WHOLE BRAIN LEARNING SYSTEM

OUTCOME-BASED EDUCATION

STATISTICS AND GRADE

PROBABILITY 11/12

QUARTER 3
LEARNING
MODULE WEEK 8/8A

1
 MODULE IN
STATISTICS & PROBABILITY

QUARTER 3
WEEK 8/8A

The t-Distribution and

Length of the Interval Estimate and
Sample Size
Development Teams

Writers: Michael G. Calipjo Jerick S. Paltong

Ma. Teresa R. Pascual
Editor: Gerson Jeremy C. Antonio
Reviewers: Gerson Jeremy C. Antonio Myla Fei Martinez
Gregorio P. Agatep, Jr.
Illustrator: Jeshimon C. Patoc
Layout Artist: Jerick S. Paltong
Management Team:
Vilma D. Eda Arnel S. Bandiola
Lourdes B. Arucan Juanito S. Labao
Marlyn S. Ventura

2
 What I Need to Know

In the previous lessons, you have learned the probability distributions and sampling
distributions. You also learned that sample statistics could be generated from sample surveys.
These sample statistics are descriptive summary measures that serve as estimates of the
corresponding population characteristics or parameters.

In this module, you will study situations when sample values are not large enough for the
Central Limit Theorem to be applied, so you should have a better understanding of the t-
distribution with simple examples. Specifically, the t-distribution is highlighted in this lesson
and its importance when making inferences about the population parameter.

There are two major ways of making inferences about the population: one is estimation,
and the other is hypothesis testing. The concepts and foundations of estimation will be
introduced and illustrated. Moreover, finding the length of the interval and sample
determination are also highlighted in this lesson, and the sample size is an important aspect
in estimation.

Most Essential Learning Competencies MELCs:

The learner will be able to:

1. illustrate the t-distribution;
2. identify percentiles using the t-table.
3. identify the length of a confidence interval;
4. compute for the length of the confidence interval;
5. compute for an appropriate sample size using the length of the interval; and
6. solve problems involving sample size determination.

Objectives:

At the end of the module, you should be able to:

1. describe the t-distribution;
2. contrast t-distribution from z-distribution;
3. locate the t-value using the t-distribution table;
4. show the region under the t-distribution with a given t-value;
5. show percentiles using the t-table;
6. use the t-value as applied in real-life problems.
7. calculate the length of the interval estimate;
8. calculate sample size using the length of the interval; and
9. solve real-life problems involving sample determination.

3
 What I Know

Direction: Read each item carefully. Select the correct answer among the choices given and
write the letter of your choice.
1. Which of the following is another term used to describe t-distribution?
A. binomial t-distribution B. z-distribution
C. geometric t-distribution D. student’s t-distribution
2. Which of the following is NOT a characteristic of t-distribution?
A. It is a leptokurtic distribution. B. It is a mesokurtic distribution.
C. It is symmetrical about the mean. D. The mean of the distribution is not equal to zero.
3. Which of the following is NOT TRUE about z- and t-distribution?
A. Both distributions have bell-shaped graphs.
B. Both assume that the population variance is given.
C. Both can transform individual scores to standardized scores.
D. Both can be used for the hypothesis testing of the population mean.
4. Which of the following t-values describes a two-tailed test with a 95% confidence level and
degrees of freedom of 20?
A. 1.729 B. 2.086 C. 2.093 D. 2.861
5. In a t-distribution, the critical values are based on ____.
A. n B. t C. z D. df
6. When n < 30 and the population standard deviation is not known, what is the appropriate
distribution to use?
A. p B. r C. t D. z
𝑥̅ −𝜇 𝑠
7. In the t-distribution formula, 𝑡 = 𝑠 , what do you call the number of values?
√𝑛
√𝑛
A. p B. r C. t D. z
8. Which of the following describes the absolute difference between the upper confidence limit
and the lower confidence limit?
A. Margin of Error B. Confidence Limits
C. Confidence Level D. Length of the Confidence Interval
9. In a research study about students' learning style, 1 200 students were asked if they can
assimilate concepts while watching television. There were 586 students who said Yes.
Using a 95% confidence level, what is the confidence interval estimate for the population
proportion p?
A. 44% to 54% B. 45% to 53% C. 46% to 52% D. 48% to 50%
10. What is the length of the confidence interval in item #9?
A. 0.02 B. 0.06 C. 0.08 D. 0.10
11. What is the length of the confidence interval given the following data: 𝑝̂ = 0.25,
𝑛 = 400, 𝑐𝑜𝑛𝑓𝑖𝑑𝑒𝑛𝑐𝑒 𝑙𝑒𝑣𝑒𝑙 = 95%?
A. 0.072 B. 0.078 C. 0.080 D. 0.085
12. What is the sample size required to estimate a population proportion given the following
data: 𝑝̂ = 0.48, 𝐸 = 0.042, 𝑐𝑜𝑛𝑓𝑖𝑑𝑒𝑛𝑐𝑒 𝑙𝑒𝑣𝑒𝑙 = 90%?
A. 300 B. 338 C. 382 D. 383

4
 Lesson

1 The t-Distribution

What’s In

Activity 1: Activate My Prior Knowledge!

Direction: Determine whether the statement is TRUE or

FALSE by checking the appropriate box that best
describes the standard normal curve. If false, write
the word/s or number/s that makes the statement
false, then change these word/s or number/s to
make it true.
STATEMENT TRUE FALSE
1. The shape of a normal curve is symmetrical, unimodal, and
asymptotic to the vertical axis.
2. The normal curve is a bell-shaped probability distribution.
3. The mean, median, and mode coincide at the center in a normal
probability distribution.
4. The total area under the normal curve is equal to 1.
5. The area of the curve represents all possible probabilities, and the
area between the normal curve and the x-axis is equal to 1.
6. The normal distribution is also known as the Boolean distribution.
7. A normal curve is a graphical representation of statistical values that
are needed in describing the characteristics of populations as well as
in decision making.
8. A normal distribution is called the standard normal distribution when
the distribution has a mean 𝜇 = 1 and standard deviation 𝜎 = 0.
9. The width of the curve is determined by the standard deviation of the
distribution.
10. The area under the curve represents the probability, proportions, or
percentage associated with specific sets of measurement values.

What’s New

Activity 2: Compare Me!

Direction: Given next are the z- and t-distribution curves and their properties. Using a Venn
diagram, classify each property if it belongs to the z-distribution or t-distribution, or
both. Write only the number that corresponds to each property in the Venn
Diagram that follows. Write your answer on a separate sheet of paper.

5
 The z- and t- distribution Properties of z- and t-distribution

1. It contains the transformation of each individual score

into standardized scores.
2. The graph is bell-shaped and symmetrical about the
mean.
3. It is more variable since the distribution values
depend on the variations of the mean and the
standard deviation.
4. The distribution value depends on the fluctuations of
the mean from sample to sample.
5. Its graph is flatter at the center and has heavy tails.
6. This distribution can be used to calculate the
confidence interval of population mean as well as the
confidence interval of the difference of two means.

The Venn Diagram

z-distribution only t-distribution only

Activity 3: Use Me!

Study the given table. Write your answer on a separate sheet of paper.

Table of t Critical Value or the student’s t-Distribution

6
Using the table above, find the confidence coefficients or the t-value for each of the following
given the following information. (An example is done for you).

sample degrees of significance confidence t-values or

Tailed-
No. size n freedom d.f. level 𝛼 level confidence
tests
(n – 1) (1-𝛼) coefficients
Example n= 21 20 0.05 95% 2-tailed ±2.086
1. n= 6 5 0.10 90% 1-tailed
2. n= 7 6 0.05 95% 2-tailed
3. n= 12 11 0.02 98% 2-tailed
4. n= 24 23 0.01 99% 1-tailed
5. n= 30 29 0.01 99% 2-tailed

What is It

The t-Distribution

t – Distribution – a family of distributions that look almost identical to the normal distribution
curve, only a bit shorter and flatter. Just like the normal curve, a bell-shaped and unimodal. It
is formulated in 1908 by an Irish brewing employee named William S. Gosset. It is sometimes
called the student’s t-distribution.

Statistics analysis on some studies which cannot be done using the normal distribution can be
done using the t-distribution. The t-distribution is used with small samples taken from an approximately
normal population. While z-statistic is learned in the previous lessons, which uses population variance,
the t-statistic uses the sample deviation, especially when the population variance is unknown. The z-
statistic is used when 𝑛 ≥ 30, while the t-statistic is used when 𝑛 < 30.

