Calculating Process Statistics

The specification and control limits are obtained from a specification that is linked to the most recent sample of an entity. The process statistics are calculated from a range of samples, which are filtered as follows:

• The set of filter_by_* columns in the Characteristic table (filter_by_item_id, filter_by_wo_id, filter_by_oper_id, etc.) that are true for the characteristic are used to restrict the samples. Samples having same value as the most recent sample in the column are restricted.

• The sample time is filtered using the cut-off time configured in the system attribute. This limits the number of samples.

• The number of samples is filtered using a value configured in the system attribute. This limits the number of samples.

The most recent sample record for a characteristic is represented as the starting sample. A range is obtained from the most recent sample record to the oldest sample record based on the values configured in the system attributes. The values for some of the process statistic attributes depend on the default chart type configured characteristic or the override of the characteristic's default chart for a particular QM specification.

The statistical values are as follows:

Actual Percent Out of Specification Limits (ActPercentOutofSL)

The ratio of the number of individual results that are outside of specification limits to the total number of individual results.

Process Capability (Cp)

The ratio of the difference between the upper and lower specification limits and six times the estimated standard deviation based on sample variability. The difference between it and the target value is compared to three times the estimated standard deviation if there is only one specification limit. This is only calculated for variable-type data.

Process Capability Index (CpK)

The ratio of the difference between the upper and lower specification limits and six times the estimated standard deviation based on sample variability. It considers a mean that is not centered between the specification limits. This is only calculated for variable-type data.

Average (Mean)

Specifies the average of the individual results for variables. For attributes, the average of the values are plotted on the default chart.

Process Performance (Pp)

The ratio of the difference between the upper and lower specification limits and six times the estimated standard deviation based on the entire measured population. This is only calculated for variable-type data.

Process Performance Index (PpK)

The ratio of the difference between the upper and lower specification limits and six times the estimated standard deviation based on the entire measured population. It considers a mean that is not centered between the specification limits. This is only calculated for variable-type data.

Range

Specifies the difference between the highest data point and the lowest data point. This is calculated as the difference between the maximum individual reading and the minimum individual reading.

Average Range of Subgroups (RBar)

Specifies the average range of values from a set of samples. This is only calculated for variable-type data.

Number of Result Rows (Rows)

Specifies the total number of individual results (for variables), or the number of subgroups (for attributes) involved in calculating the process statistics.

Estimated Standard Deviation (EstSigma)

Specifies the statistical measure of the spread or the variability within samples. The configuration of the characteristic determines if it is based on Rbar or calculated from the data. This value is used for calculating Cp and Cpk. This is only calculated for variable-type data.

Standard Deviation (StdDev)

Specifies the statistical measure of the spread or the variability of the individual results. This value is used for calculating Pp and Ppk.

Total Number of Samples (Total)

Specifies the total number of samples for a characteristic involved in calculating the process statistics. If default chart type of the characteristic is set to Individual and Moving Range, Moving Average and Range, or Moving Average and Sigma, the total is calculated as follows:

Individual and Moving Range Chart

The total number of samples is equal to the total number of individual readings (result data) from all the samples used to calculate process statistics. Each individual reading from a sample is treated separately.

Moving Average and Range Chart and Moving Average and Sigma Chart

The total number of samples is calculated as the difference of the total number of individual readings from all the samples and the moving average span configured for a characteristic. An individual sample is added.

Minimum Individual Reading (Min)

Specifies the minimum individual reading among the set of sample measurements.

Maximum Individual Reading (Max)

Specifies the maximum individual reading among the set of sample measurements.

Lower Specification Limit (LSL)

Specifies the lower specification limit for a specification that is obtained from the most recent sample.

Upper Specification Limit (USL)

Specifies the upper specification limit for a specification that is obtained from the most recent sample.