Capability Analysis - Between/Within

Graphs - Histogram of Measurements

  

The histogram of measurements consists of the following:

·    B/W and overall curves superimposed on the histogram. The B/W (between/within) and overall curves are normal density functions using the process mean and different variances. The B/W curve uses the between/within variance, while the overall curve uses the overall sample variance.

Assess the normality of the data by comparing the curve to the bars. A normal distribution is symmetric and bell shaped. With small sample sizes it may be difficult to assess normality using a histogram.

Examine the curves to see how closely they follow each other. A substantial difference between the B/W curve and the overall curve may indicate that the process is out of control.

·    Target, and lower and upper specification limits (LSL and USL) represented by vertical dashed lines on the histogram. Use these lines to assess whether measurements are centered on target and inside the specification limits.

Example Output

image\capbw_1n.gif

Interpretation

For the coating data:

·    The coating data appears approximately normal.

·    The B/W and overall curves are closely aligned.

·    The process is approximately centered on target and the measurements are located within the specification interval.