CONFIDENCE

INTERVALS
FOR A SINGLE POPULATION MEAN WITH
UNKNOWN POPULATION STANDARD
DEVIATION
LEARNING
OBJECTIVE
Calculate and interpret confidence
intervals for estimating a population
mean where the population standard
deviation is unknown.

2
 “ A small S.sample
William
inaccuracies
interval.
Goset
His
in the
of the Guinness
and
Dublin, Ireland
size caused
(1876–1937)
experiments with hops
confidence
brewery
barley
few samples.
in very
produced

3 Presentation title
” 20XX
 “
Just replacing
He found
produce
that σ
STUDENT’S
”the ” actual
on the sample
depends accurate
T-DISTRIBUTION size
results when
calculate a confidence interval.
he
s
with ” distribution
” did not
. tried to

4 Presentation title
” 20XX
FORMULA:

n μ σ x̄ s
Sample Size Population mean Population Sample mean Sample Standard
Standard Deviation
Deviation

t
T-score
 EXAMPLE
A researcher wants to estimate the average number of hours
SITUATION graduate school students in Zamboanga del Norte spend studying
per week.

Sample Size (n): 12 graduate students

DATA Construct a 95% confidence interval for the mean number of
hours.

To find the confidence interval, you need the:

*SAMPLE MEAN
*EBM or error bound for the population mean/margin of error.
Weekly Study Hours For Each Student
9.5, 12, 8.8, 11.5, 15, 10.8, 9.7 , 5,11 , 9.5, 14, 4

Find the Sample Mean (x̄ ):

9.5 + 12 + 8.8 + 11.5 + 15 + 10.8 + 9.7 + 5 + 11 + 9.5 + 14 + 4 = 120.8/12
x̄ = 10.06667

Compute the deviations from the mean for each data

point:
(9.5 - 10.06667)2= 0.3211 Sample Standard Deviation (S):
(12 - 10.06667)2= 3.7377 √10.1697 = 3.189
(8.8 - 10.06667)2= 1.6044
. . .

Find the Sample Variance

0.3211 + 3.7377 + 1.6044 +. . . = 111.867/12-1
= 10.1697
EBM- Error bound for the population mean
Formula: t x s/√n
t - t-score
s- sample standard deviation
n- sample size

To find the confidence interval, we need to find the t-score for the 95% confidence
The Degrees of Freedom for the t-distribution is n−1.
interval.
n-means
This Samplethat weSize
need to find the t-score so that the area in the tails
is 1−0.95 = 0.05
12−1 = 11
t-score= 2.201
EBM- Error bound for the population mean
LIMITS FOR THE CONFIDENCE
Formula: t x s/√n INTERVAL
t - t-score
s- sample standard deviation
n- sample size Lower Limit= 10.06667 − 2.0263= 8.04 hours
Upper Limit= 10.06667 + 2.0263= 12.09 hours
2.201 x 3.189 / √12
7.019 / 3.464

= 2.0263 8.04 12.09

hours hours
 INTERPRETATION

8.04 12.09
hours hours

We estimate with 95% confidence that the true population mean hours that graduate
school students in Zamboanga del Norte spend studying per week is BETWEEN
8.04 hours and 12.09 hours.
 CONFIDENCE
INTERVALS
FOR A POPULATION
PROPORTION
LEARNING
OBJECTIVE
Calculate and interpret
confidence intervals for estimating a
Population Proportion.

13
SYMBOLS

n p̂ C z
Sample Size Sample Confidence Z-score
Proportion Level
a confidence interval for a population proportion is
constructed by taking a sample of size n from the population,
calculating the sample proportion p̂ and then adding and
subtracting the margin of error from p̂ to get the limits of the
confidence interval.
 EXAMPLE
Suppose that a market research firm is hired to estimate the percent of
adults living in a large city who have cell phones. Five hundred
SITUATION randomly selected adult residents in this city are surveyed to determine
whether they have cell phones. Of the 500 people surveyed, 421
responded yes – they own cell phones.

Sample Size (n): 500 people surveyed

Success: 421 who responded Yes
DATA Construct a 95% confidence interval for the proportion of adult residents
of this city who have cell phones.

To find the confidence interval, you need the:

SAMPLE PROPORTION
MARGIN OF ERROR.
 p̂ = x/n where x= number of successes, n= sample size, n-x= failures
1- p̂ = sample proportion of failures or

is the sample proportion.

• p̂ is used to estimate the unknown population proportion p.

• The estimated sample proportion p̂ is used because p is the unknown quantity we
are trying to estimate with the confidence interval.
Calculating the Margin of Error
Other way:

AREA= 1+CL
2

1.96
 For a 90% confidence interval: z-score ≈ 1.64
For a 91% confidence interval: z-score ≈ 1.69
For a 92% confidence interval: z-score ≈ 1.75
For a 93% confidence interval: z-score ≈ 1.81
For a 94% confidence interval: z-score ≈ 1.88
For a 95% confidence interval: z-score ≈ 1.96
For a 96% confidence interval: z-score ≈ 2.05
For a 97% confidence interval: z-score ≈ 2.17
For a 98% confidence interval: z-score ≈ 2.32
For a 99% confidence interval: z-score ≈ 2.58
19 Presentation title 20XX
Calculating the Margin of Error
Other way:

AREA= 1+CL
2

1.96
Calculating the Confidence Interval
1.96

1.96

1.96
 INTERPRETATION
Question:

Is it reasonable to conclude that 85%

of the adult residents of this city have
cell phones?

Yes, because 85% is inside the

confidence interval.

We are 95% confident that the proportion of adult residents of this city
who have cell phones is between 81% and 87.4%.
Thank you