## Activity

John Noguera commented on the post, Nonparametric: Distribution-Free, Not Assumption-Free 2 years, 4 months ago

The second repeated measures decision diamond is a typo. It should be “Outliers?”

Curious if anyone is using DEA in Six Sigma Project Selection or DFSS.

This is a decision making operations research tool but curious if this has found its way into anyone’s Six Sigma toolkit. Google shows a few papers out there but wondering if it’s gaining traction. 2 years, 8 months ago

Curious if anyone has used Multi Objective Pareto Frontier as an alternative to the Desirability Function? 2 years, 9 months ago

John Noguera's profile was updated 3 years, 8 months ago

I agree – this is not simple, but the hard part will be getting familiar with the basics of the R language, and getting the data in (which is why I suggested R Studio).

P.S. If you are successful with TBATS, that will have an impact on our DiscoverSim development plans – p.m. me for details.

3 years, 8 months agoDe Livera and Hyndman developed a model for complex seasonality called TBATS:

https://robjhyndman.com/papers/ComplexSeasonality.pdf

Unfortunately (for now) this is only available in R, so I suggest:

Install Base R

Install R Studio

Install the forecast package.I hope that helps. Let me know if that works for you.

Robert, you might be interested in this article by Rob Hyndman:

https://robjhyndman.com/hyndsight/show-me-the-evidence/

Using thousands of data sets from the M3 forecast competition, he shows that the compound hybrid of Exponential Smoothing and ARIMA outperform all commercial forecast tools. Of course “all models are wrong, some are useful”…[Read more]

Forgot to mention the Ljung-Box test on the residuals is a good complement to the ACF plot. 3 years, 8 months ago

You are welcome. Be sure to check the autocorrelation (ACF) plot on the residuals to ensure that the model is adequate.

Also same assumptions as in a Regression model: residuals should be approximately normal and have equal variance. 3 years, 8 months ago

Use Excel 2016 Forecast.ETS (easiest) or Minitab’s Exponential Smoothing or ARIMA. 3 years, 8 months ago

Thanks Robert, I may well have misunderstood the question. 3 years, 8 months ago

Also I should point out that if your goal is to assess goodness-of-fit, you should use the Z-Score method as an approximation only for cases where the Anderson Darling critical values values are not available (e.g. the threshold distributions). 3 years, 8 months ago

Re Z-Score method: Sleeper credits this to Bothe. In Minitab and SigmaXL, Nonnormal Process Capability, it is called the Z-Score method.

3 years, 8 months agoNormal Z-Score = inverse cdf of the normal distribution on the cdf of the nonnormal distribution.

See Andrew Sleeper’s book: “Six Sigma Distribution Modeling” 3 years, 8 months ago

I should add that you can estimate 2 sided TI’s using the VCOV Percentile CI method using two one sided intervals: alpha upper = 0.025, percentile upper = 99.95; alpha lower = .025, percentile lower 0.05 (using your example). This will result in conservative TIs, but at least gives you an estimate.

On the other hand, Yuan’s simulation method will…[Read more]

@Alan.jacob, the problem with using a Johnson Transformation in a Tolerance Interval is that you have uncertainty in all 4 parameters. This uncertainty will not be accounted for in the 95% of the Normal Exact TI.

I recommend distribution fitting and Monte Carlo simulation to compute the TI’s, or if that is not feasible, use the VCOV percentile…[Read more]

John Noguera commented on the post, Help for Practitioners Trying to Understand ANOVA Table 4 years, 4 months ago

Thanks Keith!

Always appreciate your work.

Thanks Robert!

What software are you using to do the custom contrasts?

Also, while we are talking about post-hoc, what do you do with post-hoc on contingency tables? Adjusted Residuals seem to be the easiest (per Agresti) but curious as to what you prefer.

Finally post-hoc on Kruskal-Wallis? Dunn is popular, but…[Read more]

Thanks Robert!

What software are you using to do the custom contrasts?

Also, while we are talking about post-hoc, what do you do with post-hoc on contingency tables? Adjusted Residuals seem to be the easiest (per Agresti) but curious as to what you prefer.

Finally post-hoc on Kruskal-Wallis? Dunn is popular, but…[Read more]

Hi all,

A bit of informal research on the use of ANOVA post hoc tests in the Six Sigma community.

Tukey is well known and the most popular ANOVA post hoc test, but I was wondering if anyone uses Dunnett’s (multiple comparison to control) or Hsu’s (multiple comparison to best)?

Thanks! 4 years, 9 months ago

- Load More