Which StDev is bigger?CPK or PPK
Six Sigma – iSixSigma › Forums › Old Forums › General › Which StDev is bigger?CPK or PPK
 This topic has 8 replies, 8 voices, and was last updated 13 years, 6 months ago by Craig.

AuthorPosts

March 25, 2009 at 4:09 am #52096
HuangyanweiParticipant@Huangyanwei Include @Huangyanwei in your post and this person will
be notified via email.Hello , I need your help.
In Minitab£¬when calculate Cpk or PPK, use related StDev(Within or Overall).
My qestion, which StDev is bigger?always PPK StDev?I think not,because I often find Cpk SteDev is always bigger than PPk SteDev?
Pls give some explanation.
Thanks.0March 25, 2009 at 12:47 pm #182720
Gary ConeParticipant@garyacone Include @garyacone in your post and this person will
be notified via email.The standard deviation for Ppk should always be greater or equal to
the standard deviation for Cpk.When it’s not, it’s because some estimation has been made for the
standard deviation associated with Cpk. The estimation is usually
when you have made subgroups size = 1 and moving range is used.0March 25, 2009 at 2:05 pm #182722if using mintab to form random date, and calculate cpk,ppk, you can always find Steve for cpk is bigger than ppk, even subgoup is 5 or more.
why?0March 25, 2009 at 5:15 pm #182739yu yu,
I wouldn’t bother to understand what the numbers represent either. Just keep generating those random number sets and running the capability numbers. It doesn’t really matter what they mean just so you can get Minitab to do the analysis. That is what is important.
Your other option is to turn off your computer and understand what the numbers represent then you will know that what Gary Cone said is true. Then figure out what you are doing wrong.
When you figure this out then you can figure out why Cpk will only be equal to or greater than Cp. Pure conjecture, if I were a betting person I would bet we will hear from you again in about a year.0March 25, 2009 at 9:44 pm #182754Anon,
If you are going to be snarky, at least get your facts straight. Cpk can never be greater than Cp – only less than or equal to.0March 25, 2009 at 10:01 pm #182755Zoltan,
That would be correct but now we will see them back in less than year.0March 25, 2009 at 10:49 pm #182757
Bower ChielParticipant@BowerChiel Include @BowerChiel in your post and this person will
be notified via email.Hi Anon, GarySurely any calculation of Cp, Cpk, Pp, Ppk etc.is going to involve estimation of some sort!Best WishesBower Chiel
0March 26, 2009 at 12:04 am #182760True, but mR is a poor one, just better than nothing.
0March 26, 2009 at 10:42 am #182767The original poster should study the formulas to answer this question.
Short term sigma will vary based on the choice of subgroup size. Also, since the range is used for estimating sigma, only 2 data points in each subgroup are used for the estimation.
Long term sigma will be the same for a given data set as it does not involve subgroup size, RBar calcs, d2 factors, and it uses all the data.
Try crunching the data below and calc cpk and ppk using subroup size 3 and then 5. Try using the XBar/S approach for subgroup size 9.
Random80,2.580.271741381.912070679.170107676.886771779.310134379.819943383.339142481.014008283.34329478.359133582.656855981.297196277.433550478.812705781.170546279.860023482.013038380.77011379.728586180.323561377.460475576.497974380.972126777.33562781.302931279.484176878.805654182.325127177.693351482.585998580.306328976.591258975.872435176.154374282.124018576.382226878.756533879.931679284.756554278.732030479.972229779.138389578.087130576.729063981.147533479.568373379.960751479.081382578.064946481.521382476.789109277.711547680.753827278.03083483.316858179.210368577.688889780.906081378.558076278.25072777.261488581.659291482.934349481.55761177.813372276.828578875.420678778.849201778.137084880.235490380.699264481.899598581.554661580.445139775.302697979.874024380.506680682.773424174.091067183.713889784.288995880.571852280.384882483.648579381.308760576.463769678.918963881.687990980.054462580.75560790 
AuthorPosts
The forum ‘General’ is closed to new topics and replies.