Académique Documents
Professionnel Documents
Culture Documents
a Population Proportion
A Confidence Interval for a Population Proportion,p
The examples below report proportions. Note that each variable is
measured with the nominal scale of measurement.
The career services director at Sehir University reports that 80
percent of its graduates enter the job market in a position
related to their field of study.
A company representative claims that 45 percent of Burger King
sales are made at the drive-through window.
A survey of homes in the Uskudar area indicated that 85
percent of the new construction had central air conditioning.
A recent survey of married men between the ages of 35 and 50
found that 63 percent felt that both partners should earn a
living.
A Confidence Interval for a Population Proportion
.053 p .107
Adjusted (1 – )100% Confidence Interval for a
Population Proportion, p when np is small
p 1 p
p z 2
n4
x2
p
where n 4 is the adjusted sample proportion of
observations with the characteristic of interest, x is the
number of successes in the sample, and n is the sample
size.
Determining the Sample Size
X μ
σ
z
n
Determining Sample Size
Using ( X μ)
Z X μ Z*
σ n
n
Sampling Error, or
margin error ME
Z
2 2
n 2
ME
To determine the required sample size for the mean, you
must know:
1. The desired level of confidence (1 - ), which
determines the critical Z value
2. The acceptable sampling error (margin of error), ME
3. The standard deviation, σ
Example 1
æ z ×s ö
2
n =ç ÷
è E ø
æ (2.58)(20) ö
2
n =ç ÷ = 107
è 5 ø
Example 3
(z 2 )2 2
n
(SE)2
1.96 400
2 2
50
2
245.86 246
To estimate population proportion p
Sample Size Determination for 100(1 – )
% Confidence Interval for p
In order to estimate p with a sampling error ME and with
100(1 – )% confidence, the required sample size is
found by solving the following equation for n:
p(1 p)
z ME
n
n Z p (1 - p)2
ME
Example 1
n = p (1- p ) ç ÷
èEø
2
1.96
n (.30 )(. 70 ) 897
.03
Example 2
æzö
2
n = p (1- p ) ç ÷
èEø
æ 1.645 ö
2
n = (.5)(1-.5) ç ÷ = 67.65
è .10 ø
n = 68 cities
So, if there is no estimation for p…
Finite Population Correction for
Simple Random Sample
Finite-Population Correction Factor (FPC)
N n p(1 p) N n
x p
n N n N
Rule of Thumb for Finite Population Correction Factor
C.I. for the Mean () C.I. for the Mean ()
N n s N n
xz xt
n N n N
p(1 p) N n
pz
n N
CI for Mean with FPC – Example
s N n
xt
n N
$75 250 40
$450 t
40 250
$75 250 40
$450 1.685
40 250
$450 $19.98 .84
$450 $18.31
($431.69, $468.31)
It is likely tha t the population mean is more than $431.69 but less than $468.31.
To put it another wa y, could the population mean be $445? Yes, but it is not
likely tha t it is $425 because the value $445 is within th e confidence
interval and $425 is not within the confidence interval.
Finite Population Correction Factor Example
Since
n 60 .086
N 700
is greater than .05 use the finite correction
factor
Example