Characteristics of the t-Distribution

1. It is symmetric about t = 0.
2. Its variance is greater than one, which makes it wider and flatter in the middle.
3. It has more area in its tails than that of the normal curve.
4. Its shapes depend on the sample size n. As the sample size n becomes larger, the t-
distribution gets closer to the standard normal distribution.

The t-values, found in the Table of t Critical Value or the student’s t-Distribution, are
proportions of the areas of the t-curve. They are also called Confidence Coefficients.

𝑥̅ −𝜇
𝑥̅ = 𝑠𝑎𝑚𝑝𝑙𝑒 𝑚𝑒𝑎𝑛
The t-Distribution Formula is: 𝑡𝛼,𝑛−1 = 𝑠 where 𝜇 = 𝑝𝑜𝑝𝑢𝑙𝑎𝑡𝑖𝑜𝑛 𝑚𝑒𝑎𝑛
√𝑛
𝑠 = 𝑠𝑡𝑎𝑛𝑑𝑎𝑟𝑑 𝑑𝑒𝑣𝑖𝑎𝑡𝑖𝑜𝑛 𝑜𝑓 𝑡ℎ𝑒 𝑠𝑎𝑚𝑝𝑙𝑒
𝑛 = 𝑠𝑎𝑚𝑝𝑙𝑒 𝑠𝑖𝑧𝑒

7
Observe that on the t-table:
The value of t depends on the degrees of freedom (d.f.) and the level of significance
𝛼. The level of significance for directional tests (1-tailed) is different from that of non-
directional (2-tailed) tests.

Degrees of Freedom, denoted by d.f., is the number of values that are free to vary
after the sample statistic has been computed. These values tell us the specific curve to use
when a distribution consists of a family of curves.
Example: If the mean of 5 values is 10, then 4 of the 5 are free to vary. But once the
4 values are selected, the 5th value must be a specific number to get a sum of 50. Thus, if n
=5, df = n - 1 = 4.

Confidence Level, denoted by (𝟏𝟎𝟎% − 𝜶 𝒐𝒓 𝟏 − 𝜶) is the percentages of all

possible samples that can be expected to include the true population parameter. The most
commonly used confidence levels are 90%, 95%, and 99%.
Level of Significance, denoted by 𝜶 (read as “alpha”) is equal to 100% minus the
confidence level corresponds to the risk indicated by the t-test table for the calculated
|𝑡| value. Usually given as 0.10, 0.05, and 0.01.

See the figure below:

Level of Significance, 𝛼 = 100% - confidence level
Confidence level = 100% - 𝛼

𝒕𝜶 −𝒕𝜶
When to use the t-distribution instead of z-distribution? When n < 30 and the sample
standard deviation is known.

Illustrating the example using the t-curve, for directional (1-

tailed), the 𝛼 = 0.05 (𝑙𝑒𝑣𝑒𝑙 𝑜𝑓 𝑠𝑖𝑔𝑛𝑖𝑓𝑖𝑐𝑎𝑛𝑐𝑒) is allotted to one
side of the curve depending on the given situation. If 𝛼 = 0.05,
then one end will still have a value of 𝛼 = 0.05.

Illustrating the example using the t-curve, since it non-

directional (2-tailed), half of the 𝛼 (𝑙𝑒𝑣𝑒𝑙 𝑜𝑓 𝑠𝑖𝑔𝑛𝑖𝑓𝑖𝑐𝑎𝑛𝑐𝑒) is
allotted on both sides of the curve. If 𝛼 = 0.05, then both ends
𝛼 0.05
will have a value of = = 0.025.
2 2

8
Remark: Take note that this concept is very important when dealing with hypothesis testing in the next chapter.

Example 1: Find 𝑡𝛼,𝑛−1

2
Find the t-value with 10 degrees of freedom and level of significance of 0.10. Consider the non-
directional test since no other details are given.

SOLUTION:

To find 𝑡0.1,10 , we have to consider the value that

is located in the intersection of the degrees of
freedom in the column, and the value of the 𝛼 in
the row. We can see the identified value is
1.812.

The critical value of t

Example 2: Find the critical value t for constructing a 95% confidence interval for a mean of sample
size n = 18 observations.

SOLUTION:

Finding the degrees of freedom, df = n – 1 = 18 – 1 =

17, since 𝛼 = 0.025 for a non-directional 95%
confidence interval, the critical value t = ±2.110.

The Percentile of the t-distribution

Example 3. Find the 90th percentile of the t-distribution with 12 degrees of freedom
SOLUTION:
The percentile of the t-distribution is the value of the variable
that has an area to the left of the given percentage.

To find the 90th percentile of the distribution with 12 degrees

of freedom, we refer to the table and get the left tail
probability of 0.90. Note that the right tail probability of 0.10
will give you the same value.

The value of the 90th percentile of the distribution is 1.356 90th percentile

which means that 90% of the values of the distribution lies on

the left side of this marker as illustrated by the figure at the
right.

Problem Solving: Calculating the t-score

A t-score, like a z-score, is a form of a standardized test statistic, which allows us to

transform a raw score into a standardized score that makes comparison easier. These
standardized scores are used in hypothesis testing (which will be discussed in the next
chapter).

9
Study the following examples:

Example 1 STEPS SOLUTION

The average score of all Step. 1 𝜇 = 85, 𝑠 = 13, 𝑥̅ = 90,
Grade-11 students who took Write the given 𝑛 = 15, 𝑑𝑓 = 𝑛 − 1 = 15 − 1 = 14
the Statistics test in a information.
particular year is 85 out of 120.
A sample of 15 examinees Step 2.
was randomly selected, and 𝑥̅ − 𝜇
Solve for t. 𝑡= 𝑠
the standard deviation for this
sample is 18. What is the t- √𝑛
90 −85
value? 𝑡= 13
√15
𝑡 = 1.49

Example 2 STEPS SOLUTION

A sample of size n = 20 is a Step 1. df = n – 1

simple random sample Find the degrees df = 20 – 1
selected from a normally of freedom df. df = 19
distributed population. Find the
value of t such that the shaded
area to the left of t is 0.05.

To find 𝑡0.1,19 , we have to

consider the value located in
Since the t-distribution is symmetric
the intersection of the degrees
about 0, then the areas to the right and
of freedom in the column and
the value of the 𝛼 in the row. left of t are both 0.05. In the Table of t-
Critical Values, move down the first
column headed df until df=19. Move to
the right along this row, reaching the
column headed 0.05 (area in one tail)
or 0.10 (area in two tails)
−𝑡0.05 = 1.729
Since we are interested in the area at
the left of t, hence, the negative
value.

Example 3 STEPS SOLUTION

Suppose you have a sample of Step 1. df = n – 1

size n = 12 from a normal Find the degrees df = 12 – 1
distribution. Find the critical of freedom df. df = 11
value 𝑡𝛼 that corresponds to a
2
Step 2. Compute
95% confidence level. 𝛼
. Given that the confidence level is
2
To find 𝑡0.05,11 , we have to 95%,
(1 − 𝛼) 100% = 95%
consider the value that is
1 − 𝛼 = 0.95
located in the intersection of

10
the degrees of freedom in the 𝛼 = 0.05
column, and the value of the 𝛼 𝛼
= 0.025
in the row. 2

In the table of t-critical values, move

down the first column headed df until
df = 11, then move to the right along
this row until the column headed 0.05
for two tails is reached.
𝑡𝛼 = 𝑡0.025 = 2.201
2

Identifying Percentiles Using the t-Distribution Table

Percentiles can be identified using the t-Critical Values Table.

Example 4 SOLUTION

The graph of distribution with the given df = 15 is a) Given that df = 15 and 𝛼 = 0.05
shown below. (1 − 𝛼) 100% = 𝜌
(1 − 0.05)100% = 𝜌
Answer each of the following: 0.95 (100%) = 𝜌
a) If the shaded area on the right is 0.05, 𝜌 = 95%
what is the area to the left of 𝑡1 ?
𝜌 = 0.95 area to the left of 𝑡1 .
b) What does 𝑡1 represent?
c) Find the value of 𝑡1 .
b) Hence, 𝑡1 𝑟𝑒𝑝𝑟𝑒𝑠𝑒𝑛𝑡𝑠 the 95th percentile
𝑡0.95 .

c) To find the value of 𝑡1 , look at 15 under

the column headed df. Proceed to the
right until the column headed 0.05 for
one tail is reached. The result is
𝑡1 =1.753.

What’s More
Activity 4: Solve Me!
Direction: Given each graph of a t-distribution, answer the questions that follow. Write
your answer on a separate sheet of paper.

