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

    2
    ReputationRep:
    I've only just started the module and done only the first two chapters, but I'm already having trouble with it. Its not the difficulty, but rather, its the lack of logic/purpose to doing things, which I'm frustrated with.

    So I have some questions:

    1) what exactly is the point of 'coding'? - As I see it at the moment, its just an extra uneccessary step to finding the mean of the data.

    2) I'm told in the book that I 'usually will be given the coding formula'. But what happens, when I'm not given it. How will I know which values to choose? - In the one of the examples in the book, it says this: '7.5 was chosen as it is the mid-point of the modal class. 5 was chosen as this is the smallest class width, but any numbers would do'. So the bit in bold suggests that actually, I could pluck any number out of the air and use it in the coding formula? (seems very arbitary to me, and leads me to question why did the authors of the book bother explaining their choice of numbers)

    3) In one example from the book where I have to estimate the median of data in a grouped frequency table, the total frequency (which was an even number) is divided by 2 and the value from this was taken to be the nth term of the median - thereby suggesting that the median lies on that term. I don't understand, because previously the book stated that if the total frequency was an even number, then the median would lie between the two terms in the middle, rather than one.
    Offline

    13
    (Original post by W.H.T)
    I've only just started the module and done only the first two chapters, but I'm already having trouble with it. Its not the difficulty, but rather, its the lack of logic/purpose to doing things, which I'm frustrated with.

    So I have some questions:

    1) what exactly is the point of 'coding'? - As I see it at the moment, its just an extra uneccessary step to finding the mean of the data.

    2) I'm told in the book that I 'usually will be given the coding formula'. But what happens, when I'm not given it. How will I know which values to choose? - In the one of the examples in the book, it says this: '7.5 was chosen as it is the mid-point of the modal class. 5 was chosen as this is the smallest class width, but any numbers would do'. So the bit in bold suggests that actually, I could pluck any number out of the air and use it in the coding formula? (seems very arbitary to me, and leads me)

    3) In one example from the book where I have to estimate the median of data in a grouped frequency table, the total frequency (which was an even number) is divided by 2 and the value from this was taken to be the nth term of the median - thereby suggesting that the median lies on that term. I don't understand, because previously the book stated that if the total frequency was an even number, then the median would lie between the two terms in the middle, rather than one.
    1) Coding - to make it easier with data where there are large values.

    2) E.g. "Use X = (x - 10) / 50". Basically the formula is what you do to "code" the values.

    3) Grouped frequency table - i.e. continuous data. When you find the median and you get 50.8 (because it's continuous), you need to use interpolation to find the exactly value of the 50.8th term.
    Offline

    15
    ReputationRep:
    Oh great I'm starting S1 next week
    • Thread Starter
    Offline

    2
    ReputationRep:
    (Original post by vedderfan94)
    Oh great I'm starting S1 next week
    Well the actual methods are easy - certainly from my experience so far (just hope this continues). I've rarely heard complaints about its difficulty by people I know who are doing it or have done it.

    But like I said, some of the stuff there definetly doesn;t come across as 'logical' as from example the mechanics modules.
    • Thread Starter
    Offline

    2
    ReputationRep:
    (Original post by im so academic)
    1) Coding - to make it easier with data where there are large values.

    2) E.g. "Use X = (x - 10) / 50". Basically the formula is what you do to "code" the values.

    3) Grouped frequency table - i.e. continuous data. When you find the median and you get 50.8 (because it's continuous), you need to use interpolation to find the exactly value of the 50.8th term.
    I know the formula is what I use to change the values. But my question is how are the values within it chosen? (like I said, the book explains its choice of values, but then goes on to say that ''any numbers would do'')

    Also, on your answer to my 3rd question, I understand its continous and therefore the median term doesn't have to be a whole number. But when the total frequency (e.g. the total number of observations) is an even number, then the median should lie between two terms in the middle (e.g. nth and bth term). The book basically just takes the nth term as the median.

    Its just like this: if I have 10 values from ten observations, then the median value would be between the 5th and 6th term (so if you were to work out the median then you would add up the 5th and 6th term, then divide the answer by two). Why would the book just take the 5th term as the median?
    Offline

    13
    (Original post by W.H.T)
    I know the formula is what I use to change the values. But my question is how are the values within it chosen? (like I said, the book explains its choice of values, but then goes on to say that ''any numbers would do'')

    Also, on your answer to my 3rd question, I understand its continous and therefore the median term doesn't have to be a whole number. But when the total frequency (e.g. the total number of observations) is an even number, then the median should lie between two terms in the middle (e.g. nth and bth term). The book basically just takes the nth term as the median.

