Join TSR now and get all your revision questions answeredSign up now

Official Edexcel S3 thread Wednesday 20 May 2015 Morning [6691] Watch

    Offline

    0
    ReputationRep:
    Hi guys
    This is june 2013 (R)
    for part a why is the mean a+2 and not 17.2
    Name:  Screen Shot 2015-05-19 at 12.57.01 PM.png
Views: 107
Size:  35.5 KB
    Offline

    2
    ReputationRep:
    (Original post by physicshelper)
    Hi guys
    This is june 2013 (R)
    for part a why is the mean a+2 and not 17.2
    Name:  Screen Shot 2015-05-19 at 12.57.01 PM.png
Views: 107
Size:  35.5 KB
    You always use the population mean if you have it
    Offline

    3
    ReputationRep:
    btw i don't think we'll get tied ranks bc in the syllabus it says


    "Regression and correlation
    What students need to learn:
    Spearman’s rank correlation coefficient, its use,interpretation and limitations.
    Numerical questions involvingties will not be set. Someunderstanding of how to deal withties will be expected"
    Offline

    2
    ReputationRep:
    (Original post by mmms95)
    the mark scheme says anything from 2d.p or more is fine, but i usually do 3 d.p, might end up doing 4 d.p in the exam tho :P just in case
    Yeah, they do seem quite picky for the chi squared value
    Offline

    0
    ReputationRep:
    (Original post by FN510)
    You always use the population mean if you have it
    thanks!!
    Offline

    2
    ReputationRep:
    There's no penalty for too many decimal places, so I always do it to 4 d.p.
    Offline

    0
    ReputationRep:
    Question 3 on the June 2012 paper

    Name:  Screen Shot 2015-05-19 at 12.30.42.png
Views: 88
Size:  57.2 KB

    for part (d), the mark scheme states that 20k is above the upper confidence limit so the complaint is justified, could someone please explain this part to me?
    Offline

    3
    ReputationRep:
    (Original post by shamika)
    P(|z|<3) = P(-3<z<3) always, by definition.

    It is only 2 x P(z<3) if the distribution is symmetric about 0. Thus it is true for the standard normal, but won't be for a uniform distribution between 0 and 1 say.
    ahh okay, so just to clarify, its ALWAYS going to be 2 x probability it its normal distribution right?

    (Original post by FN510)
    Yeah, the diagram does help. If it p(|W| > 2) say, that = 2p(W >2). But if it was p(|W| < 2) that's equal to p(-2 < W < 2)
    wait, won't the last one also be 2 x ??? in the mark scheme they always times the probability by 2, so i assume the method marks are only achieved if you use that, (even tho the other method works too)
    Offline

    2
    ReputationRep:
    (Original post by JuliM)
    Question 3 on the June 2012 paper

    Name:  Screen Shot 2015-05-19 at 12.30.42.png
Views: 88
Size:  57.2 KB

    for part (d), the mark scheme states that 20k is above the upper confidence limit so the complaint is justified, could someone please explain this part to me?
    20k is above the 95% certainty of mean time of car tyre change, therfore they are changing the tyres too soon
    Offline

    0
    ReputationRep:
    (Original post by getback339)
    20k is above the 95% certainty of mean time of car tyre change, therfore they are changing the tyres too soon
    So are they supposed to change the tyres if the mean lies within the confidence interval? This might be going over my head but I'm struggling to understand the question
    Offline

    2
    ReputationRep:
    I'm a little confused as to how much they expect us to know about proving biased/unbiased-ness in estimators...
    Offline

    2
    ReputationRep:
    (Original post by JuliM)
    So are they supposed to change the tyres if the mean lies within the confidence interval? This might be going over my head but I'm struggling to understand the question
    i didnt explain that very well to be fair... you worked out how many miles on average the garage replaces the brake pads. The actual number of miles before brake pads need replacing is 20,000 so the garage on average is changing them too soon. Im pretty bad at explaing haha
    Offline

    0
    ReputationRep:
    (Original post by getback339)
    i didnt explain that very well to be fair... you worked out how many miles on average the garage replaces the brake pads. The actual number of miles before brake pads need replacing is 20,000 so the garage on average is changing them too soon. Im pretty bad at explaing haha
    No no I get it now, thank you for your help!
    Offline

    13
    ReputationRep:
    (Original post by mmms95)
    ahh okay, so just to clarify, its ALWAYS going to be 2 x probability it its normal distribution right?
    Any normal distribution which has mean 0, yes.
    Offline

    1
    ReputationRep:
    These high grade boundaries coupled with either one dodgy question or a couple of silly errors (like arithmetic errors) is making that A* very annoying
    Offline

    2
    ReputationRep:
    For goodness of fit, hypothesis tests, how would we know when it's asking for a discrete uniform distribution?
    Offline

    2
    ReputationRep:
    (Original post by nayilgervinho)
    For goodness of fit, hypothesis tests, how would we know when it's asking for a discrete uniform distribution?
    it would be somthing obvious like fair coin or dice.
    Offline

    2
    ReputationRep:
    (Original post by getback339)
    it would be somthing obvious like fair coin or dice.
    So if the question mentions 'equally likely' I should assume it's a discrete uniform distribution.
    Offline

    2
    ReputationRep:
    (Original post by nayilgervinho)
    So if the question mentions 'equally likely' I should assume it's a discrete uniform distribution.
    not necessarily, if the observed data looks the same for all values, you havnt found estimates for prob. etc... theyl make it clear for you
    Offline

    2
    ReputationRep:
    (Original post by getback339)
    not necessarily, if the observed data looks the same for all values, you havnt found estimates for prob. etc... theyl make it clear for you
    Ok, thanks.
 
 
 
Poll
If you won £30,000, which of these would you spend it on?

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

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