Seppe
☆    

Belgium,
2018-03-19 11:58
(919 d 12:39 ago)

Posting: # 18574
Views: 2,364
 

 95% CI of CV [General Sta­tis­tics]

Hi

I have a problem with calculating the 95%CI of the CV
I have an example but i don't now how they get the result of the 95%CI.

Example:

1. 3,8
2. 3,9
3. 3,9
4. 3,8
5. 4,1
6. 4,0
7. 3,4
8. 3,6
9. 3,8
10.3,7

Mean= 3,8
SD= 0,2
CV= 5,3
95%CI (3,6;9,7)

How do you get the interval of 3,6;9,7 from the CV?
The only thing I know that it's not a normal distribution

Greetz
mittyri
★★  

Russia,
2018-03-21 11:35
(917 d 13:02 ago)

@ Seppe
Posting: # 18576
Views: 1,810
 

 95% CI of CV

Hi Seppe,

cannot get exactly the same (assuming normal distribution)
confint.cv <- function(x,alpha=.05, method="modmckay"){
  # Calculate the confidence interval of the cv of the vector x
  # Author: Kevin Wright
  # See: Vangel, Mark.  Confidence Intervals for a Normal Coefficient
  # of Variation. American Statistician, Vol 15, No1, p. 21--26.
  # x <- c(326,302,307,299,329)
  # confint.cv(x,.05,"modmckay")
 
  x <- na.omit(x)
  v <- length(x)-1
  mu <- mean(x)
  sigma <- sqrt(var(x))
  k <- sigma/mu
  # CV > .33 may give poor results, so warn the user
  if(k>.33) warning("Confidence interval may be very approximate.")
 
  method <- casefold(method) # In case we see "McKay"
 
  if(method=="mckay"){
    # McKay method.  See equation 15.
    t1 <- qchisq(1-alpha/2,v)/v
    t2 <- qchisq(alpha/2,v)/v
    u1 <- v*t1
    u2 <- v*t2
    lower <- k/sqrt(( u1/(v+1) -1)*k*k + u1/v)
    upper <- k/sqrt(( u2/(v+1) -1)*k*k + u2/v)
  } else if (method=="naive"){
    # Naive method.  See equation 17.
    t1 <- qchisq(1-alpha/2,v)/v
    t2 <- qchisq(alpha/2,v)/v
    lower <- k/sqrt(t1)
    upper <- k/sqrt(t2)
  } else {
    # Modified McKay method. See equation 16.
    method="modmckay"
    u1 <- qchisq(1-alpha/2,v)
    u2 <- qchisq(alpha/2,v)
    lower <- k/sqrt(( (u1+2)/(v+1) -1)*k*k + u1/v)
    upper <- k/sqrt(( (u2+2)/(v+1) -1)*k*k + u2/v)
  }
  ci <- cbind.data.frame(method = method, lower=lower,upper=upper, CV= k, alpha=alpha)
  return(ci)
}
x=c(3.8,3.9,3.9,3.8,4.1,4.0,3.4,3.6,3.8,3.7)
results <- rbind(confint.cv(x), confint.cv(x, method = "mckay"), confint.cv(x, method = "naive"))
print(results)


gives
    method      lower      upper         CV alpha
1 modmckay 0.03617573 0.09632067 0.05263158  0.05
2    mckay 0.03618047 0.09641016 0.05263158  0.05
3    naive 0.03620185 0.09608475 0.05263158  0.05

Kind regards,
Mittyri
Activity
 Admin contact
21,072 posts in 4,394 threads, 1,468 registered users;
online 3 (0 registered, 3 guests [including 1 identified bots]).
Forum time: Thursday 01:37 CEST (Europe/Vienna)

Enlightenment is man’s emergence from his self-imposed nonage
for which he himself was responsible.
Nonage is the inability to use one’s own intellect
without the direction of another.    Immanuel Kant

The Bioequivalence and Bioavailability Forum is hosted by
BEBAC Ing. Helmut Schütz
HTML5