Weibull Advanced Pane for a Reliability Growth Data Set
When a reliability growth data set is selected in the LDA Navigator, you supply the advanced parameters needed for this type of analysis in the Weibull Advanced pane. For this type of data set, the estimation method is always display-only because the method depends on the data type that you selected in the Weibull Parameters pane. The following table describes all parameters that appear in this pane for a reliability growth data set.
Parameter
Description
Estimation method
The procedure for estimating the parameters for the failure distribution is based on the data type selected for the reliability growth data set in the Weibull Parameters pane. The estimation method can also determine how well the analysis line fits the data set being analyzed.
MLE (maximum likelihood estimation). For a Crow/AMSAA data type, the MLE estimation method is used. This is an iterative solution procedure. MLE maximizes the likelihood and log likelihood of the distribution. In this case, Use MMLE is available.
Ranked Regression. For a Duane data type, the ranked regression estimation method is used.
Use MMLE
Indicates whether to use MMLE (modified maximum likelihood estimation) to reduce the bias that sometimes occurs in the MLE method. This checkbox is available only when MLE is selected as the estimation method.
When it is cleared (default), a bias corrective factor is not used to adjust the MLE.
When it is selected, a bias corrective factor is used to adjust the MLE.
Specify best fit time range
Indicates whether starting and ending times for the plot are specified. This range of time should represent the period when the product or system is operating. When this check box is cleared (default), Start time and End time are unavailable. The smallest and largest time values for the data points are used to determine the minimum and maximum values for the plot’s x-axis. When this checkbox is selected, Start time and End time become available so that you can enter the minimum and maximum values to use for the plot’s x-axis. For a plot of a reliability growth data set, you cannot change the range for the x-axis values on the Axis page in the Plot Properties sheet. For more information, see Axis Page.
Start time
The time that the product or system begins operating. The default is 0.01.
End time
The time that the produce or system stops operating. The default is 100.
Termination type
Indicates whether the end of operation is due to a failure or reaching some specified amount of operating time. Choices are:
Failure. When selected (default), no other information is needed.
Time. When selected, a termination time greater than or equal to the time of the last data point must be entered in the field that becomes available to the right.
Calculation results
The display-only results under this heading show the parameter values for the selected estimation method once the data set has been calculated.
When a Duane data type is selected, the ranked regression estimation method is used. In this case, λ, β, α, and ρ2 are calculated.
When a Crow/AMSAA data type is selected, the MLE estimation method is used. Because MLE does not result in X and Y values that can be plotted on a probability plot, no ρ2 value is associated with it. In this case, only λ, β, and α are calculated.