Normal Distributions

[costargh]

Hmmm ok... so we can't really find out what percent of people got 172/180 or higher?

[Mao]

you can:



conditional probability! =D

[costargh]

So whats the answer.... lol... Mao, you know I am mathematically retarded.

And just to ease my mind that its correct could you do it for like percentage of people that got 178/180?

[Mao]

172+: 1.45%
178+: 0.32%

(another problem with discrete data... do we count a score such as 170 to be 168~170? or 170~172? either ways anomaly at ends...)

[costargh]

THANKS MAOOO

[excal]

Hah, you should also remember these:

1σ (s.d.) away from the mean on both sides is 68% of values
2σ is 95%
3σ is 99%

They can ask you this in a tech free exam.

[Mao]

Hah, you should also remember these:

1σ (s.d.) away from the mean on both sides is 68% of values
2σ is 95%
3σ is 99%

They can ask you this in a tech free exam.

if you use this in the tech free exam you'd get it wrong

3σ is 99.7% in VCELand

[excal]

Damn study designs.

If you're gonna round to 2 s.f., why not KEEP it that way!

[costargh]

This question is specifically for Mao considering he has been able to give me an answer for the other ones.

166/180. top what %?

[excal]

Pr(X > 166)

You do not need to include an upper X < 180 bound as you are saying 'EVERYONE above 166'

[Collin Li]

You can argue that there should be noone above 180 though.

However, I did it this way because it seemed that VCAA was using the same method:


Putting an upper bound would have yielded approximately 7.8% instead.

[Mao]

same method as before, 2.88%

[cara.mel]

172+: 1.45%
178+: 0.32%

(another problem with discrete data... do we count a score such as 170 to be 168~170? or 170~172? either ways anomaly at ends...)

You count 170 as 169-171 if your discrete data is only every 2nd number which I think you're suggesting there.
But in reality people can get 171/180 so you would count 170 as ~ 169.5-170.5
i lernt dis in mth1030 so it iz 1052.7% more accurate den vce infoz lol.

[costargh]

Well, I don't know which figure is correct.
So far I've been told it is
around 5%
around 7.8&
around 2.88%

:S

[Collin Li]

Well, I don't know which figure is correct.
So far I've been told it is
around 5%
around 7.8&
around 2.88%

:S

7.8% is what you get if you used Mao's method to evaluate scores above 152. However, VCAA quoted that scores above 152 corresponded to the top 10% (which would be using the simpler method).

You get 5.5% using VCAA's method for scores above 166. You get 2.8% using Mao's method.