The Student Room Group

HomeWork is way too hard this week...another q

Hi guys

Gradually I'm working through my stats homework question by question but they seem to just be getting harder. The question I have below, I don't even know where to start...can anyone give me so,e advice as to what I should be looking at?

"The aptitude test scores of applicants to a university graduate program are normally distributed with mean 500 and standard deviation 60. If the university wishes to set the cut-off score for grad programs so that only the top 10 % of applicants qualify for admission, what is the required cut of score? What percentage of applicants have test scores within two standard deviations of the mean?"

So far, all I have come up with is
10 % of 500 is 50
2 SD from the mean is 380 & 620
Square root of 60 is 7.74 ( does that mean 7.74 is the variance?)


And that really is all I have. I don't know where to go with this or how to figure it out, if anyone can give me some advice or hints on how to figure this question out, it really would be appreciated
(edited 9 years ago)

Scroll to see replies

Original post by Fyer1234
Hi guys

Gradually I'm working through my stats homework question by question but they seem to just be getting harder. The question I have below, I don't even know where to start...can anyone give me so,e advice as to what I should be looking at?

"The aptitude test scores of applicants to a university graduate program are normally distributed with mean 500 and standard deviation 60. If the university wishes to set the cut-off score for grad programs so that only the top 10 % of applicants qualify for admission, what is the required cut of score? What percentage of applicants have test scores within two standard deviations of the mean?"

So far, all I have come up with is
10 % of 500 is 50
2 SD from the mean is 380 & 620
Square root of 60 is 7.74 ( does that mean 7.74 is the variance?)


And that really is all I have. I don't know where to go with this or how to figure it out, if anyone can give me some advice or hints on how to figure this question out, it really would be appreciated


The variance is the square of the standard deviation, not the square root.
How many standard deviuations above the mean will cut off 10%?
(edited 9 years ago)
Reply 2
Original post by brianeverit
The variance is the square of the standard deviation, not the square root.
How many standard deviuations above the mean will cut off 10%?


Thanks

but i I don't know what the 10% is. 10% of 500? I'm really struggling with this one as I'm not sure what direction to take

So if the standard deviation is 60, the variance must be 3600...
(edited 9 years ago)
Reply 3
Original post by brianeverit
The variance is the square of the standard deviation, not the square root.
How many standard deviuations above the mean will cut off 10%?


I havent ent progressed much but can anyone tell me if any of these ideas arson the right track:

500 is the mean so 2 standard deviations from the mean account for 95%. ( answer to 2nd question)

3 sd from the mean account for 99% so the highest number within the spread should be 680 and the lowest 320.

the highest 10% have to score over 568 and between 680.

am I getting closer?
Original post by Fyer1234
I havent ent progressed much but can anyone tell me if any of these ideas arson the right track:

500 is the mean so 2 standard deviations from the mean account for 95%. ( answer to 2nd question)

3 sd from the mean account for 99% so the highest number within the spread should be 680 and the lowest 320.

the highest 10% have to score over 568 and between 680.

am I getting closer?


Not really.
1.282 standard deviations above the mean cuts off the top 10%.
where did you get 568 from?
Reply 5
Original post by brianeverit
Not really.
1.282 standard deviations above the mean cuts off the top 10%.
where did you get 568 from?


Thanks

Lol to be honest i am trying everything at the moment.

3sd from the mean accounts for 99% = 680 if sd is 60.

10% of 680 is 68

500+68 = 568

How did you get the 10% answer?


Posted from TSR Mobile
Is this S1 homework?
Original post by Fyer1234
Thanks

Lol to be honest i am trying everything at the moment.

3sd from the mean accounts for 99% = 680 if sd is 60.

10% of 680 is 68

500+68 = 568

How did you get the 10% answer?


Posted from TSR Mobile


From the normal distriobution tables.
Reply 8
Original post by brianeverit
From the normal distriobution tables.


Thanks

this is the first time ive been made aware of this table.

so 1.282 standard deviations from the mean = 77

500 is the mean, so is the answer to the first part of the question 577?
Reply 9
Original post by Muttley79
Is this S1 homework?


It's elementary statistics in 1st year undergrad.
Reply 10
Original post by Fyer1234
It's elementary statistics in 1st year undergrad.


If you have not done statistics before , my advice is to borrow or buy the standard EDEXCEL stats books and look at some examples ...
You need to learn about standard normal and Z scores. If you google you may find an online pdf of the Edexcel S1 textbook.
Reply 12
Thanks guys

Can anyone give me some advice on how I figure out the answers for the question I posted? (Eg what I have to calculate) It seems I have a lot to learn but this question is so baffling
Reply 13
Original post by Fyer1234
Thanks guys

Can anyone give me some advice on how I figure out the answers for the question I posted? (Eg what I have to calculate) It seems I have a lot to learn but this question is so baffling


read posts 11 and 12
Reply 14
Original post by TeeEm
read posts 11 and 12


Ok thanks

S o in order to figure this question out, I must learn about z-scores and standard normal
Reply 15
Original post by Fyer1234
Ok thanks

S o in order to figure this question out, I must learn about z-scores and standard normal


you need to learn a methodology so some simpler books with examples will help you.
Maybe try looking at some worked solutions on examsolutions?

S1 Normal distribution
Reply 17
Original post by TeeEm
you need to learn a methodology so some simpler books with examples will help you.


mmm thanks guys

looking at the z-score, it's not so hard to calculate. It's just x - mean / sd

however I can't see how that relates to the question I have for homework...

I can see how the empirical rule can fit in here somewhere but the z-score I can't see how.

im not asking for the answer but can someone please explain how this question is to be calculated, things to be thought of etc, am I looking at this question wrong?
Original post by Fyer1234
mmm thanks guys

looking at the z-score, it's not so hard to calculate. It's just x - mean / sd

however I can't see how that relates to the question I have for homework...

I can see how the empirical rule can fit in here somewhere but the z-score I can't see how.

im not asking for the answer but can someone please explain how this question is to be calculated, things to be thought of etc, am I looking at this question wrong?


The z-scores are a way of standardising the data so that you can use the tables. i.e. You can now look up that z score in the normal distribution table.
Reply 19
Original post by brittanna
The z-scores are a way of standardising the data so that you can use the tables. i.e. You can now look up that z score in the normal distribution table.


Thanks

but I do t have th z-score because I don't know what value or how to find the value I need to minus the mean with...?

Quick Reply

Latest