PROBLEM/SITUATION SOLUTION

1. The graph of distribution with df = 15 is shown below.

11
 Find the value of 𝑡1 such that the:
a) shaded area on the left is equal to 0.10
b) shaded area on the right is 0.10
c) total shaded area is 0.02
d) area to the left of 𝑡1 = 0.95

2. The graph of distribution with df = 19 is shown below.

Answer each of the following:

a) If the total shaded area is 0.05, what is the area to the
left of 𝑡1 ?
b) What does 𝑡1 represent?
c) What is the value of 𝑡1 .

Activity 5. Let’s Check Your Understanding!

Direction: Refer to the t-distribution table to find the critical value of the following: Write
your answer on a separate sheet of paper.
________ 1. n = 19, 𝛼 = 0.10, one-tailed
________ 2. n = 5, 𝛼 = 0.20, two-tailed
________ 3. n = 12, 𝛼 = 0.005, one-tailed
________ 4. df = 15, 𝛼 = 0.01, two-tailed
________ 5. df = 30, 𝛼 = 0.05, one-tailed
Direction: Find the critical values of t when the area of the right-hand tail of the t-distribution
is 0.05 given the degrees of freedom df.

________ 6. df = 6
________ 7. df = 25
________ 8. df = 40

Direction: Find the critical values of t when the area of the left-hand tail of the t-distribution
is 0.10 given the degrees of freedom df.
________ 9. df = 7
________ 10. df = 24

12
 What I Have Learned

A. The t-Distribution Formula is:

𝑥̅ = 𝑠𝑎𝑚𝑝𝑙𝑒 𝑚𝑒𝑎𝑛
𝜇 = 𝑝𝑜𝑝𝑢𝑙𝑎𝑡𝑖𝑜𝑛 𝑚𝑒𝑎𝑛
𝑡𝛼,𝑛−1 =
𝑥̅ −𝜇
𝑠 ; where: 𝑠 = 𝑠𝑡𝑎𝑛𝑑𝑎𝑟𝑑 𝑑𝑒𝑣𝑖𝑎𝑡𝑖𝑜𝑛 𝑜𝑓 𝑡ℎ𝑒 𝑠𝑎𝑚𝑝𝑙𝑒
√𝑛
𝑛 = 𝑠𝑎𝑚𝑝𝑙𝑒 𝑠𝑖𝑧𝑒
B. Degrees of Freedom (d.f.) – the number of values that are free to vary after sample
statistic has been computed, and they tell us the specific curve to use when a
distribution consists of a family of curves.
Degrees of Freedom (d.f.) formula when used in t-distribution is n – 1, where n =
sample size

C. t-values, found in the t-Table – are proportions of the areas in two-tails of the t-curve.
They are called critical values of t. They are also called confidence coefficients.

What I Can Do
Activity 6: Let Me Confirm!

Direction: Complete the solution to the given situation below. Write your answer on a
separate sheet of paper.
Situation: A student suspects that the data she collected for the research study does not
represent the target population. Here are the data she collected.
16 20 22 25 26
27 29 30 30 32
34 30 37 42 35
The population mean is 27. Assuming normality in the target population, is the student’s
suspicion correct? Use a 90% confidence level.

For the solution, follow the following steps:

Step 1. Organize the data by using a table, then find the sample mean, sample variance,
and the sample standard deviation.
Step 2. Find the degrees of freedom.
Step 3. Find the critical value.
Step 4. Compute the test statistic t.
Step 5. Draw the t-curve and interpret.

13
 Lesson LENGTH OF THE
2 INTERVAL ESTIMATE AND
SAMPLE SIZE

What’s In

Activity 1: Let Us Recall!

Direction: Choose the letter of the answer that correctly describes each statement.

1. In statistics, what is the process by which one makes inferences about a population based
on information obtained from a sample?
A. Estimator B. Estimate
C. Point Estimation D. Estimation

2. What do you call a single value that may refer to a parameter value?
A. z-statistic B. Point Estimate
C. t-statistic D. Interval Estimate

3. In a z-distribution, which of the following are the critical values if 𝛼 = 0.01?

A. ±1.645 B. ±1.96 C. ±2.33 D. ±2.575

4. In a population of Grade 11 students, 72% can dance. Which statement is TRUE?

A. This means that 0.28 can dance.
B. This means that 28% of the students can dance.
C. This means that 72% of 100 of all students can dance.
D. This means that 72 out of every 100 students can dance.

5. Which of the following best illustrate the statement, as the sample size n increases, the
shape of the distribution of the sample means taken with replacement from a population
with mean 𝜇 and standard deviation 𝜎 will approach a normal distribution?
A. The z-distribution B. The t-distribution
C. The Bayes’ Theorem D. The Central Limit Theorem

What’s New

Estimation is the process of determining parameter values.

Point estimation is an estimation that results in a single value of the statistic, while
interval Estimation is an estimation that results in a range of values of the statistic.

14
 What is It

Point Estimation

Example1: The sample mean weight of 50 Grade 11 students is 60 kgs.

Estimator: sample mean 𝑥̅
Estimate: 60 kgs.

Point Estimate of the Population Mean 𝝁

Among all parameters, the population mean is the most commonly estimated and tested. This
is because of the characteristic and usefulness of this measure to various fields and settings.

The sample mean 𝑥̅ is the best point estimate for the population mean 𝝁.
Example 2: The following monthly salaries (In Philippine Peso) were gathered from a
sample of randomly selected ten teachers in the public school.

25,000 34,750 43,750 28,500 22,500

33,500 35,800 39,760 19,500 29,000
What is the point estimate for the teachers' average monthly salaries in the public
school? The teachers' average monthly salaries in the public school is Php 31,206.00.

Point Estimate of the Population Proportion p

The sample proportion 𝑝̂ is the best point estimate of the population proportion p.

Take note that in getting the population proportion, we use the formula:
𝑥
𝑝̂ = , where 𝑝̂ (read as “p hat”) is the point estimator
𝑛
x is the number of successes
n is the sample size
It follows that 𝑞̂ = 1 − 𝑝̂ , where 𝑞̂ (𝑟𝑒𝑎𝑑 𝑎𝑠 "q hat") is the sample proportion of failures in the
sample size n.

Example 3: In a recent survey of 850 Grade 11 students, it was found out that 476 of them
have laptops. What is the sample proportion 𝑝̂ ?
Solution: Given: x = 476; n = 850; 𝑝̂ = ?
Find 𝑝̂ .
𝑥 476
𝑝̂ = = = 0.56 𝑜𝑟 56%
𝑛 850

Example 4: In a random sample of 120 Grade 11 students were asked if they like modular
learning as their learning modality preference that they could use in this time of
new normal due to the covid-19 pandemic crisis, 48 of them said YES. What is
the sample proportion 𝑝̂ ?

The sample proportion 𝑝̂ is 0.40 or 40%.

15
Margin of Error

Margin of Error for Population Mean 𝝁 with Known Variance

In statistics, the margin of error is the amount of sampling error in an estimate of a

population mean 𝜇 if the variance is known at a certain level of confidence. It is the product
𝜎
of the standard error and the critical value of the confidence level. In symbols, 𝐸 = 𝑧𝛼 ( ),
2 √𝑛
𝛼
Where E = margin of error; 𝑧𝛼 = positive z-value at the boundary for the area of on the left
2 2
and right tails of the standard normal table; 𝜎 = population standard deviation; n = sample
size; and 𝑛 ≥ 30.

Confidence Level in an interval estimate of a parameter is the probability that the interval
estimate contains the parameter. It describes what percentage of the interval from many
different samples contain the unknown population parameter. There are three commonly used
confidence levels: 90%, 95%, and 99%.

Level of Significance, denoted by 𝜶 (read as “alpha”) is equal to 100% minus the

confidence level.

Example 5: Calculate the margin of error using the formula given above with given the
confidence level, standard deviation, and sample size. Find the value of 𝑧𝛼.
2
Complete the table below using the z-table.

Confidence 𝑧𝛼 Population Standard

Sample Size n Margin of Error E
Level 2 Deviation 𝜎

1. 80% 2.5 30
2. 90% 5 50
3. 95% 12 100
4. 98% 15 75
5. 99% 10 50

Margin of Error for Population Mean 𝝁 with Unknown Variance

𝑠
The formula 𝐸 = 𝑡𝛼 ( ) is used when the population variance is unknown, where E
2 √𝑛
𝛼
= margin of error; 𝑡𝛼 = positive z-value at the boundary for the area of on the left and right
2 2
tails of the t-table; s = sample standard deviation; n = sample size; and n < 30.

