Method to get the names of ill-defined parameters

+ +

The method for generalised nonlinear regression fits as obtained +with mkinfit and mmkin checks if the degradation parameters +pass the Wald test (in degradation kinetics often simply called t-test) for +significant difference from zero. For this test, the parameterisation +without parameter transformations is used.

+ +

Usage

illparms(object, ...)
+
+# S3 method for class 'mkinfit'
+illparms(object, conf.level = 0.95, ...)
+
+# S3 method for class 'illparms.mkinfit'
+print(x, ...)
+
+# S3 method for class 'mmkin'
+illparms(object, conf.level = 0.95, ...)
+
+# S3 method for class 'illparms.mmkin'
+print(x, ...)
+
+# S3 method for class 'saem.mmkin'
+illparms(
+  object,
+  conf.level = 0.95,
+  random = TRUE,
+  errmod = TRUE,
+  slopes = TRUE,
+  ...
+)
+
+# S3 method for class 'illparms.saem.mmkin'
+print(x, ...)
+
+# S3 method for class 'mhmkin'
+illparms(object, conf.level = 0.95, random = TRUE, errmod = TRUE, ...)
+
+# S3 method for class 'illparms.mhmkin'
+print(x, ...)

+ +

Arguments

+ + +

object: The object to investigate
...: For potential future extensions
conf.level: The confidence level for checking p values
x: The object to be printed
random: For hierarchical fits, should random effects be tested?
errmod: For hierarchical fits, should error model parameters be +tested?
slopes: For hierarchical saem fits using saemix as backend, +should slope parameters in the covariate model(starting with 'beta_') be +tested?

Value

For mkinfit or saem objects, a character vector of parameter +names. For mmkin or mhmkin objects, a matrix like object of class +'illparms.mmkin' or 'illparms.mhmkin'.

Details

The method for hierarchical model fits, also known as nonlinear +mixed-effects model fits as obtained with saem and mhmkin +checks if any of the confidence intervals for the random +effects expressed as standard deviations include zero, and if +the confidence intervals for the error model parameters include +zero.

Note

All return objects have printing methods. For the single fits, printing +does not output anything in the case no ill-defined parameters are found.

+ +

Examples

fit <- mkinfit("FOMC", FOCUS_2006_A, quiet = TRUE)
+#> Warning: Optimisation did not converge:
+#> false convergence (8)
+illparms(fit)
+#> [1] "parent_0" "alpha"    "beta"     "sigma"   
+# \dontrun{
+fits <- mmkin(
+  c("SFO", "FOMC"),
+  list("FOCUS A" = FOCUS_2006_A,
+       "FOCUS C" = FOCUS_2006_C),
+  quiet = TRUE)
+illparms(fits)
+#>       dataset
+#> model  FOCUS A                      FOCUS C
+#>   SFO                                      
+#>   FOMC parent_0, alpha, beta, sigma        
+# }
+