|
Parameter
|
Description
|
|---|---|
|
Data type
|
The type of data to use in the non-parametric LDA. Choices are Inspection and Interval. The default is Inspection. The selection you make here, and the status of Grouped for inspection data, affects the columns shown in the Weibull Data Points pane. For more information, see Weibull Parameters Pane for a Non-Parametric Life Data Set.
|
|
Grouped
|
Indicates whether inspection data is collected in ranges rather than shown in a precise form. This checkbox is available only when Inspection is selected as the data type. As indicated above, it affects the columns shown in the Weibull Data Points pane. When this checkbox is cleared (default), inspection data is not grouped. In this case, Quantity in State and Failure/Suspension columns are shown. When this checkbox is selected, inspection data is grouped. In this case, Quantity Failed and Quantity Suspended columns are shown.
|
|
Total quantity
|
Indicates the total number of units for which data has been collected. This checkbox is available only when Interval is selected as the data type. It controls whether the Total Quantity column is shown in the Weibull Data Points pane. When this checkbox is cleared (default), this column is not shown. When it is selected, this column is shown. For more information, see Weibull Parameters Pane for a Non-Parametric Life Data Set.
|
|
Method
|
The method to use to estimate the failure probability for each data point in the data set. Choices are:
• Kaplan-Meier. When selected, the failure probability for a data point is estimated considering the total number of data points, the total number of units for which data was collected, the total number of failures in the group, and the total number of suspensions in the group. This method, also known as the product limit estimator, assumes that suspensions took place at the end of the interval.
• Modified Kaplan-Meier. When selected, the standard actuarial adjustment is used to adjust the equation for the Kaplan-Meier estimate to assume that suspensions took place at the midpoint of the interval. This method is commonly used for large sample sizes with data that is grouped into time intervals and includes suspensions.
|
|
Confidence type
|
The type of bounds to use for the analysis and to display on the Weibull plot. This option is available only when supported by the selected plot type. Choices, are None, Lower Confidence, Double Confidence, Upper Confidence, and Upper and Lower. For more information, see Confidence Types. When None is selected, no confidence bound is used. Consequently, % is unavailable. When any other choice is selected, this parameter is made available.
|
|
%
|
The percentage value to use to calculate the confidence bounds. This parameter is unavailable when None is selected as the confidence type. When you select any other choice, this field becomes available. Its default is 90.
|
|
Resulting data set
|
This parameter, and the ones below it, provide for saving the results from the non-parametric analysis to a parametric data set. For more information, see Resulting Data Sets.
|