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

    1
    ReputationRep:
    (Original post by masryboy94)
    i presume it would be, because the real values are still continuous, because if you get say for example 27 mins 52 seconds ..... and so on and you round it to the nearest minute of 28 mins, the actual value is still continuous
    that's what i thought although in this paper they seem to have treated it as discrete (it's question 4):
    http://www.carlgauss.co.uk/PDFs/A-Le...an%20Paper.pdf

    the markscheme shows them taking the 10.5th value, 4.5th value and 15.5th value for the quartiles. :s
    http://www.edexcel.com/migrationdocu...ark_scheme.pdf

    maybe it's just an old paper? i'm really not sure.
    Offline

    2
    ReputationRep:
    (Original post by Didierr)
    This is from Jan 2011 question 6 and I have no clue how question e and f, if anyone has any clue please help!

    http://www.edexcel.com/migrationdocu...e_20110114.pdf
    6. The discrete random variable X has the probability distribution
    x 1 2 3 4
    P(X = x) k 2k 3k 4k
    (a) Show that k = 0.1
    (1)
    Find
    (b) E(X)
    (2)
    (c) E(X 2)
    (2)
    (d) Var(2 – 5 X )
    (3)
    Two independent observations X1 and X2 are made of X.
    (e) Show that P(X1 + X2 = 4) = 0.1
    (2)
    (f) Complete the probability distribution table for X1 + X2
    (2)
    y 2 3 4 5 6 7 8
    P(X1 + X2 = y) 0.01 0.04 0.10 0.25 0.24


    ________________________________ ________________________________ ___________
    ________________________________ ________________________________ ___________

    http://www.thestudentroom.co.uk/show...8#post42628868

    I answered the same question on there somewhere..
    Offline

    3
    ReputationRep:
    (Original post by PurpleSquid)
    that's what i thought although in this paper they seem to have treated it as discrete (it's question 4):
    http://www.carlgauss.co.uk/PDFs/A-Le...an%20Paper.pdf

    the markscheme shows them taking the 10.5th value, 4.5th value and 15.5th value for the quartiles. :s
    http://www.edexcel.com/migrationdocu...ark_scheme.pdf

    maybe it's just an old paper? i'm really not sure.
    Don't think too deeply into it. Continuous data, grouped frequency table. Discrete data, ungrouped data outside of a table.
    Offline

    1
    ReputationRep:
    (Original post by B-Stacks)
    Don't think too deeply into it. Continuous data, grouped frequency table. Discrete data, ungrouped data outside of a table.
    haha ok thanks.

    although if age comes up in an ungrouped out-of-table data question i think i'll pass out.
    Offline

    3
    ReputationRep:
    So let me get this straight if you have data that like (2 5 9 1 8 11 90 72 85 81 51 39 etc) to find the median would I do N+1/2 or just N/2
    • Welcome Squad
    Offline

    14
    ReputationRep:
    When drawing the regression line do you plot anything else apart from the means? Have you guys done the Jan 2013 paper? Is it just me or was that paper quite tricky?? :confused:
    Offline

    11
    ReputationRep:
    (Original post by Shady778)
    So let me get this straight if you have data that like (2 5 9 1 8 11 90 72 85 81 51 39 etc) to find the median would I do N+1/2 or just N/2
    I always do n+1/2 because that makes it easier to locate the position, also DONT FORGET TO ORDER YOUR DATA FROM ASCENDING TO DESCENDING WITH THIS METHOD
    Offline

    2
    ReputationRep:
    (Original post by Shady778)
    So let me get this straight if you have data that like (2 5 9 1 8 11 90 72 85 81 51 39 etc) to find the median would I do N+1/2 or just N/2
    i believe you do can do both, if you do n/2 just add 0.5 on after.
    Offline

    11
    ReputationRep:
    (Original post by Fortitude)
    When drawing the regression line do you plot anything else apart from the means? Have you guys done the Jan 2013 paper? Is it just me or was that paper quite tricky?? :confused:
    I think everyone hated that paper. I'm about to attempt it now. WISH ME LUCK
    • Welcome Squad
    Offline

