Hey there! Sign in to join this conversationNew here? Join for free
x Turn on thread page Beta
    • Thread Starter
    Offline

    1
    ReputationRep:
    hey all ~

    needing your help

    say i have 90 in a sample and i needed to find the 10th percentile.

    np=90*0.1
    np=9.

    does this mean i have to take the 9th number in the sample? (after sorting it out, smallest to largest)

    thanks guys - please help me cos im so confused: will tell more once someone has answered...(i have to ask this question first, just to make sure im doing the right thing lol)
    Offline

    1
    ReputationRep:
    Yup, if you want the 10th percentile of 90, you take the 9th number in the sample once ordered.
    • Thread Starter
    Offline

    1
    ReputationRep:
    and i am guessing that the same works for the 50th percent (median)....

    well. if the sample size was 90 again and using the same method i needed to find the median, i would do np=90*0.5, which is 45.
    Therefore i would read off the 45th number in the sample, once its been sorted ascendingly?
    • Thread Starter
    Offline

    1
    ReputationRep:
    ^which isn't right, because the middle number would actually be the 45.5th number? which means that i should be taking the average of the 45th and the 46th number.

    which way should i use?!
    Offline

    1
    ReputationRep:
    45th number, I believe.
    • Thread Starter
    Offline

    1
    ReputationRep:
    yeah thats what i initially thought too....but thats the wrong answer

    am working it out by hand and by a computer stats package and the correct answer is the average between the 45th and 46th number to be the median.

    thats why im so confused :'(
    Offline

    1
    ReputationRep:
    Well in my S1 notes, I have written down that the median of the sample is 50th percentile, which would be the 45th number.

    Maybe someone else could clarify.
    • Thread Starter
    Offline

    1
    ReputationRep:
    thanks for your help so far.

    thats what i originally thought too...but doing it the basic way again (sorting out the numbers the crossing off each one on either end until they meet in the middle), there was no middle number cos it was an even sample: i had to average the 45th and 46th numbers.
    Offline

    1
    ReputationRep:
    So do the answers given equal to the average of the n/2 and (n + 1)/2 numbers?
    • Thread Starter
    Offline

    1
    ReputationRep:
    for the median it was the average of the (n/2 + (n+1)/2), yes
    Offline

    1
    ReputationRep:
    I think we can assume that the median percentile is the (n + 1)/2 th term then.
    • Thread Starter
    Offline

    1
    ReputationRep:
    yep, but then its stupid cos on the notes we were given it doesn't say that im so going to take this up with the person who gave me the notes!!!!!!

    thanks matt2k, for reassuring me that i wasn't going insane and that i CAN work out a silly S1 level question!!!!!!!
    Offline

    1
    ReputationRep:
    Just out of interest, which notes are they? Where did you get them from?

    S1 is boring.
    Offline

    2
    ReputationRep:
    For the k'th percentile, start at 1 and go k% of the way towards 90.

    You end up at the 1 + 0.01k*89 = 1 + 0.89k th entry.

    Examples:
    k = 50 (median): 45.5th entry [ = (1/2)(45th entry + 46th entry) ]
    k = 10 (10th percentile): 9.9th entry [ = (1/10)(9th entry + 9*10th entry) ]
    Offline

    0
    ReputationRep:
    (Original post by Jonny W)
    For the k'th percentile, start at 1 and go k% of the way towards 90.

    You end up at the 1 + 0.01k*89 = 1 + 0.89k th entry.

    Examples:
    k = 50 (median): 45.5th entry [ = (1/2)(45th entry + 46th entry) ]
    k = 10 (10th percentile): 9.9th entry [ = (1/10)(9th entry + 9*10th entry) ]
    thats the way to do it i believe

    statistics is so convoluted....
    • Thread Starter
    Offline

    1
    ReputationRep:
    you lot are LEGENDS! reps for all of you! (one at a time though!)

    so for the 90th percentile, using symmetry, it should be the 80.1th entry?

    am wondering how to work it out though? still can't get my head quite around it.

    k = 90
    (9/10)(81st entry + ...
    i need to make 801 but i don't know how to...
    Offline

    2
    ReputationRep:
    (Original post by posh_git)
    you lot are LEGENDS! reps for all of you! (one at a time though!)

    so for the 90th percentile, using symmetry, it should be the 80.1th entry?

    am wondering how to work it out though? still can't get my head quite around it.

    k = 90
    (9/10)(81st entry + ...
    i need to make 801 but i don't know how to...
    90th percentile
    = 81.1th entry . . . . . same distance from 90 as 9.9 is from 1
    = (1/10)[9(81th entry) + (82th entry)]
    • Thread Starter
    Offline

    1
    ReputationRep:
    oh oh oh! i totally get it now!!!!!!!!!

    thanks a lot people!!!!!!
 
 
 
Reply
Submit reply
Turn on thread page Beta
Updated: April 10, 2006
Poll
Do you agree with the proposed ban on plastic straws and cotton buds?
Useful resources

Make your revision easier

Maths

Maths Forum posting guidelines

Not sure where to post? Read the updated guidelines here

Equations

How to use LaTex

Writing equations the easy way

Student revising

Study habits of A* students

Top tips from students who have already aced their exams

Study Planner

Create your own Study Planner

Never miss a deadline again

Polling station sign

Thinking about a maths degree?

Chat with other maths applicants

Can you help? Study help unanswered threads

Groups associated with this forum:

View associated groups

The Student Room, Get Revising and Marked by Teachers are trading names of The Student Room Group Ltd.

Register Number: 04666380 (England and Wales), VAT No. 806 8067 22 Registered Office: International House, Queens Road, Brighton, BN1 3XE

Write a reply...
Reply
Hide
Reputation gems: You get these gems as you gain rep from other members for making good contributions and giving helpful advice.