Turn on thread page Beta
    Offline

    1
    ReputationRep:
    (Original post by Saiyan)
    do you have an email address hollayJA/confused??

    yeh, thanx alot saiyan, rep coming your way.

    email- [email protected]
    Offline

    0
    ReputationRep:
    (Original post by confused?)
    yeh, thanx alot saiyan, rep coming your way.

    email- [email protected]
    whats a rep? - Anyway.. I've sent it
    • Thread Starter
    Offline

    1
    ReputationRep:
    Hey guys!

    Jan 2005. im working my way through it. Although i'd be glad if someone could exaplin number four to me.

    Question 4
    how comes the alternative hypothesis being tested is <? i wrote greater than or equal to...looks like thire testing aginst his veiws, i dunno? is this sumthing we always do?
    and also i approximated it to the poisson, as np>5, and nq<5...that didnt seem to be accepted in the mark scheme either.
    and then, in the binomial way, why are we testing less than or equal to 9, must be beacuse of the hypothesis right?
    Offline

    0
    ReputationRep:
    (Original post by Tazzie)
    Hey guys!

    Jan 2005. im working my way through it. Although i'd be glad if someone could exaplin number four to me.

    Question 4
    how comes the alternative hypothesis being tested is <? i wrote greater than or equal to...looks like thire testing aginst his veiws, i dunno? is this sumthing we always do?
    and also i approximated it to the poisson, as np>5, and nq<5...that didnt seem to be accepted in the mark scheme either.
    and then, in the binomial way, why are we testing less than or equal to 9, must be beacuse of the hypothesis right?
    Hello Tazzie!! for this one.. I did it like this....

    3/4 in favour

    observed = 10/16 - already hints to binomial too mee

    we don't care if more than 3/4 vote government still right
    but we do care about <3/4

    so,

    ho: p = 3/4
    h1: p <3/4
    los = 10% (0.1)
    one tail test
    under ho P=3/4

    X~B(16, 3/4)

    then i look @ binomial cumulative thingy
    look under n = 16 and p = 0.75

    then I find where sig is in between

    P(X<=9) = 0.0796
    ------------------------>0.1
    P(X<=10) = 0.1897

    therefore, decision:

    X<= 9 Reject Ho!!
    X>9 Accept Ho!!

    observed = 10... ACCEPT HO..

    then write conclusion.. :eek:

    Now! Hurry up and help me with Q6 ! I'm still stuck with it

    ***
    Edit:
    oh guess what I just thought of something... remember.. if they asked as to use a normal approx... don't forget to - or + 0.5 when finding the rejection region! I always forget!
    • Thread Starter
    Offline

    1
    ReputationRep:
    hey thanx for that.
    the binomial thing is what i did too, but then i apporimated to poisson. but that was stupid of me, cos n wasnt >50. but then yh, so it makes sense!
    just gonna make sure the hypothesisy thing does

    question 6 was a crap one to me. i thought of you though when i di it, i thought it must have something to do with that method you were showing with binomial proportions???


    but anyway, i only got it correct until the approximation. thereafter went downhill! What you thinking?
    • Thread Starter
    Offline

    1
    ReputationRep:
    just finished the paper. thought it was an arite paper, yet only got 44/60.. 73% innit. yikes! IwantanA!
    • Thread Starter
    Offline

    1
    ReputationRep:
    anyone brainy enough to tell us how to do 6!?
    Offline

    0
    ReputationRep:
    (Original post by Tazzie)
    anyone brainy enough to tell us how to do 6!?
    lol I've posted the images of the question on another thread... let me see if anyone has replied yet.
    http://www.thestudentroom.co.uk/t124372.html
    • Thread Starter
    Offline

    1
    ReputationRep:
    (Original post by Saiyan)
    lol I've posted the images of the question on another thread... let me see if anyone has replied yet.
    http://www.thestudentroom.co.uk/t124372.html
    nope! no-one! lol. hope confused gets here soon, he seems to know his stats!
    Offline

    1
    ReputationRep:
    (Original post by Tazzie)
    nope! no-one! lol. hope confused gets here soon, he seems to know his stats!

    i havent started the paper yet but i just looked at 6. Could be binomial with n as 300 and p as 1/12. What do you think? could this be done?
    Offline

    0
    ReputationRep:
    (Original post by Tazzie)
    nope! no-one! lol. hope confused gets here soon, he seems to know his stats!
    hehe Yup!! - Agreed
    Offline

    0
    ReputationRep:
    (Original post by confused?)
    i havent started the paper yet but i just looked at 6. Could be binomial with n as 300 and p as 1/12. What do you think? could this be done?
    where did u get 1/12 from???
    • Thread Starter
    Offline

    1
    ReputationRep:
    its X-B(300,0.05).

    i got that far, and also found the approximation:
    X-N(15,14.25)

    but then?
    Thanx confused!
    • Thread Starter
    Offline

    1
    ReputationRep:
    huh! how did i get 0.05! its the right answer, but cant remebr why i got it!
    Offline

    0
    ReputationRep:
    (Original post by Tazzie)
    its X-B(300,0.05).

    i got that far, and also found the approximation:
    X-N(15,14.25)

    but then?
    Thanx confused!
    but 0.05 is the significants level not the probability ??? :confused: :confused:
    Offline

    0
    ReputationRep:
    (Original post by Tazzie)
    huh! how did i get 0.05! its the right answer, but cant remebr why i got it!
    lol RIGHT! come on think Tazzie how did u get it
    Offline

    0
    ReputationRep:
    i also got 0.05, and am now wondering y!
    mmm, must find out
    • Thread Starter
    Offline

    1
    ReputationRep:
    (Original post by Saiyan)
    lol RIGHT! come on think Tazzie how did u get it
    erm, i dont know! argh, this aint good!

    argh, from my working it looks like, it said approximation to normal, only binomial fits, i needed a probabaility..0.05 was good...lol!

    but theres a better explantion somewhere, I think, its because of the type 1 error.

    here were given the proabability a type one error can occur, p=0.05, n=300. therefore the error can be distributed binomially.

    and so to work out if the error occurs at 20, you calculate normally, using an approximation to the normal.

    anyone?
    Offline

    1
    ReputationRep:
    maybe you just have to use the sig level as probability but dont know why yet. will find out by tomorrow atleast.
    Offline

    0
    ReputationRep:
    (Original post by confused?)
    maybe you just have to use the sig level as probability but dont know why yet. will find out by tomorrow atleast.
    Our S2 Exam is tomorrow though :rolleyes:

    oh oh .... I think i know how to do it ! let me see if it works brb.
 
 
 
Turn on thread page Beta
Updated: June 26, 2005
The home of Results and Clearing

2,416

people online now

1,567,000

students helped last year

University open days

  1. Keele University
    General Open Day Undergraduate
    Sun, 19 Aug '18
  2. University of Melbourne
    Open Day Undergraduate
    Sun, 19 Aug '18
  3. Sheffield Hallam University
    City Campus Undergraduate
    Tue, 21 Aug '18
Poll
A-level students - how do you feel about your results?
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.