Weibull Analysis in Excel with QI Macros
Its easy to do a Weibull analysis with the QI Macros SPC Software for Excel.
What is a Histogram?
Histograms show the spread, or dispersion, of variable data. The customer's upper specification (USL) and lower specification limits (LSL) determine how well the process delivers on customer requirements.
What is cool about the QI Macros Weibull Analysis?
Not all data is normally distributed (i.e., bell-shaped). Weibull analysis is especially suited to failure rates (e.g., how long does a TV, PC or whatever operate before failing).
Just select your data and select Histogram Weibull from the QI Macros menu. The macro will prompt for spec limits, create a histogram and calculate Weibull and process capability metrics for you. Here's an example of Ball Bearing failure rates. Failure rates peak at 81.57:
Weibull Analysis
The Weibull distribution can approximate many other distributions: normal, exponential and so on.
- Shape
- The Shape parameter gives the pattern of the curve.
- Shape < 1 is a decreasing failure rate (a.k.a. infant mortality)
- Shape > 1 is an increasing failure rate (wear-out failures)
- Shape = 1 yields exponential distribution (constant failure rate)
- Shape = 3.6 approximates the normal distribution
- Scale
- The Scale parameter relates to the peak of the curve.
There are several methods for estimating the scale and shape parameters:
- probability plotting
- Least squares (rank regression) - QI Macros uses this method
- maximum likelihood estimation (MLE).