Example 6: Calculate the margin of error E using the formula given above with given the
confidence level, standard deviation, and sample size. Find the value of 𝑡𝛼.
2

Complete the table below using the t-table.

Confidence Sample Standard Degrees of 𝑡𝛼 Margin of
Sample Size n
Level Deviation 𝑠 Freedom df 2 Error E
1. 80% 2.5 9 8
2. 90% 5 15 14
3. 95% 12 20 19
4. 98% 15 25 24
5. 99% 10 28 27

16
Margin of Error for Population Proportion p

The margin of error E in the case of population proportion p is similar to the case of
𝑝𝑞
the population mean except for the fact that the standard error 𝑆𝐸𝑝 = 𝑧𝛼 √ . Take note that
𝑛
2
𝑥
𝑝̂ , n𝑞̂ > 5, recall that 𝑝̂ = , where x = number of successes and n = sample size.
𝑛

Example 7: Calculate the margin of error using the formula given above with given the
confidence level, standard deviation and sample size. Find the value of 𝑧𝛼.
2
Complete the table below.
𝑧𝛼 Number of
Confidence Sample 𝑥 Margin of
2 Successes 𝑝̂ = 𝑞̂ = 1 - 𝑝̂
Level Size n 𝑛 Error E
x
1. 80% 30 20
2. 90% 50 30
3. 95% 100 80
4. 98% 75 35
5. 99% 50 20
*Use z-table

Interval Estimation

Interval Estimation is an estimation that results in a range of values of the statistic.

Example 8: The sample mean weight of 50 Grade 11 students is between 57.5 kgs and
62.5 kgs, with a 95% level of confidence.
Estimator: sample mean
Estimate: 57.5 – 62.5 kgs.

In the estimate, 57.5 – 62.5 is called the interval estimate.

In interval estimate, 57.5 is the lower confidence limit
62.5 is the upper confidence limit

The range of values is the interval estimate or confidence interval where the
confidence level, the margin of error, and the range of values of the computed statistic are
presented. The confidence level of the confidence coefficient is (1 – 𝛼)100%. The common
values of confidence level are their corresponding z-score which will help you in finding the
confidence interval are presented in the table that follows:
Confidence Level 𝜶 z-score (two-tailed)
90% 0.10 ±1.645
95% 0.05 ±1.96
98% 0.02 ±2.33
99% 0.01 ±2.575

A. Interval Estimation for Population Mean 𝝁 with Known Variance

If the population standard deviation is given and confidence level of (1 – 𝛼)100%,
then the confidence interval can be calculated using the estimator below:
𝝈 𝝈
𝒙̅ − 𝒛𝜶 ( 𝒏) < 𝝁 < 𝒙̅ + 𝒛𝜶 ( 𝒏) where,
𝟐 √ 𝟐 √
𝝈
𝒙̅ − 𝒛𝜶 ( ) = called the Lower Confidence Boundary or Limit (LCL)
𝟐 √𝒏
𝝈
𝒙̅ + 𝒛𝜶 ( ) = called the Upper Confidence Boundary or Limit (UCL)
𝟐 √𝒏
𝝈
𝒛𝜶 ( ) = called the margin of Error E
𝟐 √𝒏

17
 𝒙̅ = mean of the random sample of size n or the point estimate
𝜶
𝒛𝜶 = called the critical value or z-value or confidence coefficient at (1- ) confidence
𝟐 𝟐
level
𝝈
= called the standard Error of the mean
√𝒏
n = sample size
𝜎 = population standard deviation = √𝜎 2
For a specific value, 𝛼 = 0.05, the distribution of 𝒙̅ ‘s is:

Example 9: The mean score of a random sample of 49 Grade 11 students who took the
First Statistics Quiz is 78. The population variance is known to be 0.16. At 95%
confidence level, find the interval estimate of all Grade 11 students' mean
scores.

SOLUTION:
Step 1. Find the value of 𝒛𝜶 .
𝟐
Given: ̅ = 78;
𝒙 𝜎 𝟐 = 0.16; 𝜎 = √0.16 = 0.4; 𝑛 = 49
Solving for 𝛼:
Confidence level = 95%
(1 – 𝛼)100% = 95%
(1 – 𝛼)1 = 0.95
1 – 𝛼 = 0.95
𝛼 = 1 − 0.95
𝛼 = 0.05 𝛼 𝑖𝑠 𝑑𝑖𝑣𝑖𝑑𝑒𝑑 𝑏𝑦 2 𝑠𝑖𝑛𝑐𝑒 𝑡ℎ𝑒 𝑖𝑛𝑡𝑒𝑟𝑒𝑠𝑡 𝑖𝑠 𝑜𝑛
𝜶
Solving for ,
𝟐
α 0.05 𝑒𝑖𝑡ℎ𝑒𝑟 𝑙𝑒𝑓𝑡 𝑜𝑟 𝑟𝑖𝑔ℎ𝑡 𝑜𝑓 𝑡ℎ𝑒 𝑝𝑜𝑝𝑢𝑙𝑎𝑡𝑖𝑜𝑛 𝑚𝑒𝑎𝑛
= = 0.025
2 2

Finding for the value of 𝒛𝜶 , subtract 0.025 from 0.5:

𝟐
0.5 – 0.025 = 0.4750
Use the z-table to find the area 0.4750. The area 0.4750 is under the column headed
6. Move along this row to the left until 1.9 under column headed z is reached. Thus, 𝑧𝛼 =
2
1.96.

Step 2. Find the Margin of Error E.

σ
E = zα ( )
2 √n
0.4
E = 1.96 ( )
√49
E = 0.112

18
Step 3. Substitute the values of 𝒙̅ and E in the confidence interval
σ σ
x̅ − zα ( ) < μ < x̅ + zα ( )
2 √n 2 √n
x̅ − E < μ < x̅ + E
78 − 0.112 < μ < 78 + 0.112
77.888 < μ < 78.112
77.89 < μ < 78.11
So, 77.89 = Lower Confidence Limit (LCL)
78.11 = Upper Confidence Limit (UCL)

Interpretation:
Thus, with 95% confidence, the sample mean 𝑥̅ = 78 differs from the population mean 𝜇 by no
more than 0.112 or 0.11, and the true population mean 𝜇 is between 77.89 and 78.11.

B. Interval Estimation for Population Mean 𝝁 with Unknown Variance, but the Sample
Size is Large

This is when the population standard deviation is not given, but the sample size is
sufficiently large (n ≥ 30). If the confidence level of (1 – 𝛼)100%, then the confidence
interval can be calculated using the estimator below:
𝑠 𝑠
𝑥̅ − 𝑧𝛼 ( ) < 𝜇 < 𝑥̅ + 𝑧𝛼 ( ) where,
2 √𝑛 2 √𝑛

𝑠 𝜎
𝐸 = 𝑧𝛼 ( ) = margin of error; = standard error of the mean
2 √ 𝑛 √𝑛
𝛼
𝑧𝛼 = critical value or z-value or confidence coefficient at (1- 2 ) confidence level
2
𝑥̅ = 𝑠𝑎𝑚𝑝𝑙𝑒 𝑚𝑒𝑎𝑛; 𝑠 = 𝑠𝑎𝑚𝑝𝑙𝑒 𝑠𝑡𝑎𝑛𝑑𝑎𝑟𝑑 𝑑𝑒𝑣𝑖𝑎𝑡𝑖𝑜𝑛; n = sample size

Example 10: In a sample size of 40 with a mean of 186 and standard deviation of 6, interpret
the confidence interval for the population at a 95% confidence level.

