Loading ...
Sorry, an error occurred while loading the content.

[ai-geostats] 95% CRs for Variance Estimates

Expand Messages
  • JW
    Hello Readers, Last week Behrang Kushavand brought to my attention that the lower and upper limits of symmetric 95% confidence ranges for variance estimates
    Message 1 of 1 , Mar 5, 2006
    • 0 Attachment
      Hello Readers,
       
      Last week Behrang Kushavand brought to my attention that the lower and upper limits of symmetric 95% confidence ranges for variance estimates are incorrect and gave the correct lower and upper limits. I checked Behrang's calculations and informed him that his are correct and mine were wrong. I have transmitted the revised file to our Webmaster who has already posted it on ai-geostats.org under Documents. My vote of confidence to Behrang and Gregoire!
       
      Late last year the formula for the variance of a set of measured values determined in samples with variable weights was also discussed on ai-geostats. It is simple to prove that the denominator in this formula is no longer a positive integer but becomes a positive irrational. In fact, a posted Excel template (see Variances_variable_weights under Documents) shows that positive irrationals converge on positive integers when variable weights converge on constant weights. Does anyone disagree with the corollary of converging weights? Please let me know why!
       
      Thanks and regards,
      Jan W Merks
    Your message has been successfully submitted and would be delivered to recipients shortly.