    Its just like this: if I have 10 values from ten observations, then the median value would be between the 5th and 6th term (so if you were to work out the median then you would add up the 5th and 6th term, then divide the answer by two). Why would the book just take the 5th term as the median?
    1) The question states the values you should use.

    2) Well, that's just the rule (which only applies to discrete data).

    3) Because that's just the rule and it's discrete so you can't have the "5.5th" value. That's just the way it goes.
    Offline

    0
    ReputationRep:
    (Original post by im so academic)
    x
    Aren't you like 10? :curious:
    • Thread Starter
    Offline

    2
    ReputationRep:
    (Original post by im so academic)
    1) The question states the values you should use.

    2) Well, that's just the rule (which only applies to discrete data).

    3) Because that's just the rule and it's discrete so you can't have the "5.5th" value. That's just the way it goes.
    No logic then is there?

    At the beginning I'm told that the median (if the total frequency 'n' is an even number) would be n/2.

    Next, I'm told another thing.

    Offline

    13
    (Original post by W.H.T)
    No logic then is there?

    At the beginning I'm told that the median (if the total frequency 'n' is an even number) would be n/2.

    Next, I'm told another thing.

    There are different median rules depending on the data - i.e. whether it's discrete or continuous.
    Offline

    2
    ReputationRep:
    (Original post by W.H.T)
    No logic then is there?

    At the beginning I'm told that the median (if the total frequency 'n' is an even number) would be n/2.

    Next, I'm told another thing.

    I will hopefully straighten it out for ya:

    Finding the median depends on whether the data is grouped or not.

    For grouped data:

    n/2 gives the exact number you want, whether it is a decimal or whole number. Use interpolation to find it if you have to.

    For singular data: (e.g stem-leaf)

    If n/2 gives you a whole number, round it up to the nearest point 5 (e.g 6 -> 6.5). If it gives you a decimal, round it up to the nearest whole number. (e.g 5.435 -> 6)

    This works, trust me.

    The same rules also apply for finding quartiles, deciles and centiles ( or w/e they hare called ).
    Offline

    2
    ReputationRep:
    (Original post by vedderfan94)
    Oh great I'm starting S1 next week
    for your exam in January or June?
    Offline

    15
    ReputationRep:
    (Original post by mir3a)
    for your exam in January or June?
    June, so I don't see why we have to start yet.
    Offline

    2
    ReputationRep:
    (Original post by Thrug)
    I will hopefully straighten it out for ya:

    Finding the median depends on whether the data is grouped or not.

    For grouped data:

    n/2 gives the exact number you want, whether it is a decimal or whole number. Use interpolation to find it if you have to.

    For singular data: (e.g stem-leaf)

    If n/2 gives you a whole number, round it up to the nearest point 5 (e.g 6 -> 6.5). If it gives you a decimal, round it up to the nearest whole number. (e.g 5.435 -> 6)

    This works, trust me.

    The same rules also apply for finding quartiles, deciles and centiles ( or w/e they hare called ).
    off topic but I thought that it was Lord Kelvin that said whats in your sig
    Offline

    2
    ReputationRep:
    (Original post by clad in armour)
    off topic but I thought that it was Lord Kelvin that said whats in your sig
    Nope.

    Not according to John Gribbin anyway.
    Offline

    12
    ReputationRep:
    S1 all in all is an easy module. Just learn the stuff parrot fashion if need be.
    • Thread Starter
    Offline

    2
    ReputationRep:
    (Original post by Boobies.)
    S1 all in all is an easy module. Just learn the stuff parrot fashion if need be.
    Yeah but it just seems as though all you learn is 'how' something works rather than also 'why'.
    Offline

    12
    ReputationRep:
    (Original post by W.H.T)
    Yeah but it just seems as though all you learn is 'how' something works rather than also 'why'.
    I know, but instead of letting it bug you the best thing you can do is make sure you're able to pass your exam and leave it till you get to uni to understand the why. Otherwise, you could ask for extra lessons/find out in your own time?
    Offline

    14
    (Original post by W.H.T)
    Yeah but it just seems as though all you learn is 'how' something works rather than also 'why'.
    The median is just a useful definition. It allows us to work with and understand data better. There's no more 'why' to it than that.
    Offline

    13
    (Original post by Thrug)
    The same rules also apply for finding quartiles, deciles and centiles ( or w/e they hare called ).
    Percentiles. :p:
    Offline

    2
    ReputationRep:
    (Original post by im so academic)
    Percentiles. :p:
    Makes sense
 
 
 
Reply
Submit reply
Turn on thread page Beta
Updated: November 28, 2010
Poll
Do I go to The Streets tomorrow night?
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.