SOLUTION:
Step 1. Find the value of 𝒛𝜶 .
𝟐
Given: ̅ = 186;
𝒙 𝒔 = 6; 𝑛 = 40
Solving for 𝛼:
Confidence level = 95%
(1 – 𝛼)100% = 95%
(1 – 𝛼)1 = 0.95
1 – 𝛼 = 0.95
𝛼 = 1 − 0.95
𝛼 = 0.05 𝛼 𝑖𝑠 𝑑𝑖𝑣𝑖𝑑𝑒𝑑 𝑏𝑦 2 𝑠𝑖𝑛𝑐𝑒 𝑡ℎ𝑒 𝑖𝑛𝑡𝑒𝑟𝑒𝑠𝑡 𝑖𝑠 𝑜𝑛
𝜶
Solving for ,
𝟐
𝜶 𝟎.𝟎𝟓 𝑒𝑖𝑡ℎ𝑒𝑟 𝑙𝑒𝑓𝑡 𝑜𝑟 𝑟𝑖𝑔ℎ𝑡 𝑜𝑓 𝑡ℎ𝑒 𝑝𝑜𝑝𝑢𝑙𝑎𝑡𝑖𝑜𝑛 𝑚𝑒𝑎𝑛
= = 𝟎. 𝟎𝟐𝟓
𝟐 𝟐

Finding for the value of 𝒛𝜶 , subtract 0.025 from 0.5:

𝟐
0.5 – 0.025 = 0.4750
Use the z-table to find the area 0.4750. The area 0.4750 is under the column headed 6. Move
along this row to the left until 1.9 under column headed z is reached. Thus, 𝑧𝛼 = 1.96.
2
Step 2. Find the Margin of Error E.
s
E = zα ( )
2 √n
6
E = 1.96 ( )
√40

19
 E = 1.86
Step 3. Substitute the values of 𝒙̅ and E in the confidence interval
s s
x̅ − zα ( ) < μ < x̅ + zα ( )
2 √n 2 √n
x̅ − E < μ < x̅ + E
186 − 1.86 < μ < 186 + 1.86
184.14 < μ < 187.86
So, 184.14 = Lower Confidence Limit
187.86 = Upper Confidence Limit
Interpretation:
With 95% confidence, the sample mean 𝑥̅ = 186 differs from the population mean 𝜇 by no
more than 1.86, and also, the true population mean 𝜇 is between 184.14 and 187.86.

C. Interval Estimation for Population Mean 𝝁 with Unknown Variance but the Sample
Size is Small
The process and formula in calculating a confidence interval for the population mean
𝜇 using the t-distribution is when the sample size is small (n < 30) and the population
variance is unknown.
If the population standard deviation is unknown with a (1 – 𝛼)100% confidence level,
then the confidence interval can be calculated using the estimator below:
𝑠 𝑠
𝑥̅ − 𝑡𝛼 ( ) < 𝜇 < 𝑥̅ + 𝑡𝛼 ( ) where,
2 √𝑛 2 √𝑛
𝑠
𝑥̅ − 𝑡𝛼 ( ) = called the Lower Confidence Boundary or Limit (LCL)
2 √𝑛
𝑠
𝑥̅ + 𝑡𝛼, ( ) = called the Upper Confidence Boundary or Limit (UCL)
2 √ 𝑛
𝑠
𝑡𝛼 ( ) = called the margin of error
2 √𝑛
𝑡 = called the critical value or t-value or confidence coefficient
𝛼
2
𝑛 − 1 = 𝑑𝑒𝑔𝑟𝑒𝑒𝑠 𝑜𝑓 𝑓𝑟𝑒𝑒𝑑𝑜𝑚, n = sample size
𝑠
= standard error of the mean, s=sample standard deviation
√𝑛

Example 11: Mathematics teachers at the high school level are under stress if students’
achievement in their subject is low. A medical student researcher wanted to
know if stress contributes to the high hemoglobin level of these teachers. He
sampled 20 mathematics teachers and found out that the teachers’ average
hemoglobin reading was 16 grams per 100 milliliters with a sample standard
deviation of 2 grams. Find the 95% confidence interval of the true mean.
SOLUTION:
̅ = 16; 𝒔 = 2; 𝑛 = 20; 𝑑. 𝑓. = 20 − 1 = 19
Step 1. Find the value of 𝒕𝜶 . Given: 𝒙
𝟐
Solving for 𝛼:
Confidence level = 95%
(1 – 𝛼)100% = 95%
(1 – 𝛼)1 = 0.95
1 – 𝛼 = 0.95
𝛼 = 1 − 0.95
𝛼 = 0.05
Finding for the value of 𝒕𝜶 ,
𝟐
Use the t-table, find 19 in the left column and 0.05 (two-tails) in the row labeled significance
level 𝛼. The intersection where the two meets gives the value for 𝒕𝜶,𝒏−𝟏 = 2.093.
𝟐
Step 2. Find the Margin of Error E.
𝒔
𝑬 = 𝒕𝜶,𝒏−𝟏 ( )
𝟐 √𝒏
𝟐
𝑬= 𝟐. 𝟎𝟗𝟑 ( )
√𝟐𝟎

20
 𝑬 = 0.94
Step 3. Substitute the values of 𝒙̅ and E in the confidence interval
𝒔 𝒔
𝒙̅ − 𝒛𝜶 ( ) < 𝝁 < 𝒙̅ + 𝒛𝜶 ( )
𝟐 √𝒏 𝟐 √𝒏
𝒙̅ − 𝑬 < 𝝁 < 𝒙̅ + 𝑬
𝟏𝟔 − 𝟎. 𝟗𝟒 < 𝝁 < 𝟏𝟔 + 𝟎. 𝟗𝟒
𝟏𝟓. 𝟎𝟔 < 𝝁 < 𝟏𝟔. 𝟗𝟒
So, 15.06 = Lower Confidence Limit (LCL)
16.94 = Upper Confidence Limit (UCL)

Interpretation:
With 95% confidence, the sample mean 𝑥̅ =16 differs from the population mean 𝜇 by no more
than 0.94, and the true population mean 𝜇 is between 15.06 and 16.94.

D. Interval Estimation for Population Proportion p

With (1 – 𝛼)100% confidence interval for p is given by:
̂𝒒
𝒑 ̂ ̂𝒒
𝒑 ̂
̂ − 𝒁𝜶 ( √ ) < 𝒑 < 𝒑
𝒑 ̂ + 𝒁𝜶 (√ ) where:
𝟐 𝒏 𝟐 𝒏

𝑝̂𝑞̂
𝐸 = 𝑍𝛼 (√ ) = margin of error; n = sample size
2 𝑛
𝑝̂ = 𝑠𝑎𝑚𝑝𝑙𝑒 𝑝𝑟𝑜𝑝𝑜𝑟𝑡𝑖𝑜𝑛 𝑜𝑟 𝑡ℎ𝑒 𝑝𝑜𝑖𝑛𝑡 𝑒𝑠𝑡𝑖𝑚𝑎𝑡𝑒 𝑜𝑓 𝑡ℎ𝑒 𝑝𝑜𝑝𝑢𝑙𝑎𝑡𝑖𝑜𝑛 𝑝𝑟𝑜𝑝𝑜𝑟𝑡𝑖𝑜𝑛 p
𝑞̂ = 1 − 𝑝̂
𝛼
𝑧𝛼 = critical value or z-value or confidence coefficient at (1- ) confidence level
2 2
𝑝̂𝑞̂
𝜎𝑝̂ = √ = standard deviation of the sampling distribution of 𝑝̂
𝑛
̂‘s is:
For a specific value, 𝛼 = 0.05, the distribution of 𝒑

Example 12: Are you in favor of the Anti-Terrorism Bill?

A survey was conducted to know if the Filipino citizens favor the implementation
of the Anti-Terror Law. Of the randomly selected 1200 citizens, 715 said YES. At
95% confidence, find the confidence interval of all citizens who favors the Anti-
Terror Law.

SOLUTION:
Step 1. Find the value of 𝒑̂ and 𝒒
̂.
Given: 𝒙 = 715; 𝑛 = 1,200

̂ 𝑎𝑛𝑑 𝒒
Solving for 𝒑 ̂:
𝑥
𝑝̂ =
𝑛
715
𝑝̂ =
1,200
𝑝̂ = 0.60

21
 𝑞̂ = 1 − 0.60
𝑞̂ = 0.40

We know that at 95% confidence when n≥ 30 the value of 𝑧𝛼 = 1.96;

2

Step 2. Find the Margin of Error E.

𝑝̂𝑞̂
𝐸 = 𝑍𝛼 (√ )
2 𝑛

(0.60)(0.40)
𝐸 = 1.96 (√ )
1,200
𝐸 = 0.03
Step 3. Substitute the values of 𝑥̅ and E in the confidence interval
𝑝̂𝑞̂ 𝑝̂𝑞̂
𝑝̂ − 𝑍𝛼 (√ ) < 𝑝 < 𝑝̂ + 𝑍𝛼 (√ )
2 𝑛 2 𝑛
𝑝̂ − 𝐸 < 𝑝 < 𝑝̂ + 𝐸
0.60 − 0.03 < 𝑝 < 0.60 + 0.03
0.57 < 𝑝 < 0.63
57% < 𝑝 < 63%
So, 57% = Lower Confidence Limit (LCL)
63% = Upper Confidence Limit (UCL)

Interpretation:
Thus, we can be 95% confident that the true population proportion p of all citizens who favors
the implementation of the Anti-Terror Law is between 57% to 63% based on a random sample
of 1 200 citizens.

