01  4.177683e-01 -7.753318e-02
#> 2      Cp 1.000000e+04     1.000000e+04  7.730188e+03 -2.269812e+03
#> 3     Cpk 2.977036e-73    -3.832680e-43  1.404065e-03  1.404065e-03
#> 4     Cpu 2.000000e+04     2.000000e+04  1.546033e+04 -4.539668e+03
#> 5     Cpl 2.977036e-73    -3.832680e-43  4.401479e-02  4.401479e-02
#> 6     Cpm 3.333333e-01     3.333333e-01  2.880503e-01 -4.528308e-02
#> 7    Cpmk 9.923452e-78    -1.277560e-47  1.366696e-03  1.366696e-03
#> 8    CpTk 1.249103e-01     1.102875e-01  1.000801e-01 -2.483017e-02
#> 9    Spmk 2.141650e+03     1.977308e+03  1.231935e+03 -9.097149e+02
#> 10    Cpc 1.000000e+04     1.000000e+04  7.732466e+03 -2.267534e+03
#> 11   CNpk 0.000000e+00     0.000000e+00 -7.214422e-03 -7.214422e-03
#> 12  CNpmc 4.792753e-02     4.136523e-02  3.720504e-02 -1.072249e-02
#> 13 CNpmkc 0.000000e+00     0.000000e+00  2.266697e-04  2.266697e-04
#> 14  Cp_uv 0.000000e+00     0.000000e+00  1.366696e-03  1.366696e-03
#>             MSE   Risk_Value   HPD90_Lower  HPD90_Upper   HPD95_Lower
#> 1  2.343364e-02 2.936810e-02  2.601978e-01 5.749860e-01  2.432379e-01
#> 2  2.232023e+07 2.232930e+07  1.404483e-01 1.000000e+04  7.520631e-02
#> 3  7.029974e-04 7.049693e-04 -7.174927e-02 1.590372e-06 -7.174927e-02
#> 4  8.928267e+07 8.930082e+07  2.758702e-02 2.000000e+04 -4.174774e-02
#> 5  1.263764e-02 1.458923e-02  0.000000e+00 2.635498e-01  0.000000e+00
#> 6  1.030821e-02 1.234337e-02  1.294286e-01 3.333333e-01  7.041530e-02
#> 7  6.372686e-04 6.391369e-04 -6.771775e-02 1.819564e-08 -6.771775e-02
#> 8  1.385563e-03 1.999557e-03  5.899898e-02 1.440558e-01  3.837450e-02
#> 9  1.493858e+06 1.497489e+06  4.218943e-05 2.301085e+03  4.218943e-05
#> 10 2.229910e+07 2.230816e+07  1.605108e-01 1.000000e+04  7.041530e-02
#> 11 7.717603e-03 7.769588e-03  0.000000e+00 1.564175e-01 -1.310207e-01
#> 12 3.026810e-04 4.174476e-04  1.428994e-02 5.518352e-02  7.599846e-03
#> 13 1.715619e-06 1.767000e-06 -1.546218e-03 2.814646e-04 -1.546218e-03
#> 14 6.372686e-04 6.391369e-04 -6.771775e-02 1.819564e-08 -6.771775e-02
#>     HPD95_Upper   HPD99_Lower  HPD99_Upper    HW_Stat HW_Pvalue HW_Passed
#> 1  7.088777e-01  1.946527e-01 9.038548e-01 0.15621723       0.5      TRUE
#> 2  1.000000e+04  4.012932e-04 1.000000e+04 0.06293788       0.5      TRUE
#> 3  5.439582e-02 -7.174927e-02 1.213582e-01 0.21609261       0.5      TRUE
#> 4  2.000000e+04 -6.991147e-02 2.000000e+04 0.06293746       0.5      TRUE
#> 5  3.159464e-01  0.000000e+00 3.543571e-01 0.05472611       0.5      TRUE
#> 6  3.333333e-01  3.981231e-04 3.333333e-01 0.10574099       0.5      TRUE
#> 7  5.088988e-02 -6.771775e-02 1.171238e-01 0.21550619       0.5      TRUE
#> 8  1.440558e-01  1.045417e-02 1.477033e-01 0.06443744       0.5      TRUE
#> 9  2.435750e+03  4.218943e-05 2.689890e+03 0.07940454       0.5      TRUE
#> 10 1.000000e+04  3.981223e-04 1.000000e+04 0.06333397       0.5      TRUE
#> 11 2.205716e-01 -4.669647e-01 2.205716e-01 0.16040564       0.5      TRUE
#> 12 5.539170e-02  1.246212e-05 5.518352e-02 0.12133421       0.5      TRUE
#> 13 3.443590e-03 -1.546218e-03 7.548219e-03 0.15528746       0.5      TRUE
#> 14 5.088988e-02 -6.771775e-02 1.171238e-01 0.21550619       0.5      TRUE
#>    Convergence_Prob Boot95_Lower Boot95_Upper
#> 1               0.5 3.275979e-01 1.584475e+00
#> 2               0.5 1.966687e+03 1.000000e+04
#> 3               0.5 0.000000e+00 1.675544e-02
#> 4               0.5 3.933153e+03 2.000000e+04
#> 5               0.5 0.000000e+00 2.215312e-01
#> 6               0.5 2.460495e-01 3.333333e-01
#> 7               0.5 0.000000e+00 1.534837e-02
#> 8               0.5 3.524268e-02 1.552800e-01
#> 9               0.5 4.989649e-01 2.669147e+03
#> 10              0.5 2.022567e+03 1.000000e+04
#> 11              0.5 0.000000e+00 3.581466e-02
#> 12              0.5 2.915852e-02 5.555556e-02
#> 13              0.5 0.000000e+00 9.138423e-04
#> 14              0.5 0.000000e+00 1.534837e-02

Plotting Results

plot(fit)

These binaries (installable software) and packages are in development.
They may not be fully stable and should be used with caution. We make no claims about them.
Health stats visible at Monitor.