Hi Paul,
I'm not up to speed with correlations & curves, but:
I don't see why the 13 week rolling average doesn't smooth out the low
volume bumps- (unless you're averaging averages).  If you divide total good
pieces over 13 weeks by total pieces produced over 13 weeks, the "1 out of
2" period  shouldn't "skew" up the average.

Good Luck,
Mark Hargreaves


        -----Original Message-----
        From:   Paul Signorelli [SMTP:[log in to unmask]]
        Sent:   Friday, December 27, 2002 1:09 PM
        To:     [log in to unmask]
        Subject:        [TN] Normalizing Yield Percentages ?

        Does anyone have a standard way to normalize yield percentage charts
for
        wildly varying production volumes ?
        My yield percentage charts show 50% yield when there is 1 out of 2
        failures or 50 out of 100 failures.
        The 50% Yield with 1 out of 2 usually happens during a Christmas
week
        when there is no production, only rework.
        I have tried to normalize the charts by using a constant denominator
        based on the nominal volume.
        I use 13 week rolling averages but they are messed up by the low
volume
        yield results.
        This low volume percentage reporting can cause incorrect corrective
        actions.
        Does anyone know of a standard way to normalize the data ?
        Cronbach's Alpha,
        Split-Half Reliability (Spearman-Brown Coefficient),
        Attenuation correction,
        Pair Wise Deletion of Missing Data,
        Partial correlation,
        Parzen Window,
        Pearson Curves,
        Johnson Curves ?

        Paul Signorelli


---------------------------------------------------
Technet Mail List provided as a free service by IPC using LISTSERV 1.8e
To unsubscribe, send a message to [log in to unmask] with following text in
the BODY (NOT the subject field): SIGNOFF Technet
To temporarily halt or (re-start) delivery of Technet send e-mail to [log in to unmask]: SET Technet NOMAIL or (MAIL)
To receive ONE mailing per day of all the posts: send e-mail to [log in to unmask]: SET Technet Digest
Search the archives of previous posts at: http://listserv.ipc.org/archives
Please visit IPC web site http://www.ipc.org/html/forum.htm for additional
information, or contact Keach Sasamori at [log in to unmask] or 847-509-9700 ext.5315
-----------------------------------------------------