Turn on thread page Beta
    • Community Assistant
    Offline

    19
    ReputationRep:
    Community Assistant
    (Original post by economicss)
    Just to check, if one our expected frequencies came out to 5 exactly, this wouldn't be combined right, we only combine values less than 5?! Thanks :-)
    this is fine, i wouldn't group it with another colomn etc
    Offline

    12
    ReputationRep:
    Can someone make an S2 thread as well?
    Offline

    2
    ReputationRep:
    Is maximum likelihood estimators a part of S3 or S4?
    • Very Important Poster
    • Thread Starter
    Online

    21
    ReputationRep:
    Very Important Poster
    (Original post by ServantOfMorgoth)
    Is maximum likelihood estimators a part of S3 or S4?
    Not as far as I am aware.

    All you need to do is find the joint distribution of all of the observations in terms of the parameter, xi, log it if necessary, differentiate it with respect to the parameter and solve that, before differnetiating again to check that it is a maximum. Slightly more complicated if it involves two parameters.

    (Original post by Ayman!)
    Can someone make an S2 thread as well?
    If no one else has, I can try
    Offline

    12
    ReputationRep:
    (Original post by SeanFM)
    If no one else has, I can try
    Sean, you're back! Where have you been? And go ahead if it's not too much trouble
    Offline

    2
    ReputationRep:
    (Original post by SeanFM)
    Not as far as I am aware.

    All you need to do is find the joint distribution of all of the observations in terms of the parameter, xi, log it if necessary, differentiate it with respect to the parameter and solve that, before differnetiating again to check that it is a maximum. Slightly more complicated if it involves two parameters.
    So it isn't an a level topic?
    • Very Important Poster
    • Thread Starter
    Online

    21
    ReputationRep:
    Very Important Poster
    (Original post by ServantOfMorgoth)
    So it isn't an a level topic?
    Not as far as I am aware, for Edexcel at least.

    (Original post by Ayman!)
    Sean, you're back! Where have you been? And go ahead if it's not too much trouble
    Uni work :hide: :bricks: :work:
    Offline

    2
    ReputationRep:
    (Original post by SeanFM)
    Not as far as I am aware, for Edexcel at least.

    The derivation for the normal distribution MLE for the mean is very confusing.
    • Very Important Poster
    • Thread Starter
    Online

    21
    ReputationRep:
    Very Important Poster
    (Original post by ServantOfMorgoth)
    The derivation for the normal distribution MLE for the mean is very confusing.
    Which part? This page seems to explain it okay, I think.
    Offline

    2
    ReputationRep:
    (Original post by SeanFM)
    Which part? This page seems to explain it okay, I think.
    I closed that exact same page a few mins ago. I'm not required to know how to derive for 2 unknowns and they don't have an example with only the mean.
    • Very Important Poster
    • Thread Starter
    Online

    21
    ReputationRep:
    Very Important Poster
    (Original post by ServantOfMorgoth)
    I closed that exact same page a few mins ago. I'm not required to know how to derive for 2 unknowns and they don't have an example with only the mean.
    I think you can just treat sigma as a constant and use what they've done for the mean.
    Offline

    2
    ReputationRep:
    (Original post by SeanFM)
    I think you can just treat sigma as a constant and use what they've done for the mean.
    Haha yeah, I figured it out. Thanks
    Offline

    6
    ReputationRep:
    https://ee3a68c993d24792ee12a4f9f960...%20Edexcel.pdf

    Everything is fine for the very last part of the last question except I used a continuity correction but the mark scheme doesn't use this. Why is this?
    I did it slightly differently where I would Reset the Q to P(no of sixes is more than 180)
    Then I did P(X1+...+X100>180.5) I rechecked if I had just done P(X1+...X100>180) then I would have got the correct answer.
    Offline

    2
    ReputationRep:
    I'm a statistics expert in S1- 4 now. Thanks uni :rolleyes:

    Posted from TSR Mobile
    Offline

    12
    ReputationRep:
    (Original post by Rkai01)
    https://ee3a68c993d24792ee12a4f9f960...%20Edexcel.pdf

    Everything is fine for the very last part of the last question except I used a continuity correction but the mark scheme doesn't use this. Why is this?
    I did it slightly differently where I would Reset the Q to P(no of sixes is more than 180)
    Then I did P(X1+...+X100>180.5) I rechecked if I had just done P(X1+...X100>180) then I would have got the correct answer.
    You don't need to use a continuity correction after using in the central limit theorem in Edexcel S3
    Offline

    2
    ReputationRep:
    (Original post by Rkai01)
    https://ee3a68c993d24792ee12a4f9f960...%20Edexcel.pdf

    Everything is fine for the very last part of the last question except I used a continuity correction but the mark scheme doesn't use this. Why is this?
    I did it slightly differently where I would Reset the Q to P(no of sixes is more than 180)
    Then I did P(X1+...+X100>180.5) I rechecked if I had just done P(X1+...X100>180) then I would have got the correct answer.
    The continuity correction is only for when you do the approximations

    Posted from TSR Mobile
    Offline

    6
    ReputationRep:
    (Original post by Ayman!)
    You don't need to use a continuity correction after using in the central limit theorem in Edexcel S3
    In the book it does say a continuity correction can be applied depending on a question. It is definitely in the chapter 3 somewhere in a red box where they write comments.
    Offline

    6
    ReputationRep:
    (Original post by ServantOfMorgoth)
    The continuity correction is only for when you do the approximations

    Posted from TSR Mobile
    But it is an approximation? We are going from binomio to normal
    Offline

    3
    ReputationRep:
    The june 2015 paper is beautiful.
    Offline

    18
    ReputationRep:
    (Original post by Rkai01)
    But it is an approximation? We are going from binomio to normal
    But you have already used Central linit theorem.


    Posted from TSR Mobile
 
 
 
Reply
Submit reply
Turn on thread page Beta
Updated: June 29, 2016

5,346

students online now

800,000+

Exam discussions

Find your exam discussion here

Poll
Should predicted grades be removed from the uni application process

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.