A teacher wants to compare the mean geology scores of two different classes. She is testing the null hypothesis that there is no difference in the population mean scores of the two classes. The difference of the sample means is 51.4. If the standard deviation of the distribution of the difference of sample means is 16.66, what is the 95% confidence interval for the population mean difference?

between -33.2 and +33.2

between -49.9 and +49.9

between -102.8 and +102.8

between -154.2 and +154.2

Question

A teacher wants to compare the mean geology scores of two different classes. She is testing the null hypothesis that there is no difference in the population mean scores of the two classes. The difference of the sample means is 51.4. If the standard deviation of the distribution of the difference of sample means is 16.66, what is the 95% confidence interval for the population mean difference?



between -33.2 and +33.2



 
between -49.9 and +49.9



 
between -102.8 and +102.8



 
between -154.2 and +154.2

anonymous · Answer

@perl

anonymous · Answer

@SolomonZelman

perl · Answer

the z score of the 95% confidence interval is 1.96

perl · Answer

so you want

51.4 +/-  1.96 * 16.66

perl · Answer

interval : ( 51.4 - 1.96*16.66 ,  51.5 + 1.96 * 16.66 )

perl · Answer

but thats not one of the choices given

anonymous · Answer

18.75 , 84.15 ,

perl · Answer

yes thats what i got

nincompoop · Answer

hmmm

nincompoop · Answer

wow
I don't think this is done

perl · Answer

none of the choices you gave make sense , though

perl · Answer

you sure you copied this correctly

perl · Answer

@nincompoop  do you agree with my approach, i am not completely certain.

nincompoop · Answer

agreed

perl · Answer

thx ^^

nincompoop · Answer

can we try this with a different approach
I don't think it is as straight-forward

perl · Answer

right, thats why i was uncertain. also there isnt much information given, such as the size of the samples

nincompoop · Answer

I am thinking of solving it based on the MSE given 16.66 
if that is even possible

perl · Answer

MSE is mean squared error? http://en.wikipedia.org/wiki/Mean_squared_error

nincompoop · Answer

ye

perl · Answer

its possible

nincompoop · Answer

LAUGHING OUT LOUD

perl · Answer

there might be some caveat in the directions or something, assume such and such

nincompoop · Answer

we're going to assume that our sample sizes are the same $n_1 = n_2 $

perl · Answer

ok

nincompoop · Answer

now we need the variance ... LAUGHING OUT LOUD wow this is getting messier

perl · Answer

haha, yes :)

perl · Answer

and the squared bias of the estimator?

nincompoop · Answer

is 16.66 in percent?

perl · Answer

nope, just a number i believe

nincompoop · Answer

this is weird
I am just going to go back to agreeing with your first solution and not beat my head on this one

nincompoop · Answer

he has weird choices and I thought I can find justifications for that HAHA

perl · Answer

:) 
most of the questions he asked seemed odd, i am starting to wonder about this

perl · Answer

but i don't have enough experience to say this definitively