BGonline.org Forums

math/stat question (OT)

Posted By: rambiz
Date: Saturday, 23 July 2011, at 8:00 p.m.

In Response To: math/stat question (OT) (Chuck Bower)

I would not weight the estimated sample probabilities but determine the variance of them and plot the point p(xi) along with the 2 points p(xi)+-var(p(xi)) against xi(which is the independent variable). I would then connect p(xi)-var(p(xi)) to p(xi)+var(p(xi)). This way you will get a range for p(xi). Obviously the range (variance) will be smaller the more measurements you have had for that specific xi.

Try to fit a curve into the "corridor" made by all the ranges. This is the way a physicist will handle noisy measurements, but me thinks, it will also work best for your case.

Messages In This Thread

• math/stat question (OT)
  Chuck Bower -- Saturday, 23 July 2011, at 5:42 p.m.
  • Clarification
    Chuck Bower -- Saturday, 23 July 2011, at 7:15 p.m.
  • math/stat question (OT)
    rambiz -- Saturday, 23 July 2011, at 8:00 p.m.
    • math/stat question (OT)
      Bob Koca -- Saturday, 23 July 2011, at 8:57 p.m.
      • math/stat question (OT)
        rambiz -- Saturday, 23 July 2011, at 9:47 p.m.
        • NOW I understand why you guys are struggling
          Chuck Bower -- Saturday, 23 July 2011, at 10:14 p.m.
          • Siamese or Persian!?
            rambiz -- Sunday, 24 July 2011, at 12:59 a.m.
          • NOW I understand why you guys are struggling
            Casper van der Tak -- Sunday, 24 July 2011, at 8:30 a.m.
          • my solution
            Chuck Bower -- Monday, 25 July 2011, at 3:40 p.m.
        • But for each value of i you have a different number of measurements
          rambiz -- Sunday, 24 July 2011, at 12:45 a.m.