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

    8
    ReputationRep:
    Name:  Scan 5.jpeg
Views: 135
Size:  43.1 KBdoes anyone know how id do a chi squared test with this? i know the quality isn't very good but any help please?
    Offline

    20
    ReputationRep:
    (Original post by tomlfc)
    does anyone know how id do a chi squared test with this? i know the quality isn't very good but any help please?
    Do you know where you would start- I.e.do you not know how to do a chi squared test or is there something that isn't going right for you?
    • Thread Starter
    Offline

    8
    ReputationRep:
    (Original post by Davalla)
    Do you know where you would start- I.e.do you not know how to do a chi squared test or is there something that isn't going right for you?
    i don't know where to start, don't know what to do at all, the teacher just gave it us to do without us learning about it
    Offline

    20
    ReputationRep:
    (Original post by tomlfc)
    i don't know where to start, don't know what to do at all, the teacher just gave it us to do without us learning about it
    If you're starting from scratch try an online tutorial which might be more beneficial. E.g. this https://youtu.be/VskmMgXmkMQ

    I'll try to sum things up though:
    What you have in your table is raw data. We call these the observed frequencies (O). For each observed frequency you need to find what is called an expected frequency (E) by multiplying the row and column totals and then dividing them by the 'total total' (the largest number in the bottom right corner). By now you should have a an expected frequency for each observed frequency.

    Then you need to do: 'O minus E, squared, divided by E' for each data entry that you have.

    By now you should have four new numbers as a result of the previous equation. Add them up to get your Chi value. Then find the degrees of freedom value (df) which is: (the number of rows -1) x (number of columns - 1).

    You'd then be able to compare what your statistical test shows with a table of critical values; to be significant, your chi squared value must equal to or greater than the critical value on the table.
    • Thread Starter
    Offline

    8
    ReputationRep:
    thankyouuu
    Offline

    12
    ReputationRep:
    Is this A-level or degree? Either way, this is bad teaching. The point of doing stats by hand is not to learn how to do the stats by hand (everyone uses SPSS any way and the manual method is just following simple steps; as above).

    The point of doing stats by hand is to learn why you do each step and how the statistic actually works.
    • Thread Starter
    Offline

    8
    ReputationRep:
    a level, she said we don't actually need to know how to do it for exams but to do it anyway so we know about it
    Offline

    0
    ReputationRep:
    How do you know if your chi-squared results are reliable???
    Offline

    18
    ReputationRep:
    (Original post by qwertyasdfghj)
    How do you know if your chi-squared results are reliable???
    You look at the p value or calculate confidence intervals. A lower p value means you have greater certainty that the null hypothesis is incorrect. Confidence intervals are a little beyond a level.
 
 
 
Reply
Submit reply
Turn on thread page Beta
Updated: November 26, 2015
Poll
Do you like carrot cake?

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.