    14
    ReputationRep:
    (Original post by Shady778)
    So let me get this straight if you have data that like (2 5 9 1 8 11 90 72 85 81 51 39 etc) to find the median would I do N+1/2 or just N/2
    If you did n/2 & got a whole no then you'd the answer would be the mp of that term & the next term. If you didn't get a whole no you'd just round up & choose the corresponding term.
    • Welcome Squad
    Offline

    14
    ReputationRep:
    (Original post by nukethemaly)
    I think everyone hated that paper. I'm about to attempt it now. WISH ME LUCK
    That's ok then, hope ours is easier!! Ha, ha don't worry you don't need luck for practicing a past paper! Anyway though Good Luck & GOOD LUCK for tomorrow! :p:D
    Offline

    0
    ReputationRep:
    (Original post by JAJC)
    Aight, for statistical independence in probability questions like these remember two rules P(A|B)=P(A). P(B|A)=P(B) . P(A)P(B)=P(AnB)

    So, we know from the previous question the probability of kamil being late given jake being late is 0.15/0.25 = 0.6. Now if we using the equation P(K|J)=P(K) we can see that if P(K|J)= 0.6 and P(K) = 0.2 that they are not equal therefore not independent. In part e the teacher has a suspicion if they are linked, independent means they are not related at all, so if kamil and jakes lateness is not independent they are somehow linked therefore confirming her suspicion
    (Original post by Air1337)
    d) We have P(J) 0.25 and P(K) 0.2 which you calculated earlier in the question.

    If P(J) * P(K) = P(J n K) it will be statistically independent

    However, 0.25*0.2 = 0.05 =/= (P(J n K) so J and K are not independent

    e) Confirms teachers suspicions since Jake and Kamil could be going to school together, since they are dependent.
    understand now.. thanks!!!!
    Offline

    1
    ReputationRep:
    Hey Guys,

    I have a few issues and queries:

    First of all:

    Can someone explain to me how skewness works and every possible way of working out the skewness?

    How do you relate it back to the data, for example I have no difficulty working it out and stating whther it's postively skewed, negatively skewed or symmetrical. But is that enough or would I have to relate it back to the data.

    When is it best to use the mean and median?

    I understadn when they are two completely different numbers and you apply it to the context for example at a sale you'd pick the lower one, but what if they don't give you much context and they ask which is the best.

    All I know is that you'd wouldn't pick mean if there are outliers as extreme values affect the mean

    When would you not pick the the median? Are there any other reasons not to pick the mean?

    When finding the median using interpolation when should you take the upper and lower bound?

    Which is right:

    x f CF
    0 - 100 3 3
    100 - 200 4 7
    200 - 300 3 10


    0 m 100
    -------------------------------
    3 5 7 and then use a/b = c/d


    x f CF
    0 - 99 3 3
    100 - 199 4 7
    299 - 300 3 10


    99.5 Q3 199.5
    ----------------------------------------
    7 7.5 10 then use a/b - c/d

    How does coding work?

    Coding does not affect pmcc, but addition/subtraction and multiplication/division affects the mean

    but Standard deviation is only affected by division/subtraction.

    mean of v = 45 and the SD = 15 n = 9 and v = (x-5)/10

    would the uncoded mean be:
    45*9 = 405
    405 - (9*5)/10 = 36


    or would it be:

    45 - 5/10 = 4

    For the uncoded SD would it be:

    15/10 = 1.5

    Thanks I've got so many Qs, so anyone willing to help I'd be really grateful.
    • TSR Support Team
    • Community Assistant
    • PS Reviewer
    Offline

    18
    ReputationRep:
    Best of luck to you guys doing S1 tomorrow. :yy:

    Hopefully the probabilities will be in your favour :teehee:

    Hopefully you won't have to vennt your frustration on here after the exam.
    Offline

    0
    ReputationRep:
    A group of office workers were questioned for a health magazine and 2/5 were found to take regular exercise. when questioned about their eating habits 2/3 said they always eat breakfast, of those who always eat breakfast 9/25 also take regular exercise

    find probability randomly selected member
    a) always eat breakfast and take regular exercise
    b) does not eat breakfast and not take regular exercise
    c) determine, weather or not always eating breakfast and taking regular exercise are statistically independent
    understand a, not b could someone help please??
    Offline

    0
    ReputationRep:
    Can anyone put a link for the Jan 2013 paper???
    Offline

    0
    ReputationRep:
    (Original post by vithusan40)
    Can anyone put a link for the Jan 2013 paper???
    http://www.examsolutions.net/a-level...y/paper.php#Q5

    It's here on ExamSolutions with worked video solutions, I'm doing it at the moment.
    Offline

    0
    ReputationRep:
    (Original post by zakkaz)
    Hey Guys,

    I have a few issues and queries:

    First of all:

    Can someone explain to me how skewness works and every possible way of working out the skewness?

