Hi guys!
I have a problem finding the percentile (0.1,0.5,0.9) of my bell curve in excel. Wonder if someone could help out. The data looks something like this:
Size Volume (%)
100 0
200 1
300 0
Any help would be appreciated
Hi guys!
I have a problem finding the percentile (0.1,0.5,0.9) of my bell curve in excel. Wonder if someone could help out. The data looks something like this:
Size Volume (%)
100 0
200 1
300 0
Any help would be appreciated
Percentiles aren't difficult.
if you have a range of values in (say) A1:A15...
=PERCENTILE(A1:A15,.9)
gives you the 90th percentile. However, I'm a wee bit confused by the data example that you have shown. Can you upload a larger sample?
Glenn
None of us get paid for helping you... we do this for fun. So DON'T FORGET to say "Thank You" to all who have freely given some of their time to help YOU.
Temporary addition of accented to illustrate ongoing problem to the TT: L? fh?ile P?draig sona dhaoibh
Hi Glenn,
I have tried using that formula before but doesn't work.
Check out the attached file. Im expecting values in size.
Last edited by matjeng; 05-15-2014 at 03:08 PM.
It's the zeros that are your problem. Delete them to leave NOTHING and the percentile works perfectly.
I think that I may have misunderstood your request. If it's the percentile of the SIZE that you want, refer to the attached sheet.
Not that simple mate. The 0.1 should be 4.425, 0.5 = 35.927 (yes I have the answer just need to put it in excel)
What definition of "percentile" are you using to get those values? They don't seem to fit the usual definitions I'm used to for percentile, so I cannot see how you come up with those results.
Originally Posted by shg
Thanks (again) Mr Shorty. I've been puzzling over exactly what definition of percentile the OP has been using. I spend too much time playing with numbers & can't see what the OP is after...
Seems like I have to figure out the mathematics behind it first. Thank you guys for helping out.
I was thinking about this again. Have you a set of raw data that you have attempted to fit to a normal distribution (bell curve)? That's what we need to see - not the fitted data.
There are currently 1 users browsing this thread. (0 members and 1 guests)
Bookmarks