Scribd
Upload
26 views

Interference (Workshop 10) Winston Boon - ID: n9450947 Q (1a) Confidence Interval

This document discusses confidence intervals and hypothesis testing. It provides an example of calculating a 95% confidence interval for a sample mean of 110.5 with a standard deviation of 3 and a sample size of 10. The confidence interval was calculated to be 108.354 to 112.646. A hypothesis test was also conducted to test if the sample mean was different from the actual mean of 110. With a sample size of 10, there was not enough evidence to reject the null hypothesis that the means were equal. When the sample size was increased to 200, keeping all other values the same, the confidence interval narrowed and the p-value was low enough to reject the null hypothesis, showing that sample size impacts the results of these statistical tests.

Uploaded by

Winston Boon
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
26 views

Interference (Workshop 10) Winston Boon - ID: n9450947 Q (1a) Confidence Interval

This document discusses confidence intervals and hypothesis testing. It provides an example of calculating a 95% confidence interval for a sample mean of 110.5 with a standard deviation of 3 and a sample size of 10. The confidence interval was calculated to be 108.354 to 112.646. A hypothesis test was also conducted to test if the sample mean was different from the actual mean of 110. With a sample size of 10, there was not enough evidence to reject the null hypothesis that the means were equal. When the sample size was increased to 200, keeping all other values the same, the confidence interval narrowed and the p-value was low enough to reject the null hypothesis, showing that sample size impacts the results of these statistical tests.

Uploaded by

Winston Boon
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
You are on page 1/ 2

Interference (Workshop 10)

Q(1a) Confidence Interval


x =estimated mean=110.5 ( given)
0=actual mean=110(given)
S=standard deviation=3
N=sample space=3
Given :S 2=9, 9=3 ; 95 confidence interval
Find
=1confidence=10.95=0.05
Find t multiplier values
t

Winston Boon | ID: n9450947

( 2)

N1, 1

t 9 , 0.975
Use ttable find t multiplier using values
t multiplier ( t 9 , 0.975 ) =2.262
s
3
95%CI : x t multiplier
=95 %CI :110.5 2.262
N
10
( 108.354,112.646 )
95 confident that isinterval
Q(1b) Hypothesis Testing
x u0
Calculate t test =
s
N
110.5110

=0.527046
3
10
|t test|<t multiplier=2.262<0.527046

Not enough ev idence for rejecting null hypothesis , thususing MATLAB Pvalue
with 2( 1tcdf ( t , N ) )
P=0.6097
'
Rvalue > =0.6097> 0.05(do n t neglect null hypothesis)
Part (c)
If all measurements come out to be the same,
x =110.5, S=3, =110, Sample 200
t
; given =0.05
N1,1

Refer table of value ;=1.9720


S
95 CI : x t multiplier
N
3
110.5 1.972
200
( 110.082, 110.918 )
110.5110
=2.36702
|t test|=
3
200
|t test|>t multiplier
Because 2< t test <3, able support the rejection of null hypothesis
Can put into MATLAB:

2 1P ( t <|t test|)

2[ 1tcdf ( t , N ) ]
2[ 1tcdf ( 0.5270,200 ) ]
P=0.0194
Pvalue <=0.0194 <0.05
Reject null hypothesis
Are your results the same as in Part (b)? If not why?
The results changed in part C, as the sample size increases. Larger sample sizes essentially
come with smaller, more accurate confidence intervals and smaller p-values. Larger sample
sizes similarly give accurate answers, thus the results in part b, are more accurate than in Part
(c), because of the samples size, hence why the results differ.

You might also like