What Distribution Best Fits a Single Variable Data Set
on January 01, 2012
I have a single variable data set in Excel. How do I determine what distribution best fits the data?
SigmaXL Version 6 includes powerful tools to deal with nonnormal data.
Specific to the question, we have a Distribution Fitting option that allows you to do any of the following:
· Specify a distribution or transformation:
- Based on theory or process knowledge
- Supported Distributions: Normal, Half-Normal, Lognormal (2 & 3 parameter), Exponential (1 & 2 parameter), Weibull (2 & 3 parameter), Beta (2 & 4 parameter), Gamma (2 & 3 parameter), Logistic, Loglogistic (2 & 3 parameter), Largest Extreme Value, Smallest Extreme Value
- Supported Transformations: Box-Cox Power, Johnson Family
- Note that we use Anderson Darling (AD) Goodness of Fit rather than Chi-Square. AD is a more powerful test than Chi-Square.
· Automatic Best Fit:
- All of the above transformations and distributions (that are valid for the data) are applied and SigmaXL selects the best based on the AD p-value estimate.
· All Distributions:
- All valid distributions and transformations reported with histograms, curve fit and probability plots sorted by AD p-value
· Process Capability Indices and Control Charts are also available.
The SigmaXL Workbook gives more information on this topic.
Statistical details are given in the appendix of the SigmaXL Workbook.
|Was this helpful? Yes No Print/Save Pdf|