The Student Room Group

OCR S2 (non-mei)

Scroll to see replies

Original post by 000alex
What are the exact things I need to look for in a question to see if I have to use the CLT or not? I really don't get it >.<


If they give you a distribution of the mean and n is large then you should probably use CLT

Edit: or above
How's everyone feeling for tomorrow? I think I've finally cracked S2!
Original post by rich1334
How's everyone feeling for tomorrow? I think I've finally cracked S2!


I feel like I'm waaay too relaxed for this exam :/ No idea why :tongue: Good luck on S2 tomorrow as well! :smile:
Original post by lllllllllll
I feel like I'm waaay too relaxed for this exam :/ No idea why :tongue: Good luck on S2 tomorrow as well! :smile:


Same, I feel like I'm going to be complacent and then be hit by some awful question in the exam :tongue: Good luck to you too!
Reply 44
That's was horrible. Couldn't do question 4 for gods sake.


Posted from TSR Mobile
I may have gotten question 8(II) wrong :frown: I know it was a small number but were we meant to work out P(Type-II) using using the significance level or critical value?


Posted from TSR Mobile
Original post by Sam596
That's was horrible. Couldn't do question 4 for gods sake.


Posted from TSR Mobile


Was that the one about Type-1/2 yprobabilities?

Edit: just realised it is. Dw I don't think a lot of people got that

Posted from TSR Mobile
(edited 8 years ago)
I know I've screwed up question 8(ii) but *touchwood* the rest went okay.
Reply 48
Question 4 was two binomial approx, one poisson one normal right? iirc it was a normally distributed function so type 1 error probability is the significance level and type 2 was given, then you modelled it as a binomial function (it either has an error or doesnt) and do the standard for approximating

that was a cute context from ocr on question 2 - dead bunnies along a road?

also is anyone feeling confident in their 8ii answer? im not sure mine is right but it was the only thing i could think of (I'll type it up once im not on mobile)
Original post by ms8061
Question 4 was two binomial approx, one poisson one normal right? iirc it was a normally distributed function so type 1 error probability is the significance level and type 2 was given, then you modelled it as a binomial function (it either has an error or doesnt) and do the standard for approximating

that was a cute context from ocr on question 2 - dead bunnies along a road?

also is anyone feeling confident in their 8ii answer? im not sure mine is right but it was the only thing i could think of (I'll type it up once im not on mobile)


I got poisson and then normal approximations for Q4 too.

Very last question I did

(1/3*P(X<8|p=0.5) + 1/3*P(X<8|p=0.7) )* 4 and got 0.931 or something like that
LIKE WHAT WAS UP WITH THAT EXAM!!!
Question 4, couldnt even attempt!!!
I felt pretty good about all my answers, ill post as many as i can remember.

a=6 then a=1.5 for cont dist qn

Mean = 146, S.D=2 for normal qn

Very last qn was something like:
1/3(0.6 + 0.03) <-- i really cant remember
So P(type 2 error) = 0.23 ish

So P(X at least 1 out of 4) = 1 - P(X=0) = 1- (1-0.23)^4
(edited 8 years ago)
Original post by ms8061
Question 4 was two binomial approx, one poisson one normal right? iirc it was a normally distributed function so type 1 error probability is the significance level and type 2 was given, then you modelled it as a binomial function (it either has an error or doesnt) and do the standard for approximating

that was a cute context from ocr on question 2 - dead bunnies along a road?

also is anyone feeling confident in their 8ii answer? im not sure mine is right but it was the only thing i could think of (I'll type it up once im not on mobile)


Original post by rich1334
I got poisson and then normal approximations for Q4 too.

Very last question I did

(1/3*P(X<8|p=0.5) + 1/3*P(X<8|p=0.7) )* 4 and got 0.931 or something like that


Yup, I got poisson and normal distributions too.

I reckon I've got 2 marks for 8(ii) as I worked out the P(Type II) at 0.5 and 0.7 but what I've done after that was just clutching at straws. My friend made it a binomial distribution?
I'm pretty sure my method is partially wrong, could very much be a binomial

Original post by Molly_xox
Yup, I got poisson and normal distributions too.

I reckon I've got 2 marks for 8(ii) as I worked out the P(Type II) at 0.5 and 0.7 but what I've done after that was just clutching at straws. My friend made it a binomial distribution?
Reply 54
Thank god I'm not the only one who found Q4 impossible.


Posted from TSR Mobile
Original post by Molly_xox
Yup, I got poisson and normal distributions too.

I reckon I've got 2 marks for 8(ii) as I worked out the P(Type II) at 0.5 and 0.7 but what I've done after that was just clutching at straws. My friend made it a binomial distribution?


once you found P(type 2 error) about 0.23 i think . you had to find the probability of getting at least 1 out of 4 tests. so its a binomial B(4 , 0.23)
Reply 56
Did question 1 ask for standard deviation or variance? Got sigma = 2 but don't wanna lose a cheap mark for not stating variance =4...
Yeah that looks good. I stupidly multiplied my P(Type II) by 4 instead of treating it like binomial. Oh well, probably got )2/3 marks for it

Original post by tokopoko
I felt pretty good about all my answers, ill post as many as i can remember.

a=6 then a=1.5 for cont dist qn

Mean = 146, Var =4 for normal qn

Very last qn was something like:
1/3(0.6 + 0.03) <-- i really cant remember
So P(type 2 error) = 0.23 ish

So P(X at least 1 out of 4) = 1 - P(X=0) = 1- (1-0.23)^4
Original post by Tomh97
Did question 1 ask for standard deviation or variance? Got sigma = 2 but don't wanna lose a cheap mark for not stating variance =4...


I thought it asked for standard deviation too!
Original post by Molly_xox
I thought it asked for standard deviation too!


It asked for u and sigma

Quick Reply