Bioequivalence and Bioavailability Forum

R code quest [Regulatives / Guidelines]

posted by d_labes  – Berlin, Germany, 2010-02-25 17:34 (5554 d 17:19 ago) – Posting: # 4819
Views: 5,137

Dear ElMaestro,

❝ Lund <- function (Linmo, alpha, Verbose)

❝ {

❝ ...

❝ q=qr(model.matrix(Linmo))$rank

❝ n=length(residuals(Linmo))

❝ ...

why did you use this here?
Is there any hidden secret behind?

I would do:
   summary(Linmo)$df[2]  # error degrees of freedom

   ...
   t <- qt((1-alpha/n/2),df-1)   
   isr2 <- df*(t^2)/(t^2+df-1) 
   ... 

Complete thread:

• Canada: Draft Guidances published Helmut 2010-01-28 00:52 [Regulatives / Guidelines] 
  • Outlier earlybird 2010-02-09 08:35
    • Outlier (tests?) Helmut 2010-02-09 14:55
      • Outlier (tests?) earlybird 2010-02-09 16:45
        • Outlier (tests?) Helmut 2010-02-09 17:05
          • Outlier (tests?) earlybird 2010-02-09 17:18
          • Outlier "im Quadrat" d_labes 2010-02-10 13:51
            • Hotelling's T² Helmut 2010-02-11 17:56
      • Lund! d_labes 2010-02-10 13:36
        • Lund! Helmut 2010-02-12 20:04
          • intercept ElMaestro 2010-02-12 20:29
            • intercept Helmut 2010-02-13 00:03
              • intercept ElMaestro 2010-02-13 01:04
          • Lund's critical values, technically d_labes 2010-02-22 12:52
            • R code ElMaestro 2010-02-25 14:22
              • R code questd_labes 2010-02-25 16:34
                • R code quest ElMaestro 2010-02-25 17:06