Activity 4: Solve Me!

Direction: Solve each of the following problems:
1. Find and interpret the confidence interval for the population mean at 90% confidence
interval if the sample size is 20 and has a mean of 18 and a standard deviation of 2.
2. Construct a 95% confidence interval for the population proportion if 𝒒 ̂ = 0.70 and
n = 70.
3. A researcher wanted to determine passengers' mean waiting time during the delayed
Domestic flights of Cebu Pacific. He randomly selected 120 passengers and obtained
the mean waiting time (in hours) of 3.5 and a standard deviation of 1.1.
a. Compute for the confidence interval at a 90% confidence level.
b. Compute for the confidence interval at a 95% confidence level.
c. How do you compare the intervals of true waiting time of passengers in two
different levels?

What is the length of a confidence interval?

The length of a confidence interval (LCI) is the absolute difference between the upper
confidence limit (UCL) and the lower confidence limit (LCL). In symbols,
LCI = Length of the Confidence Interval
LCI = | 𝑈𝐶𝐿 − 𝐿𝐶𝐿 | = | 𝐿𝐶𝐿 − 𝑈𝐶𝐿 | UCL = Upper Confidence Level
or LCL = Lower Confidence Level
LCI = UCL – LCL where

𝑛 = 𝑠𝑎𝑚𝑝𝑙𝑒 𝑠𝑖𝑧𝑒

22
A. Length of a Confidence Interval for population mean 𝝁, n ≥ 𝟑𝟎

Example 1. Find the length of the confidence intervals of:

184.14 < 𝜇 < 187.86
SOLUTION: Given: UCL = 187.86; LCL = 184.14
LCI = UCL – LCL
LCI = 187.86 − 184.14
LCI = 3.72

Deriving the formula for interval estimate of a population mean 𝜇 with known variance:
𝝈 𝝈
𝒙̅ − 𝒛𝜶 ( ) < 𝝁 < 𝒙̅ + 𝒛𝜶 ( )
𝟐 √𝒏 𝟐 √𝒏

To find the length of the confidence interval, subtract the lower confidence limit from the
upper confidence limit:
𝝈 𝝈
LCI = [𝒙̅ + 𝒛𝜶 ( )] - [𝒙̅ − 𝒛𝜶 ( )]
√𝒏
𝟐 √𝒏 𝟐
𝝈 𝝈
LCI = 𝒙̅ + 𝒛𝜶 ( ) − 𝒙̅ + 𝒛𝜶 ( )
𝟐 √𝒏 𝟐 √𝒏
𝝈 𝝈
LCI = 𝒙̅ + 𝒛𝜶 ( ) − 𝒙̅ + 𝒛𝜶 ( )
𝟐 √𝒏 𝟐 √𝒏
𝝈
LCI = 2𝒛𝜶 ( )
𝟐 √𝒏

B. Length of a Confidence Interval for a population mean 𝝁, n < 𝟑𝟎

Deriving the formula for interval estimate of population mean 𝜇 with unknown variance

𝒔 𝒔
𝒙̅ − 𝒕𝜶 ( ) < 𝝁 < 𝒙̅ + 𝒕𝜶 ( )
𝟐 √𝒏 𝟐 √𝒏

To find the length of the confidence interval, subtract the lower confidence limit from the
upper confidence limit:
𝒔 𝒔
LCI = [𝒙̅ + 𝒕𝜶 ( )] - [𝒙̅ − 𝒕𝜶 ( )]
√𝒏
𝟐 √𝒏 𝟐
𝒔 𝒔
LCI = 𝒙̅ + 𝒕𝜶 ( ) − 𝒙̅ + 𝒕𝜶 ( )
𝟐 √𝒏 𝟐 √𝒏
𝒔 𝒔
LCI = 𝒙̅ + 𝒕𝜶 ( ) − 𝒙̅ + 𝒕𝜶 ( )
𝟐 √𝒏 𝟐 √𝒏
𝒔
LCI = 2𝒕𝜶 ( )
𝟐 √ 𝒏

Example 1: Find the length of the confidence interval given the following data:
𝑠 = 6.17; 𝑛 = 12; 𝑐𝑜𝑛𝑓𝑖𝑑𝑒𝑛𝑐𝑒 𝑙𝑒𝑣𝑒𝑙 = 99%

SOLUTION:

Step 1. Find the degree of freedom d.f.

d.f. = n – 1
d.f. = 12 – 1
d.f. = 11

Step 2. Find 𝛼 in (1 – 𝛼)100% confidence level then find 𝒁𝜶 .

𝟐
(1 – 𝛼)100% = 99%
(1 – 𝛼)1 = 0.99
1 - 𝛼 = 0.99

23
 𝛼 = 0.01
Hence, using the t-table 𝑡𝛼 = 3.106
2

Step 3. Find the LCI.

𝒔
LCI = 2𝒕𝜶 ( )
𝟐 √𝒏
𝟔.𝟏𝟕
LCI = 2(𝟑. 𝟏𝟎𝟔) ( )
√𝟏𝟐
LCI = 11.06

Example 2: Find the length of the confidence interval given the following data:
𝜎 = 0.5; 𝑛 = 36; 𝑐𝑜𝑛𝑓𝑖𝑑𝑒𝑛𝑐𝑒 𝑙𝑒𝑣𝑒𝑙 = 95%

SOLUTION:

Step 1. Find 𝛼 in (1 – 𝛼)100% confidence level then find 𝒁𝜶 .

𝟐
(1 – 𝛼)100% = 95%
(1 – 𝛼)1 = 0.95
1 - 𝛼 = 0.95
𝛼 = 0.05
𝜶
Solving for :
𝟐
𝛼 0.05
= = 0.025
2 2
Finding for the value of 𝒛𝜶 , subtract 0.025 from 0.5:
𝟐
0.5 – 0.025 = 0.4750
Hence, using the z-table 𝑧𝛼 = 1.96.
2
Step 2. Find the LCI.
𝝈
LCI = 2𝒛𝜶 ( )
𝟐 √𝒏
𝟎.𝟓
LCI = 2(𝟏. 𝟗𝟔) ( )
√𝟑𝟔
LCI = 0.237
C. Length of a Confidence Interval for population proportion p
Deriving the formula for interval estimate of population proportion p

̂𝒒
𝒑 ̂ ̂𝒒
𝒑 ̂
̂ − 𝒁𝜶 ( √ ) < 𝒑 < 𝒑
𝒑 ̂ + 𝒁𝜶 ( √ )
𝟐 𝒏 𝟐 𝒏
To find the length of the confidence interval, subtract the lower confidence limit from the
upper confidence limit:
̂𝒒
𝒑 ̂ ̂𝒒
𝒑 ̂
̂ + 𝒁𝜶 (√ )] - [𝒑
LCI = [𝒑 ̂ − 𝒁𝜶 (√ )]
𝟐 𝒏 𝟐 𝒏

̂𝒒
𝒑 ̂ ̂𝒒
𝒑 ̂
̂ + 𝒁𝜶 ( √ ) − 𝒑
LCI = 𝒑 ̂ + 𝒁𝜶 ( √ )
𝟐 𝒏 𝟐 𝒏

̂𝒒
𝒑 ̂
LCI = 𝟐 𝒁𝜶 (√ )
𝟐 𝒏
Example 1: Find the length of the given confidence interval: 0.57 < 𝑝 < 0.63
SOLUTION:
Given: UCL = 0.63; LCL = 0.57
LCI = UCL – LCL
LCI = 0.63 − 0.57

24
 LCI = 0.06 or 6%

Example 2: Find the length of the confidence interval given the following data:
𝑝̂ = 0.25; 𝑛 = 300; 𝑐𝑜𝑛𝑓𝑖𝑑𝑒𝑛𝑐𝑒 𝑙𝑒𝑣𝑒𝑙 = 95%
SOLUTION:
Step 1. Find 𝛼 in (1 – 𝛼)100% confidence level then find 𝑍𝛼.
2
(1 – 𝛼)100% = 95%
(1 – 𝛼)1 = 0.95
1 - 𝛼 = 0.95
𝛼 = 0.05
𝜶
Solving for :
𝟐
𝜶 𝟎. 𝟎𝟓
= = 𝟎. 𝟎𝟐𝟓
𝟐 𝟐
Finding for the value of 𝒛𝜶 , subtract 0.025 from 0.5:
𝟐
0.5 – 0.025 = 0.4750
Hence, using the z-table 𝑧𝛼 = 𝟏. 𝟗𝟔.
2

Step 2. Find the LCI.

