Gage Linearity Results
Gage Repeatability and Reproducibility
Click the OK button in the Gage Linearity dialog box to display the Gage Linearity Results dialog box, which contains one tab: Results.
- Summary box
- The Summary box is located at the top of the Results dialog box. It displays various types of information needed for a quick review of your analysis. This information can also be displayed in spreadsheet and graph formats using the options on the Results tab.
- Tables
- The following options are displayed in the Tables group box:
- All tables
- Click this button to produce the tables of gage linearity, bias, regression statistics, regression & ANOVA, and bias significance in a single spreadsheet output. You can also produce these individual tables in separate spreadsheets using the rest of the options described below.
- Linearity & bias
- This option is available only if you provided a value for the Process variation option in the Gage Linearity dialog box. Click this button to generate a spreadsheet containing the estimated values of linearity and bias. Bias measures the difference between observed (measured) and reference (master) values while linearity estimates how accurate a measurement process is over an expected range
- Regression statistics & table
- Click this button to create a number of statistics for the regression model including R2 and R2 adjusted. These quantities provide estimates of how well the regression fits the data.
- ANOVA table
- Click this button to display a spreadsheet containing the ANOVA table. You can use the contents of this spreadsheet for identifying sources of variability in your regression model.
- Bias significance table
- Click this button to generate a bias significance table in spreadsheet format. For each part, the regression table contains the master (reference) readings, average of the measurements, estimates of bias and the p-values. The bias measures deviation of the sample average (per part) from the master value. Note that you can select the method for estimating the standard deviation (used for calculating the p-values) using either the sample range method or the standard formula based on sample standard deviation (see the description of the options in the Method for calculating the standard deviation group box below)
- Graphs
- The following options are displayed in the Graphs group box:
- Summary: Multiple graphs
- Click this button to generate a line plot of the linear regression. This graph will also contain the histogram plot for the percentage of linearity and bias (provided that an estimate of process variation is provided). Note that you can generate these individual plots in separate graphs using the options described below.
- Bias v/s master
- Click this button to generate the graph of the linear regression.
- Percent of process of variation
- This option is available only if you provided a value for the Process variation option in the Gage Linearity dialog box. Click this button to generate the histogram plot for the percentage of linearity and bias.
- Method for calculating standard deviation
- Select one of the following options to specify the method to be used for calculating the standard deviation (used in calculating the p-values).
- Sample ranges
- Select this option button to base the estimate of the standard deviation on sample range.
- Sample standard deviation
- Select this option button to base the estimate of the standard deviation on sample standard deviation.
- Summary
- Click this button to produce the plot of linearity and bias. This multiple graph contains the plot of the linear regression as well as the histogram of the percentage of linearity and bias (for a given value of process variation).
- Cancel
- Click this button to close the Results dialog box and return to the Gage Linearity dialog box.
- Options
- Click the Options button to display the Options menu.
- By Group
- Click this button to display the By Group dialog box, which is used to generate output for each unique level of a By variable or unique combination of multiple By variables at the individual results level.
Copyright © 2021. Cloud Software Group, Inc. All Rights Reserved.