Module 8
Lesson 1: Sample Proportion
Learning Competency:
Quarter 3- Statistics and Probability
Surveys
- are common to elicit people’s perceptions about emerging
issues.
- provide information to the public so that they may be guided
accordingly in their day to day actions.
- For example, a TV network conducts a public opinion survey on
issues that relate to the President’s policies.
- Many decisions are based on countable observations
obtained from surveys. However, to be credible &
meaningful, these countable observations should represent a
random sample from a target population.
Solving Population Proportion & Sample Proportion
Let: p- population proportion; 𝑝̂- (“p hat”) sample proportion
𝑿
- We use: 𝑝̂= , where: X- number of members in the sample
𝒏
n- sample size
- The complement of 𝑝̂ is 𝑞̂ (read as “q hat”)
given by: 𝑞̂ = 1 ̶ 𝑝̂
Example
In a job satisfaction survey in a certain resort, 200
employees were asked if they were satisfied with their jobs.
There were 128 who responded with a “yes”. What proportion is
this? What proportion responded with a “no”?
Solution :
Step 1. Given: X = 128 n = 200
Step 2. Solution:
Let: 𝑝̂ - be the proportion of “yes” responses ;
𝑞̂ - be the proportion of “no” responses
𝑿 𝟏𝟐𝟖
𝑝̂ = 𝒏
= 𝟐𝟎𝟎
= 𝟎. 𝟔𝟒 𝑞̂ = 1 ̶ 𝑝̂ = 1 ̶ 0.64 = 0.36
Step 3. Conclusion: Therefore, 64% of the 200 (128) employees in a
certain resort were satisfied with their jobs while 36% (72 employees)
were not satisfied with their jobs.
Module 8- Lesson 1 Exercise
1. Find 𝑝̂ and 𝑞̂ given X = 28, n = 110.
2. A total of 150 Gr. 8 students who have access to internet
services were asked if they play online games before they attend
classes. 105 students responded “yes”. What is the population
proportion of students who play video games before attending
classes? What percent do not play video games before attending
classes? Interpret.
Module 8
Lesson 2: Confidence Interval of Population
Proportion
Learning Competency:
Quarter 3- Statistics and Probability
- It has become a common practice to obtain data using surveys as basis
of decision making. As with the estimates of the population mean, we
want to ensure that our interval based on samples contain the true
value of the population proportion.
- The interval depends on the sampling distribution of 𝑝̂. That
is, if we were to draw random samples over and over again,
each time calculating a new interval 𝑝̂, then the frequency
distribution of all the 𝑝̂ values would be p. Thus, 𝑝̂ is an
unbiased estimator of p.
- The formula for computing a large sample confidence interval for
population proportion p is:
ෝ𝒒
𝒑 ෝ ෝ𝒒
𝒑 ෝ
ෝ − 𝒛𝜶Τ𝟐
𝒑 ෝ + 𝒛𝜶Τ𝟐
<𝒑<𝒑
𝒏 𝒏
Example 1
Compute the population proportion confidence interval given n = 300, 𝑝̂ = 0.40, 90%
confidence level.
Solution :
Step 1. Given: n= 300 90% ; 𝑧𝛼Τ2 = ±1.645
n= 300 90% 𝑧𝛼Τ2 = ±1.645
𝑝̂ = 0.40 𝑞̂ = 1 ̶ 𝑝̂ = 1 ̶ 0.40 = 0.60
Step 2. Compute the confidence interval:
𝑝ො 𝑞ො 𝑝ො 𝑞ො
𝑝ො − 𝑧𝛼Τ2 < 𝑝 < 𝑝ො + 𝑧𝛼Τ2
𝑛 𝑛
0.40 0.60 0.40 0.60
0.40 − 1.645 < 𝑝 < 0.40 + 1.645
300 300
0.353 < 𝑝 < 0.446
𝟎. 𝟑𝟓 < 𝒑 < 𝟎. 𝟒𝟓
Step 3. Conclusion: Thus, with 90% confidence, we can say that the interval is from 35% to
45%.
Example 2
A survey of 1200 citizens showed that 715 trust the president. Compute a 95%
confidence interval for the proportion of all citizens who trust the president. Solution :
Step 1. Given: n= 300 90% ; 𝑧𝛼Τ2 = ±1.645
X= 715 n= 1200 95% 𝑧𝛼Τ2 = ±1.96n= 1200
𝑋 715
Find 𝑝̂. 𝑝ො = = = 0.595 𝑜𝑟 𝟎. 𝟔𝟎 Find 𝑞̂. 𝑞̂ = 1 ̶ 𝑝̂ = 1 ̶ 0.60 = 0.40
𝑛 1200
Step 2. Compute the confidence interval:
𝑝ො 𝑞ො 𝑝ො 𝑞ො
𝑝ො − 𝑧𝛼Τ2 < 𝑝 < 𝑝ො + 𝑧𝛼Τ2
𝑛 𝑛
0.60 0.40 0.60 0.40
0.60 − 1.96 < 𝑝 < 0.60 + 1.96
1200 1200
0.572 < 𝑝 < 0.627
𝟎. 𝟓𝟕 < 𝒑 < 𝟎. 𝟔𝟑
Step 3. Conclusion: Thus, with 95% confidence, we can say that the interval from 57%
to 63% contains the true percentage of all citizens who trust the president.