̂𝒒
𝒑 ̂
LCI = 𝟐 𝒁𝜶 (√ )
𝟐 𝒏

(𝟎.𝟐𝟓)(𝟎.𝟕𝟓)
LCI = 2(1.96) (√ )
𝟑𝟎𝟎
LCI = 0.098 or 9.8%

How to determine sample size?

How large should a sample be? Many researchers find this a problem. Many rely on old
methods to determine the sample size they need in their investigations. This problem should
be addressed carefully because needlessly large samples are a waste of important resources.
On the other hand, the insufficient sample size may lead to poor results.

How to determine the sample size in estimating 𝝁?

Derivation for sample size n needed in estimating a population mean 𝜇.
𝑧𝛼 • 𝜎
𝐸= 2
√𝑛
𝐸√𝑛 = (𝑧𝛼 𝑧 • 𝜎)
2
𝑧𝛼 • 𝜎 2
2 2
(√𝑛) = ( )
𝐸
𝑧𝛼 • 𝜎 2
2
𝑛=( )
𝐸

Example: Sarah, a researcher, would like to study the average life-span of a high-end mobile
gadget produced by a certain company. The population mean life-span of the said
mobile is eight years, and the standard deviation is four years. How many sampling
units must be included in the investigation for her to be sure with 99% accuracy
that the sample mean is within 1.5 years of the population mean?

SOLUTION: Given: 𝐸 = 1.5;

𝑐𝑜𝑛𝑓𝑖𝑑𝑒𝑛𝑐𝑒 𝑙𝑒𝑣𝑒𝑙 = 99%; 𝑧𝛼 = 2.575
2

25
 𝑧𝛼 • 𝜎 2
2
𝑛=( )
𝐸
(2.575)(4) 2
𝑛= [ ]
1.5
𝑛 = 47.15
𝑛 = 48
Note: the resulting value of n is rounded up to the nearest whole number.
How to Determine the Sample Size for Estimating 𝒑?
Derivation for sample size n needed in estimating a population proportion p:
To do this, modify the equation of margin of Error E by applying the properties of equality:

2
𝑝̂ 𝑞̂ 𝑛 • 𝐸2 = 𝑝̂ 𝑞̂ • (𝑧𝛼 )
𝐸 = 𝑧𝛼 √ 2
2 𝑛 2
𝑝̂𝑞̂•(𝑍𝛼 )
𝐸 𝑝̂𝑞̂ 2
=√ 𝑛= or
𝑧𝛼 𝑛 𝐸2
2 𝑍𝛼 2
2
𝐸 𝑝̂𝑞̂ 𝑛 = 𝑝̂ 𝑞̂ ( 𝐸2 ) for 𝑝̂ 𝑖𝑠 𝑘𝑛𝑜𝑤𝑛
(𝑧 ) =
𝛼 𝑛 2
2
𝐸2 𝑝̂𝑞̂ 0.25 (𝑍𝛼 )
2 = 𝑛= 2
for 𝑝̂ 𝑖𝑠 𝑢𝑛𝑘𝑛𝑜𝑤𝑛
𝑛
(𝑧𝛼 ) 𝐸2
2

Example: Andrei, a Senior High School student, would like to estimate the proportion of those
who support the bill, which lowers the criminal liability of minors from 15 years old
to 9 years old within five percentage points with a 90% confidence level. A survey
conducted a week ago showed that 39% are in favor of this bill. How many
respondents should he sample to estimate the proportion of those in favor of the
bill?

SOLUTION: Given: 𝑝̂ = 0.39; 𝑞̂ = 0.61; 𝐸 = 0.05;

𝑐𝑜𝑛𝑓𝑖𝑑𝑒𝑛𝑐𝑒 𝑙𝑒𝑣𝑒𝑙 = 95%; 𝑧𝛼 = 1.645
2
𝑍𝛼 2
1.645 2
𝑛 = 𝑝̂ 𝑞̂ ( 𝐸2 ) = (0.39)(0.61) ( 0.05 ) = 257.51 ≈ 𝟐𝟓𝟖

Slovin’s Formula

There are situations when we do not know the behavior of the population. One formula
usually used by researchers when there was limited information about the population is
Slovin’s formula.
Slovin’s formula is a random sampling formula used to estimate sample size, making
use of the total population and margin of error.
In symbols,
𝑁
𝑛= , where n = sample size; N = population size
1+𝑁𝑒 2
e = margin of error = 0.05 or 5% which is constant

Example: A researcher wants to study social media's effects on Grade 11 students in Ilocos
Norte College of Arts and Trades. If there are 1 000 Grade 11 students in the school, how
many students should there be in the sample?

SOLUTION: Given: N = 1,000; e = 0.05 or 5%

26
 𝑁
𝑛=
1+𝑁𝑒 2
1,000
𝑛=
1+(1,000)(0.05)2
𝑛 = 285.7
𝑛 = 286
Therefore, the minimum sample size should be 286.

What’s More
Direction: Solve each of the following with the given condition:

Problem Answer

I. Find the length of the following confidence interval

a) 37.33 < 𝜇 < 42.58 a) ____________________________
b) 0.399 < p < 0.901 b) ____________________________

II. Find the length of the confidence interval given the

upper and lower limits.
a) Upper Confidence Limit = 67.30 a) ____________________________
Lower Confidence Limit = 47.70
b) Upper Confidence Limit = 69.10 b) ____________________________
Lower Confidence Limit = 40.90
III. Find the length of the confidence interval given the
following data:
a) 𝜎 = 0.52; 𝑛 = 40; 𝑐𝑜𝑛𝑓𝑖𝑑𝑒𝑛𝑐𝑒 𝑙𝑒𝑣𝑒𝑙 = 99% a) ____________________________
b) 𝜎 = 0.40; 𝑛 = 64; 𝑐𝑜𝑛𝑓𝑖𝑑𝑒𝑛𝑐𝑒 𝑙𝑒𝑣𝑒𝑙 = 95% b) ____________________________
IV. Find the length of the confidence interval given the
following data: a) ____________________________
𝑎) 𝑠 = 5.25; 𝑛 = 14; 𝑐𝑜𝑛𝑓𝑖𝑑𝑒𝑛𝑐𝑒 𝑙𝑒𝑣𝑒𝑙 = 90% b) ____________________________
𝑏) 𝑠 = 4.50; 𝑛 = 16; 𝑐𝑜𝑛𝑓𝑖𝑑𝑒𝑛𝑐𝑒 𝑙𝑒𝑣𝑒𝑙 = 95%
V. Find the length of the confidence interval given the
following data:
𝑎) 𝑝̂ = 0.35; 𝑛 = 400; 𝑐𝑜𝑛𝑓𝑖𝑑𝑒𝑛𝑐𝑒 𝑙𝑒𝑣𝑒𝑙 = 90% a) ____________________________
𝑏) 𝑝̂ = 0.45; 𝑛 = 350; 𝑐𝑜𝑛𝑓𝑖𝑑𝑒𝑛𝑐𝑒 𝑙𝑒𝑣𝑒𝑙 = 95% b) ____________________________

VI. Solve for the sample size for each given the
following information: a) ____________________________
a) E = 0.5; 𝜎 = 2.5; 90% 𝑐𝑜𝑛𝑓𝑖𝑑𝑒𝑛𝑐𝑒 𝑙𝑒𝑣𝑒𝑙 b) ___________________________
b) E = 0.3; 𝜎 = 4.1; 95% 𝑐𝑜𝑛𝑓𝑖𝑑𝑒𝑛𝑐𝑒 𝑙𝑒𝑣𝑒𝑙
VII. Solve for the sample size for each given the
following information: a) ____________________________
a) E = 0.08; 𝑝̂ = 0.65; 99% 𝑐𝑜𝑛𝑓𝑖𝑑𝑒𝑛𝑐𝑒 𝑙𝑒𝑣𝑒𝑙 b) ____________________________
b) E = 0.05; 𝑝̂ = 𝑢𝑛𝑘𝑜𝑤𝑛; 90% 𝑐𝑜𝑛𝑓𝑖𝑑𝑒𝑛𝑐𝑒 𝑙𝑒𝑣𝑒𝑙 c) ____________________________
c) E = 0.05; 𝑁 = 4830

