# Plot the histogram of loge(area) to show that it is approximately Normal.

• May 17th 2011, 01:33 AM
Jon123
Plot the histogram of loge(area) to show that it is approximately Normal.
Hello!

I am not clearly understanding this specific question. if you cld please explain.

I am not providing the data.

If we take the natural log of the area column of the forest fire data, we find that it is approximately Normally distributed. We will call this set of values loge(area).

1. Plot the histogram of loge(area) to show that it is approximately Normal.

Do i just do a histogram? is the loge exchanged to represent forest fire data?

2. Compute the mean and standard deviation of loge(area).

This is pretty straight fwd but must check. The term 'compute' does that mean anything specifically? is that an estimate with a similar resulting answer?? or they just want straight up whatever the mean and 's' is?

3. Assuming that loge(area) follows a Normal distribution with a population mean and population standard deviation equal to the mean and standard deviation from part (i), find the probability that a randomly sampled value from the population of loge(area) will be between 0 and 2.

5. Is there a difference in the previous two answers? Explain why.
Thanks Heaps if you get this!!! :)
• May 17th 2011, 03:27 AM
SpringFan25
1.
I dont understand the statement "loge exchanged to represent forest fire data".

My interpretation of your question is that you should find the log of each data point and draw a histogram of the results.

2.
"Compute" means "do" or "calculate" i think.

you dont seem to have asked any questions about 3 or 5.
• May 17th 2011, 03:59 AM
Jon123

for question 1. i dont think it needs to be converted in logarithms because we havent learnt log all semester.

for question 3. i dont understand the log part and also what it means from 0 and 2. very confusing...

there is 150 data entries. ranginging stastiscally lets say from 0 to 250.
for Q3. do they just want whatever the data is ranging from 0 to 2. in that case there is 31 data entries from 0 to 2 ???
• May 17th 2011, 04:50 AM
CaptainBlack
Quote:

Originally Posted by Jon123
Hello!

I am not clearly understanding this specific question. if you cld please explain.

I am not providing the data.

If we take the natural log of the area column of the forest fire data, we find that it is approximately Normally distributed. We will call this set of values loge(area).

1. Plot the histogram of loge(area) to show that it is approximately Normal.

Do i just do a histogram? is the loge exchanged to represent forest fire data?

Yes you just plot the histogram of \$\displaystyle log_e\$ of the data

Quote:

2. Compute the mean and standard deviation of loge(area).

This is pretty straight fwd but must check. The term 'compute' does that mean anything specifically? is that an estimate with a similar resulting answer?? or they just want straight up whatever the mean and 's' is?
It just means calculate the mean and standard deviation.

Quote:

3. Assuming that loge(area) follows a Normal distribution with a population mean and population standard deviation equal to the mean and standard deviation from part (i), find the probability that a randomly sampled value from the population of loge(area) will be between 0 and 2.

5. Is there a difference in the previous two answers? Explain why.
No answer to 5 as you have not posted 4.

CB
• May 25th 2011, 03:59 AM
JMan69
What do you do for the last few questions?

3. Count the fraction of samples from the forest fire data where loge(area) lies between 0 and 2.
4. Assuming that loge(area) follows a Normal distribution with a population mean and population
standard deviation equal to the mean and standard deviation from part (i), find the probability
that a randomly sampled value from the population of loge(area) will be between 0 and 2.
5. Is there a difference in the previous two answers? Explain why.

Cheers