Normal distribution - Finding mean and standard deviation

AI Thread Summary
The discussion focuses on calculating the mean and standard deviation of a high jumper's performance based on her success rates at different heights. The jumper can clear 1.78m 20% of the time and 1.65m 70% of the time, leading to the need for statistical analysis using Z-scores. There is a disagreement on the Z-values derived from the normal distribution tables, with one participant obtaining Z1 = 0.8779 and Z2 = -0.5534, while another suggests Z1 should be 0.875 and Z2 = -0.875. Clarification on the correct Z-values is sought, as it affects the final calculations for mean and standard deviation. Ultimately, the conversation highlights the importance of correctly interpreting and using statistical tables in probability calculations.
James...
Messages
25
Reaction score
0

Homework Statement



A high jumper knows from experience that she can clear a height of at least 1.78m once in 5 attempts. She also knows that she can clear a height of at least 1.65m on 7 out of 10 attempts.
Find to 3 dp the mean and standard deviation of the heights the jumper can reach

Homework Equations





The Attempt at a Solution



This is a question on an online tutorial. I work it out slightly differently and get different answers.

After rounding I get

mean of 1.700m
standard deviation of 0.091m


Would anyone be able to double check for me, it's using statistics tables so I'm not sure how to put all my working down. My exam is this coming week and I want to be sure I am using the tables correctly.

I suppose the main bits I would like to check are

\Phi(Z1) = 0.8

\Phi(-Z2) = 0.7

I get Z1 = 0.8779 and Z2 = -0.5534

This is where we get different answers. I use Neaves tables and do the "inverse normal function" to gain Z, where as he uses the "c.d.f of the standard normal distribution table", finds a probability valuse as close to 0.8 and 0.7 as possible and then takes the corresponding Z value.

Any help would be appreciated.

James
 
Physics news on Phys.org
If a normal distribution has mean \mu and standard deviation \sigma, then the "standard normal variable" is z= (x- \mu)/\sigma.

What you are saying is that x= 1.78 corresponds to z= 0.8779 and x= 1.65 corresponds to z= -.05534.

So you need to solve the equations
\frac{1.79- \mu}{\sigma}= 0.8779
and
\frac{1.65- \mu}{\sigma}= -0.05534

Solve those two equations for \mu and \sigma.

Dividing one equation by the other will immediately eliminate \sigma and leave a linear equation for \mu.
 
Last edited by a moderator:
Thanks for the reply, but I get that part. I was wondering about the values of 0.8779 and -0.5534

I think they are correct for the corresponding probabilities but the answer got different values.

So it's actually the Z1 and Z2 values I need checking. After that, I'm fine.

CHeers
James
 
A table of the normal distribution is available online at
http://www.math.unb.ca/~knight/utility/NormTble.htm

I would interpret "she makes this height once in 5 attempts" as meaning she makes it 20% of the time so misses 80% of the time and I would look up z corresponding to .8- on this table that is z= .875- that height is .875 standard deviations above her mean. Similarly, making a height "7 out of 10 times" means she misses it .3 times so I would look up z corresponding to .3. This particular table only gives positive z so would look up, instead, .5+ .3= .8 which is what we already have- it was z=.875. The z corresponding to .3 is -.875.

My .875 corresponds, to the accuracy of my table, to your .8779 but my -.875 is nowhere near your -.5534. Because .3 and .8 are equally spaced about .5, I am inclined to believe my results.
 
Last edited by a moderator:
Many thanks for the reply, and you are correct. I was using the table wrong and now understand how it all works properly. Thanks for taking the time to reply.

JAmes
 
Since ##px^9+q## is the factor, then ##x^9=\frac{-q}{p}## will be one of the roots. Let ##f(x)=27x^{18}+bx^9+70##, then: $$27\left(\frac{-q}{p}\right)^2+b\left(\frac{-q}{p}\right)+70=0$$ $$b=27 \frac{q}{p}+70 \frac{p}{q}$$ $$b=\frac{27q^2+70p^2}{pq}$$ From this expression, it looks like there is no greatest value of ##b## because increasing the value of ##p## and ##q## will also increase the value of ##b##. How to find the greatest value of ##b##? Thanks
Back
Top