Scribd
Upload
24 views1 page

Calculator Use Part17

If we continually sample groups of 12 students, 90% of the samples will have a mean sleep time between 5.288 and 6.379 hours of sleep. The margin of error is 0.545 hours. When given this exam to the same sample sizes repeatedly, 98% of the samples would have a difference between their averages of 0.154 to 5.646. This interval reflects being 98% confident that the mean difference between the two exam methods lies within this range, with a margin of error of 2.746. The t confidence interval for 2 samples option is used to construct a confidence interval for the difference between the means of 2 samples when you have the sample means, sizes, and standard deviations,

Uploaded by

kunichiwa
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
24 views1 page

Calculator Use Part17

If we continually sample groups of 12 students, 90% of the samples will have a mean sleep time between 5.288 and 6.379 hours of sleep. The margin of error is 0.545 hours. When given this exam to the same sample sizes repeatedly, 98% of the samples would have a difference between their averages of 0.154 to 5.646. This interval reflects being 98% confident that the mean difference between the two exam methods lies within this range, with a margin of error of 2.746. The t confidence interval for 2 samples option is used to construct a confidence interval for the difference between the means of 2 samples when you have the sample means, sizes, and standard deviations,

Uploaded by

kunichiwa
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 1

Conclusion: if we continually sample groups of 12 students, 90% of the samples

will have a mean sleep time between 5.288 and 6.379 hours of sleep. The margin
of error is 6.379 - 5.833 = .545 hours.
9. 2-SampZInt - z confidence interval for 2 samples - since this uses the premise that we have
2 population standard deviations (quite rare), we will not use this option.
* 0. 2 SampleTInt - t confidence intervals for 2 samples 1 ! 2 .
When to use: you have 2 sample means and sample standard deviations with the same or
different sizes and you wish to find a confidence interval for 1 ! 2 . It is assumed that
both samples are normally distributed.
2

s
s
You are calculating: ( x1 ! x2 ) t * 1 + 2
n1 n2

Note that if you do this by hand, you will get a slightly different answer than the calculator
answer because the hand method requires the degrees of freedom be found by subtracting 1
from the smaller of the two n values while the calculator uses a more exact method.
Example: Two groups took the same final exam, one using a calculator, the other not. The
statistics are below. Construct a 98% confidence interval for the difference of the
method averages.
With calculator
Without calculator

x
78.8
75.9

n
28
23

s
3.7
4.3

Conclusion: if we were to continally give this exam to the same sample sizes,
98% of the samples would have a difference between their averages to be .154
to 5.646. This is the same as saying that we are 98% confident that the mean
difference between the two methods lies in the interval .154 to 5.646. The margin
of error is 5.646 - (78.8 - 75.9) = 2.746
* A. 1-PropZInt - confidence interval for an unknown proportion of successes.
When to use: You have a sample size of n and have x successes. You want to predict the
proportion of success to an indicated level of confidence. We assume that the data is from an
www.MasterMathMentor.com

- 17 -

Stu Schwartz

You might also like