iSixSigma

Need some help with a question that has me stumped

Six Sigma – iSixSigma Forums Old Forums General Need some help with a question that has me stumped

Viewing 6 posts - 1 through 6 (of 6 total)
  • Author
    Posts
  • #51726

    William2
    Member

    I have this question that has me completely stumped. I am in no way looking for an answer just some guidance on how to approach the question. I know it has to be done using minitab.Here is what I have:
    One variable or factorΒ we will call X1 is varied in a one factor experimentΒ and results in an X2. I am given an equation X1 = a/X2 + b noting that X1 and X2 follow the relationship defined by this equation. I am being asked ot compute a and b.
    If I perform a simple linear regresssion analysis I get X2 = # – (#*X1). If I perform a linear fitting line plot I get the same format.
    I am lost on how to try to find a & b in Minitab.
    Β 
    Any guidance would be appreciated
    Β 

    0
    #180152

    BC
    Participant

    I assume X1 is the “y” and X2 is the “x”
    In that case, let y = 1/X2,
    then y = X1/a – b/a.
    Use regression in Minitab to solveΒ y = m*X1 + c where m = 1/a and c = -b/a.
    Forgive me if I made a mistake in algebra.Β  I think you can figure out what I’m showing.
    BC

    0
    #180155

    William2
    Member

    I am afraid the sustitution I made may have made this unclear…
    Let me use different substitutions to try to make it clearer..I am varying p = pressure to get a volume = v. p and v follow this relationship of p = a/v +b. I am gven a set of runs and I amΒ being asked to compute a and b using mintab.

    0
    #180156

    Boyles Law
    Participant

    P*V=C
    Pressure * Volume=Constant
    Boyles Law This may help you get there

    0
    #180162

    KRISHNAN
    Member

    i need more informations about six sigma concept as your concern

    0
    #180192

    Remi
    Participant

    Hai William2;
    General: With Regression you solve Y= c0 + c1*X where X is independent and Y is dependent (either Regression -> Regression or Regression -> Fitted Line Plot).
    In your case p is independent and v is dependent and the relation you try to fnd will be looking like: v = a/(p-b) or v = a*1/p – a/b.
    Make a column of 1/p (carefull with the 0’s). And analyse Y=v as function of X=1/p.
    If your relation was not p=a/v+b but a*v+b you would have a slightly different formula and X=p.
    Hope this helps.
    Remi

    0
Viewing 6 posts - 1 through 6 (of 6 total)

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