    How do you relate it back to the data, for example I have no difficulty working it out and stating whther it's postively skewed, negatively skewed or symmetrical. But is that enough or would I have to relate it back to the data.

    When is it best to use the mean and median?

    I understadn when they are two completely different numbers and you apply it to the context for example at a sale you'd pick the lower one, but what if they don't give you much context and they ask which is the best.

    All I know is that you'd wouldn't pick mean if there are outliers as extreme values affect the mean

    When would you not pick the the median? Are there any other reasons not to pick the mean?

    When finding the median using interpolation when should you take the upper and lower bound?

    Which is right:

    x f CF
    0 - 100 3 3
    100 - 200 4 7
    200 - 300 3 10


    0 m 100
    -------------------------------
    3 5 7 and then use a/b = c/d


    x f CF
    0 - 99 3 3
    100 - 199 4 7
    299 - 300 3 10


    99.5 Q3 199.5
    ----------------------------------------
    7 7.5 10 then use a/b - c/d

    How does coding work?

    Coding does not affect pmcc, but addition/subtraction and multiplication/division affects the mean

    but Standard deviation is only affected by division/subtraction.

    mean of v = 45 and the SD = 15 n = 9 and v = (x-5)/10

    would the uncoded mean be:
    45*9 = 405
    405 - (9*5)/10 = 36


    or would it be:

    45 - 5/10 = 4

    For the uncoded SD would it be:

    15/10 = 1.5

    Thanks I've got so many Qs, so anyone willing to help I'd be really grateful.
    Hey, I can try and help with a few!
    -With the skewness, the paper should generally tell you which method to work it out by i.e. there have been a few of 3(mean-median)/standard deviation etc. And then with relating it to the question, it is hard to give a generic answer. But for example on one paper it said work out the skewness for the age of customers two hotels attracted. It worked out as a positive skew for one hotel, so that meant it attracted older customers etc (that was June 2008, Q2) and they will say when to relate it to the data

    -With the mean/median questions, generally I think they will only want the answers that you have put.

    -With the lower boundaries (and upper ones) what you said for the top part is right, not really sure about the 2nd part, but as a general rule, if the boundaries touch i.e 0-100, 100-200, 200-300 etc, take the 0, 100, 200. If there is a gap between, you take the half numbers i.e. 0-99, 100-199, 200-299, take 99.5, 199.5, 299.5 etc ( i think thats what you said?)

    -And coding: PMCC not affected at all by coding,
    Mean is affected by all four (multiplying, dividing, adding and
    subtracting) and your second part is correct i.e. 45 - 5/10
    = 4
    and standard deviation is only affected by multiplication and
    division! and yes the uncode for that is right
    Hope that helps! And good luck for tomorrow!
    Offline

    0
    ReputationRep:
    What are these 2 group frequency tables called? Continuous and discrete?
    5-10
    10-15
    15-20

    and

    5-10
    11-15
    16-20
    Offline

    2
    ReputationRep:
    (Original post by tsr1)
    A group of office workers were questioned for a health magazine and 2/5 were found to take regular exercise. when questioned about their eating habits 2/3 said they always eat breakfast, of those who always eat breakfast 9/25 also take regular exercise

    find probability randomly selected member
    a) always eat breakfast and take regular exercise
    b) does not eat breakfast and not take regular exercise
    c) determine, weather or not always eating breakfast and taking regular exercise are statistically independent
    understand a, not b could someone help please??
    i done this question the other day, took me so long to understand it !!! in the end i did a tree diagram and as soon as i filled it out correctly, the answers were so easy to get. its just actually understanding it and interpreting it through tree diagram or other statistics methods.

    Use the tree diagram i attached to try complete the question.
    Attached Images
     
 
 
 
Poll
Which pet is the best?

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.