statistics
Six Sigma – iSixSigma › Forums › Old Forums › General › statistics
- This topic has 6 replies, 7 voices, and was last updated 12 years, 8 months ago by
Stevo.
-
AuthorPosts
-
October 25, 2009 at 3:00 pm #52830
How can I analyze my data. the data is not normally distributed even I tried some transformation methods that suggested for non-normal data??
0October 25, 2009 at 3:03 pm #186356
Ken FeldmanParticipant@DarthInclude @Darth in your post and this person will
be notified via email.You have provided no useful information with your post. Provide a few more details and what you tried already and possibly you can receive some help.
0October 25, 2009 at 6:38 pm #186359Transform the thing and then do a 35,000′ management report. Don’t
worry if it makes any sense at all.Tell them you learned it from Forrest.0October 25, 2009 at 11:56 pm #186360The easiest way to deal with problems of this type is to use the Finagle Phudge Transform Factor – take the data, multiply each data point by 0, and add a number from a normal random number generator to the result. The data will now be normally distributed and you can apply any test requiring normally distributed data.
0October 26, 2009 at 2:02 am #186362
Chuck WetherholdParticipant@Chuck-WetherholdInclude @Chuck-Wetherhold in your post and this person will
be notified via email.The Finagle Phudge Transform Factor has worked reasonably well for us in the past. I would think that should be your first choice of a transformation method.
0October 26, 2009 at 7:09 am #186366Look up the meaning of analyze:
http://dictionary.reference.com/browse/analyze
Good luck.0October 26, 2009 at 12:43 pm #186367Pari By knowing that your data is Non normal you have already analyzed your data. That being said, – want are you figure out? Most of the stat package tools are sensitive enough that the normality of the data is not as critical as a lot of people would like to think. Stevo
0 -
AuthorPosts
The forum ‘General’ is closed to new topics and replies.