Use a run chart to look for evidence of bias or other measurement system variation in your process.
You might have measurements that are close to the reference line, measurements that vary throughout the entire tolerance range, or measurements that exceed the ± 10% tolerance range. If any of the points exceed the limits, you should question the system's capability.
In these results, most of the thickness measurements fall within the ± 10% tolerance range. However, some of the measurements are lower than expected (lower than the −10% tolerance range), which may indicate a problem with the measurement system.
The gage bias indicates the difference between the mean of the measurements and the reference value. Use the p-value to determine whether your measurement system has significant bias. The null hypothesis is that bias = 0 versus the alternate hypothesis that bias ≠ 0.
To determine whether the measurement system has significant bias, compare the p-value to the significance level (denoted as α or alpha). Usually, a significance level of 0.05 works well. A significance level of 0.05 indicates a 5% risk of concluding that a system has bias when it does not.
In these results, because the p-value of 0.021 is less than the significance level of 0.05, there is sufficient evidence to conclude that bias exists. The amount of bias is statistically significant, although it seems small (-0.000015).
Use the capability indices to determine whether your measurement system is capable of measuring parts consistently and accurately.
Cg compares the tolerance with measurement variation. CgK compares the tolerance with measurement variation and bias.
In these results, Cg is 0.53 and CgK is 0.42. Both of these capability indices are less than the commonly used benchmark value of 1.33. These results indicate that the measurement system cannot measure parts consistently and accurately. You must improve the measurement system to make it more reliable.