Module 8- Lesson 2 Exercise
Compute the population proportion confidence interval of the
following data.
1. Solve the problem completely.
n = 135, 𝑝̂ = 0.53, 95% confidence
2. A nutritionist wants to know the population proportion of Gr.
11 learners who eat vegetables. Pegged at 99%, as survey
among 1200 respondents was conducted and 500 said they eat
vegetables.
Module 8
Lesson 3: Sample Size
Learning Competency:
Quarter 3- Statistics and Probability
How large should a sample be?
Many researchers find this a problem. This problem should be
addressed carefully because needlessly large samples are a waste of
important resources, while insufficient sample size may lead to poor
results.
Confidence & narrowness of the interval are the two things to
remember when deciding on the quality of the sample size needed.
Formula in determining the minimum
sample size needed when estimating
the population mean is:
𝒛𝜶Τ𝟐 ·𝝈 2
𝒏=
𝑬
Example 1. In a certain barangay, Ann wants to
estimate the mean weight µ, in kilograms, of all six-year old
children to be included in a feeding program. She wants to be
99% confident that the estimate of µ is accurate to within
0.06 kg. Suppose from a previous study, the standard
deviation of the weights of the target population was 0.5kg,
what should the sample size be?
Solution :
Step 1. Given information: 99% confidence , 𝒛𝜶Τ𝟐 = 𝟐. 𝟓𝟕𝟔.
The phrase “accurate to within 0.06 kg” indicates a
narrowed width of the confidence interval thus, the desired
error: E = 0.06 kg. and σ = 0.5 kg.
Solution :
Step 1. Given information: 99% confidence , 𝒛𝜶Τ𝟐 = 𝟐. 𝟓𝟕𝟔.
The phrase “accurate to within 0.06 kg” indicates a
narrowed width of the confidence interval thus, the desired
error: E = 0.06 kg. and σ = 0.5 kg.
•:
𝒛𝜶Τ𝟐 ·𝝈 𝟐 2.576 0.5 2
Step 2. Solve: 𝒏 = 𝑬
=[ 0.06
] = 𝟒𝟔𝟎. 𝟖𝟐 ≈ 𝟒𝟔𝟏
Step 3. So, the required sample size is 461 six-year old
children.
The formula in determining the
minimum sample size needed when
estimating the population proportion is:
𝒛𝜶Τ𝟐 2
𝒏 = 𝒑 ̂𝒒 ̂
𝑬
Reminders:
•In computing the sample size for estimating a population
proportion, there are two situations to bear in mind:
1.1. If some approximation of 𝑝̂ is known, that value
may be used in the formula.
2.2. If no approximation is known, use 𝑝̂ = 0.5. This
value will result in a sample size large enough to
guarantee prediction, given the confidence interval
and the error of estimate. The reason is that
when 𝑝̂ and 𝑞̂ are 0.5 each, the product is at its
maximum.
Example 2. Joy wants to know with 95% confidence
the proportion of households who like to use detergent A. A
previous survey showed that 42% like to use detergent A. Joy
wants to be accurate within 2% of the true proportion. What
sample size does she need?
Solution :
Step 1. Given information: 95% confidence , 𝒛𝜶Τ𝟐 = 𝟏. 𝟗𝟔
E = 2% or 0.02
Determine 𝑝̂ and 𝑞̂: 𝑝̂ = 42% or 0.42 ;
𝑞̂ = 1 ̶ 0.42 = 0.58
Solution :
Step 1. Given information: 95% confidence , 𝒛𝜶Τ𝟐 = 𝟏. 𝟗𝟔
E = 2% or 0.02
Determine 𝑝̂ and 𝑞̂: 𝑝̂ = 42% or 0.42 ;
𝑞̂ = 1 ̶ 0.42 = 0.58
Step 2. Solve for n:
𝒛𝜶Τ𝟐 𝟏. 𝟗𝟔 𝟐
ෝ𝒒
𝒏=𝒑 ෝ( )𝟐 = (𝟎. 𝟒𝟐)(𝟎. 𝟓𝟖)( ) = 𝟐, 𝟑𝟑𝟗. 𝟓𝟑 ≈ 𝟐𝟑𝟒𝟎
𝑬 𝟎. 𝟎𝟐
Step 3. Thus, Joy needs a sample of 2,340 households as
respondents.
Module 8- Lesson 3 Exercise
Find the minimum sample size necessary in each of the following.
1. 90% confidence, σ = 0.3, E = 0.1
3. The Dean of a college wants to use the proportion of a
population to determine the sample size needed to interview
regarding their thoughts about the new normal. She wants to be
able to assert with a probability 0.95 that her error will be at most
0.05. Similar polls in the previous months showed that 45%
likes the new normal. How large a sample does the Dean need?