Determining If There Really is a Shift in Mean
Six Sigma – iSixSigma › Forums › Old Forums › General › Determining If There Really is a Shift in Mean
 This topic has 3 replies, 4 voices, and was last updated 18 years, 6 months ago by Robert Butler.

AuthorPosts

March 4, 2003 at 9:27 pm #31627
dizzydomParticipant@dizzydom Include @dizzydom in your post and this person will
be notified via email.Hello all,I am trying to determine if the mean cycle time on a
product line has truly shifted for the worst when an
improvment methodology was abandoned. During the
improvement process, 37 daily avg. cycle times were
collected (xbar equals 5.34 days). After the methodology
was abandoned 33 daily avg. cycle times were collected
(xbar equals 6.37days). What statistic can I apply to
show that there truly was a change in the process mean?0March 5, 2003 at 1:41 am #83516
jediblackbeltParticipant@jediblackbelt Include @jediblackbelt in your post and this person will
be notified via email.Take your data sets and check them for normality and then equal variances. If they pass then use ANOVA. Otherwise you could just do a simple onetailed ttest to see if they pass or even ANOM. There are a lot of different tests you can use. The bigger question is why did the system get abandoned? You shouldn’t even be checking for a change for the worse you should be asking those in charge of the process why they allowed it to drift back. Look at the controls that were put on the better process and see what needs improved to make the input controls better and then monitor the output. Just an opinion but I would look to ask why the process changed versus proving statistically if the changes are valix.
0March 13, 2003 at 1:06 pm #83796I agree with jediblackbelt about what should be the focus of your investigation. If you want to validate that the observed difference is statistically different before “stirring up” things. You can use the Two Sample ttest, “before” and “after” and not have to assume unequal variances.
0March 13, 2003 at 2:04 pm #83799
Robert ButlerParticipant@rbutler Include @rbutler in your post and this person will
be notified via email.If it is really a matter of comparing the averages of two sample populations then a two sample ttest with unequal variances and unequal sample sizes would be the statistical tool of choice (Minitab gives you these options. If you don’t have Minitab then pp.299304 of Statistical Theory and Methodology 2nd Edition by Brownlee has the details for manual computation). It’s worth checking for data normality but you should remember that the ttest, like ANOVA, is very robust to nonnormality.
What concerns me is that the wording of the original post suggests that the situation is not that of comparing populations but comparing populations of averages. The sentence “33 daily avg. cycle times were collected (xbar equals 6.37days)” suggests that 33 averages were gathered and the average of these averages was then computed. If this is the case then the way to check for process changes would be to go back to the averages, note their associated ranges and plot Xbar R charts for before and after and compare these to see if there has been a change in process.0 
AuthorPosts
The forum ‘General’ is closed to new topics and replies.