You are Here: Home >< Maths

# Edexcel S3 - Wednesday 25th May AM 2016 watch

1. actually I believe it is the number of degrees of freedom = number of cels (after any combinging) - number of constraints so grouping it with the 5 thingy wont take away a degree of freedom.
2. If an expected frequency is less than 5 and it is in the middle of the table, do you combine it with a value on the left or right?
3. (Original post by L'Evil Wolf)
If an expected frequency is less than 5 and it is in the middle of the table, do you combine it with a value on the left or right?
There are so many unanswered questions in S3

I'm saying that because I have no idea
4. (Original post by Euclidean)
Is there a penalty for arranging the ranks in reverse order in SRCC?

In the below question I ranked the average attendance in ascending order (C as 1) rather than descending order (B as 1). The value of the coefficient is negative as a result. I don't think the question specified very well their intentions? (It was the specimen paper though)

you're allowed to rank in reverse order, it permitted it in the 'notes' section of the mark scheme. you would just have to adjust your hypotheses and critical values to negative I imagine
5. Attachment 536311536313
another question on the June 15 paper. for part (c) I understand that U1 and Ubar are independent, but what exactly does it mean when it says 'so variance formula cannot be used'? aren't we using the variance formula in part (d) anyway?
Attached Images

6. (Original post by Achint10)
Attachment 536311536313
another question on the June 15 paper. for part (c) I understand that U1 and Ubar are independent, but what exactly does it mean when it says 'so variance formula cannot be used'? aren't we using the variance formula in part (d) anyway?
Given that it says any random sample, the 's are not necessarily independent of each other. The combination of variance formula only works if the variables are independent. This means that we can't use the variance combination formula and hence can't use part (b) here.
7. (Original post by Euclidean)
Given that it says any random sample, the 's are not necessarily independent of each other. The combination of variance formula only works if the variables are independent. This means that we can't use the variance combination formula and hence can't use part (b) here.
still confused lol. i guess i still don't really understand independent variables :/ what is it about the 'any random sample' bit that makes it so that the variables don't have to be independent? in the mark scheme it says that U1 is a part of the Ubar calculation, so they're not independent. wouldn't that be the case with any sample?
8. (Original post by Euclidean)
There are so many unanswered questions in S3

I'm saying that because I have no idea
I agree yes.
9. (Original post by L'Evil Wolf)
If an expected frequency is less than 5 and it is in the middle of the table, do you combine it with a value on the left or right?
@physicsmaths @zacken

any ideas
10. (Original post by Achint10)
still confused lol. i guess i still don't really understand independent variables :/ what is it about the 'any random sample' bit that makes it so that the variables don't have to be independent? in the mark scheme it says that U1 is a part of the Ubar calculation, so they're not independent. wouldn't that be the case with any sample?
I wrote a long response before my internet cut out and I lost it

Independence in sampling basically means that the outcome of one sample will not affect the outcome of another sample.

Imagine you're testing the number of a certain type of organism in a pond, but once you remove the organism from the pond it dies (far-fetched maybe but run with it). Once you take a first sample of the pond on say Monday, the organisms you removed will no longer be members of the population in the pond. So come Tuesday when you go to sample again, the result of your second sample will depend on those of your first. Thus the samples are not independent.

That doesn't mean to say that there aren't independent samples, because some samples may well be independent. But samples don't necessarily have to be independent. So by referencing any sample, they are telling you that the sample may be independent but it doesn't have to be. This is the reason that you can't assume independence.
11. (Original post by L'Evil Wolf)
@physicsmaths @zacken

any ideas
physicsmaths Zacken
12. haha Lol
13. (Original post by L'Evil Wolf)
If an expected frequency is less than 5 and it is in the middle of the table, do you combine it with a value on the left or right?
physicsmaths Zacken
14. (Original post by L'Evil Wolf)
physicsmaths Zacken
If only I knew something about statistics
15. (Original post by physicsmaths)
If only I knew something about statistics
lol
16. (Original post by L'Evil Wolf)
actually I believe it is the number of degrees of freedom = number of cels (after any combinging) - number of constraints so grouping it with the 5 thingy wont take away a degree of freedom.
If you had 6 cells and group them into 5 cells. You've lost a degree of freedom.

(Original post by L'Evil Wolf)
If an expected frequency is less than 5 and it is in the middle of the table, do you combine it with a value on the left or right?
It's not going to be in the middle of the table because that's how distributions we study work, the only low values occur at the tails of the distribution. If, in some bizzare, non-standard distribution we have an expected value of less than 5 in the middle, then it won't matter whether we pool to the left or the right. Remember that none of the things we do (for chi-squared) are exact, they are simple approximations.
17. When is it in chapter 3 questions that we use the modulus? I can never tell in questions when it needs to be used
18. (Original post by Zacken)
If you had 6 cells and group them into 5 cells. You've lost a degree of freedom.

It's not going to be in the middle of the table because that's how distributions we study work, the only low values occur at the tails of the distribution. If, in some bizzare, non-standard distribution we have an expected value of less than 5 in the middle, then it won't matter whether we pool to the left or the right. Remember that none of the things we do (for chi-squared) are exact, they are simple approximations.
nicely explained thank you.
19. How do you group expected values less than 5 in contingency tables? I haven't come across a question yet that asks for it to be done, but just wondering
20. (Original post by 260498)
When is it in chapter 3 questions that we use the modulus? I can never tell in questions when it needs to be used
When it says to find the probability that the difference between two things is whatever. So it means that either one could be bigger.

### Related university courses

TSR Support Team

We have a brilliant team of more than 60 Support Team members looking after discussions on The Student Room, helping to make it a fun, safe and useful place to hang out.

This forum is supported by:
Updated: June 29, 2016
Today on TSR

### AQA Mechanics Unofficial Markscheme

Find out how you've done here

### 2,775

students online now

Exam discussions

### Find your exam discussion here

Poll
Useful resources

Can you help? Study help unanswered threadsStudy Help rules and posting guidelinesLaTex guide for writing equations on TSR

## 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