# Mood Median

Six Sigma – iSixSigma Forums Old Forums General Mood Median

Viewing 9 posts - 1 through 9 (of 9 total)
• Author
Posts
• #41780

newbie
Participant

I have four non normal data sets of equal size. I have done a Mood’s Median and the p value is 0.081 which means that the data sets are not signioficantly diferent. But I see visually from the CIs generated for these individuial sets that set D and set B are “slipped”. An imaginary vertical through the D median slips past the extreme value of set B and the imaginary vertical through the B median slips before th extreme value of set D. What should be interpreted?

0
#131391

Anirvan Sen
Participant

Newbie,
The visual representation that you see echoes the p-value since it is very close to 0.05. If your confidence interval was 90% instead of 95% (alpha error: 0.10) then you can say with 90% confidence that statistically there is a difference between the samples.
But with 95% CI, you can’t statistically determine that the samples are different.
There is also another way of looking at it and that is from your data, you can only be 91.9% (1.00-0.081) Confident that your data is different.
Hope this help.
Cheers,
Anirvan

0
#131394

Whitehurst
Participant

Could you say qty for each set of data and chisquare value from mood’s median test ?
Regards, joe

0
#131399

george2
Participant

Mr Sen,
what a condiscending reply, not what i expect from a european BB at all.  This board is turning you into a yank.  Do you think the poster has absolutely no knowledge at all?  That’s not what i picked up from his post.  You notice in a previous post i mentioned the quality of CZ, german, french and Uk BB’s….not Dutch!!!!

0
#131424

Anirvan Sen
Participant

George2, You are absolutely right…It was complete uncharacteristic post from poster and I thought of this as another round of Monty Python’s/bands story. That’s why such a reply.
But I guess ppl are sitting by the fence and watching…:-(((
Meanwhile, did not catch on your postings on European BBs…Shall thou enlighten me….:-)
Cheers,
A.

0
#131441

newbie
Participant

Sample size:10 each
Chi square: 6.72

0
#131443

george2
Participant

Mr sen,
My prvious post was aimed at some American BB (i think Darth, but not sure).  basically she was referring to the job section on here and asking why European countries were looking for American BB’s.  It’s the typical insular attitude you get from a lot on here where USA is the centre of the universe and the http://WWW.  They can’t seem to understand that there is intelligent life outside their shores.  My comment was that Euro BB’s that i have contact with from CZ, France, Germant and UK deliver more project value than their american counterparts year on year.  When we roll out a global project we always use a Euro BB not American.  Another notable is that salary especially in UK and Germany for BB’s is rising above the american levels.
G2

0
#131448

Anirvan Sen
Participant

G2, You make me sound like a 55 yr-old with the Mr. Sen..The name is Anirvan.
Merry X-Mas :-)
Cheers,
Anirvan

0
#131453

Whitehurst
Participant

the values seems confirm what you said and the slip you obeserve could be due to the fact that data sets come from similar population, but from different side of distribution. If could explane better which is the scope of your test and raw data, maybe we can understand which are some further test you can run to confirm your hypothesis, because having data set (samples , I think) of equal size, it is possible  to run also other test that could help.
regards, joe

0
Viewing 9 posts - 1 through 9 (of 9 total)

The forum ‘General’ is closed to new topics and replies.