27
 What I Have Learned

A. The length of a confidence interval (LCI) is the absolute difference between the
upper confidence limit (UCL) and the lower confidence limit (LCL).
In symbols,
LCI = | 𝑈𝐶𝐿 − 𝐿𝐶𝐿 | = | 𝐿𝐶𝐿 − 𝑈𝐶𝐿 | LCI = Length of the Confidence Interval
or UCL = Upper Confidence Level
LCI = UCL – LCL where LCL = Lower Confidence Level

Length of Confidence Interval Formula

𝑛 = 𝑠𝑎𝑚𝑝𝑙𝑒 𝑠𝑖𝑧𝑒
a) Length of a Confidence Interval for population LCI = 2𝑧𝛼 ( 𝜎 )
mean 𝜇, n ≥ 30 2 √𝑛

b) Length of a Confidence Interval for population LCI = 2𝑡𝛼 ( 𝑠 )

mean 𝜇, n < 30 2 √𝑛

c) Length of a Confidence Interval for population 𝑝̂𝑞̂

proportion p LCI = 2 𝑍𝛼 (√ )
2 𝑛

B. How to determine the sample size?

Sample Size Determination Formula
a) How to determine the Sample Size for 𝑧𝛼 • 𝜎 2
Estimating 𝜇? 𝑛=( 2 )
𝐸
2
b) How to determine the Sample Size for
𝑝̂𝑞̂•(𝑍𝛼 ) 𝑍𝛼 2
Estimating 𝑝? 𝑛= 2
or 𝑛 = 𝑝̂ 𝑞̂ ( 2 )
2 𝐸 𝐸
2
0.25(𝑍𝛼)
2
𝑛= for 𝑝̂ 𝑖𝑠 𝑢𝑛𝑘𝑛𝑜𝑤𝑛
𝐸2
c) Slovin’s Formula 𝑁
𝑛=
1 + 𝑁𝑒 2
Note: the resulting value of n is rounded
up to the nearest whole number.

What I Can Do

PERFORMANCE TASK (SINGLE OUTPUT):

LEARNING COMPETENCY: Solve problems involving sample size

determination.

PERFORMANCE STANDARD: The learner is able to apply suitable sampling

distributions of the sample mean to solve real-life problems in different disciplines.

28
 SITUATION: One of the few negative effects of quitting smoking is weight gain. The data
below shows the weight gain (in pounds) of 18 respondents 12 months after they quit. If
the mean gain follows a normal distribution with a standard deviation of 9 pounds, estimate
the mean weight gain of the 18 respondents at a 95% confidence level.
14 13 20 22 12 12 17 10 12 9 11 17 15 24 29 13 13 19

GOAL: Your goal is to assist the Chairperson of the Smoking Cessation Program of the
Department of Health by providing a statistical report that involves estimation.

ROLE: You are a statistician who will estimate the mean weight gain of 18 smokers who
gained weight after they quit smoking.
PRODUCT: You are expected to prepare a statistical report which includes the result of
the estimation. Moreover, the interpretation of the analysis should be provided.

AUDIENCE: This proposal shall be presented and evaluated by the Chairperson of the
Smoking Cessation Program of the Department of Health.

STANDARDS: Your output will be evaluated based on the following: accuracy of the
estimation, comprehensiveness, and acceptability of interpretation of the results, and
content of the written presentation.

RUBRIC FOR THE REPORT

4 3 2 1 0
CRITERIA OUTSTANDING SATISFACTORY DEVELOPING BEGINNING MISSING

Accuracy of The report The report shows The report The report No attempt
Estimation shows accurate accurate and shows minimal needs made
and detailed convincing errors that improvement as
results of the results of the affect the it contains
estimation estimation accuracy of the numerous
procedure. procedure. estimation. significant errors
which affect the
accuracy of the
estimation.
Comprehensiven The The interpretation The The No attempt
ess and interpretation is is correct, and interpretation interpretation is made
acceptability of complete, claims are contains some completely
the interpretation correct, and mathematically errors that are incorrect.
of the results supported with acceptable not
details that all mathematically
claims are acceptable
mathematically
acceptable.

Content of the Content and Content and Content and Content and No attempt
Written illustrations are illustrations are illustrations are illustrations are made
Presentation clear, clear and somewhat not clear.
impressive, and impressive clear.
convincing.

29
 Assessment
Direction: Read each item carefully. Select the correct answer among the choices given and
write the letter of your choice. Write your answer on a separate sheet of paper.
1. Which type of distribution whose graph is bell-shaped, symmetric about t = 0, and its
variance is greater than 1?
A. binomial t-distribution B. z-distribution
C. geometric t-distribution D. student’s t-distribution
2. What happens to the shape of the t-distribution as n becomes larger?
A. The shape skewed to the left
B. The shape skewed to the right
C. The shape becomes platykurtic
D. The t-distribution gets closer to the standard normal distribution
3. What statistical analysis is appropriate to use with small samples taken from an
approximately normal population?
A. binomial t-distribution B. t-distribution
C. geometric t-distribution D. z-distribution
4. When n ≥ 30 and the population standard deviation is known, what is the appropriate
distribution?
A. binomial t-distribution B. t-distribution
C. geometric t-distribution D. z-distribution
5. What is the critical value of t if the sample size n is 8, two-tailed at 99% confidence level?
A. 3.169 B. 3.250 C. 3.355 D. 3.500

6. A sample size n = 20 is a simple random sample selected from a normally distributed

population. Find the value of t such that the shaded area to the left of t is 0.05?
A. 1.720 B. 1.725 C. -1.729 D. 1.730
7. What is the length of the confidence interval given that 𝜎 = 0.4; 𝑛 = 49 at 95% confidence
level?
A. 0.224 B. 0.225 C. 0.252 D. 0.254
8. What will happen to the width of the confidence interval estimate when the population
standard deviation is doubled?
A. It will increase by 100% B. It will decrease by 50%
C. It will decrease by 100% D. It will remain the same
9. What is the effect on the interval estimate if the sample size will increase by four times?
A. The width of the interval will decrease by half.
B. The interval will be two times wider than before.
C. The interval will be four times wider than before.
D. The width of the interval will decrease by four times.
10. What should be the minimum sample size for a study that aims to estimate the proportion
of OFWs from Germany who have stayed in their jobs for at least five years? Use a
confidence level of 95% with a 3% margin error.
A. 1000 B. 1067
C. 1050 D. 1068

30
31
Publishing House, Inc.
Mercado, J.P. 2016. Next Century Mathematics: Statistics and Probability. Phoenix
Publishing, Inc.:Educating minds, Shaping the future.
Gabuyo, Y.A. and M.C Cardenas. 2016. Statistics and Probability. Philippines: The Inteligente
Belecina, R.E. and E. Mateo. 2016. Statistics and Probability. Philippines: Rex Bookstore, Inc.
Publishing, Inc.
Barcelona, A.B. 2020. Statistics and Probability for Senior High School: Golden Cronica
References
Pretest
1. D 2. C 3. B 4. B 5. D
6. C 7. C 8. D 9. B 10. C
11. D 12. D What’s More
Activity 4: Solve Me!
Lesson 1 1. a) -t = 1.341
b) t = 1.341
What’s In c) t = ±2.602
Activity 1: Activate My Prior Knowledge! d) t = 1.753
1. vertical, horizontal
2. T 2. a) 97.5%
3. T b) 𝑡1 represents the 97.5th percentile 𝑡97.5
4. T c) ) 𝑡1 = 2.093
5. T
6. Boolean, Gaussian
7. T Lesson 2.
8. 𝜇 = 1, 𝜎 = 0, 𝜇 = 0, 𝜎 = 1 What’s In Activity 1
9. T 1. D 2. B 3. A 4. D 5. D
10. T
What’s More Activity 2
What’s New I. a) 5.25 b) 0.502
Activity 2: Compare Me! II. a) 19.6 b) 28.20
III. a) 0.42 b) 0.20
IV.a) 4.97 b) 0.4.79
V. a) 0.08 b) 0.10
VI.a) 68 b) 718
VII. a) 36 b) 271 c) 370
Assessment: Posttest
Activity 3: Use Me!
1. D 2. D. 3. B 4. D 5. D
1. 1.476 or -1.476 6. C 7. A 8. A 9. A 10. D
2. ±2.447
3. . ±1.363
4. 2.500 or -2.500
. ±2.575
Answer Key
For inquiries or feedback, please write or call:

Department of Education – Schools Division of Laoag City

Curriculum Implementation Division (CID)
Brgy. 23 San Matias, Laoag City 2900
Contact Number: (077) 771-3678
Email Address: [email protected]