11

Statistics
and Probability
Quarter 3 – Module 8
Confidence Interval
 ’s In

Point estimates and Interval estimates

• Point estimate. A point estimate of a population parameter is a single value of a statistic.

For example, the sample mean is a point estimate of the population mean µ. Similarly,
the sample proportion p is a point estimate of the population proportion P. (Malate J.S.,
2017)
Like, the average height of STEM 11 learners in a certain senior high school is
4 feet and 8 inches, we are giving point estimate.
• Interval estimate. An interval estimate is defined by two numbers, between which a
population parameter is said to lie. For example,
a < µ < b is an interval estimate of the population mean µ. It indicates that the
population mean is greater than a but less than b. (Malate J.S., 2017)
Like, the area of the classrooms in a certain senior high school is between 40
square meters and 50 square meters, we are giving an interval estimate.

Confidence Interval

A confidence interval consists of three parts namely A statistic, A margin of error, and
A confidence level. But if we consider the confidence level as part of the margin of error,
then confidence interval consists only of two parts namely A statistic and A margin of error.
These parts help us compute the ends or confidence limit of an interval.

Example:
1. 4ft. 8in. to 5ft. 1in., the left end of the confidence interval is 4ft. 8in.
and 5ft. 1in is the right end.
2. (5ft. 2in, 40kgs), 5ft. 2in is the left end while 40kgs is the right end.

Confidence Level

A confidence level is part of all possible samples (in percent) taken from the same
population that can be expected to include the true population parameter.

Example:
1. 95% confidence level means 95% of the intervals contain the true population
parameter.
2. 99% confidence level means 99% of the intervals contain the true population
parameter.

7
Margin of Error

The margin of error is the maximum likely difference (in percent) between sample
mean and the real population value µ.

Example. A teacher conducts a survey from a group of senior high school learners whether
they love mathematics and found out that 60% love mathematics. The teacher states that
his/her findings had a margin of error of 5% and a confidence level of 95%. This means that
if we ask group of learners from the same group of senior high school learners we are 95%
confident that between 55% and 65% will respond they ‘Love mathematics’.

Let σ be the population standard deviation, n is the sample size and Z /2 is the
suitable z-value for the preferred level of confidence. So, the general formula for the margin
of error for the sample mean is

𝜎
𝐸 = 𝑧𝛼/2 ∙
√𝑛

However, when the population standard deviation is unknown the sample standard
deviation s is used to approximate σ. So,

𝜎 𝑠
𝐸 = 𝑧𝛼/2 ∙ ≈ 𝑧𝛼/2 ∙
√𝑛 √𝑛

Steps for computing the margin of error for a sample mean:

Note: Must meet the condition that the population is normally distributed or n ≥ 30 (large)

1. Determine the population standard deviation σ, the sample size n and the suitable z
– value.
2. Multiply the z – value to the quotient of the population standard deviation σ and the
square root of the sample size n.

Example: Consider the following information:

= 98, σ = 5 and n = 190. Find the maximum error E for 95% Confidence
Interval

Solution:
𝜎
𝐸 = 𝑧𝛼/2 ∙ Formula
√𝑛
5
𝐸 = 1.96( ) by substitution
√190
𝐸 = 0.71

8
 ’s New

Identifying the length of a confidence interval

Confidence Interval Estimates of Population Parameters

Let µs be the mean and σs be the standard deviation of the sampling distribution of a
statistics S. The sampling distribution S is approximately normal or n ≥ 30 (large). The
sample statistics S is expected to lie in the interval as shown in table 1.0 below.
TABLE 1.0
Confidence level 80% 90% 95% 98% 99%
Z /2 (Confidence 1.28 1.64 1.96 2.33 2.58
Coefficients)
𝜎 𝜎 𝜎 𝜎 𝜎
Confidence interval S±Z /2 S±Z /2 S±Z /2 S±Z /2 S±Z /2
√𝑛 √𝑛 √𝑛 √𝑛 √𝑛
formula for estimating
the sample mean µs.
or or or or or
𝜎 𝜎 𝜎 𝜎 𝜎
S ± 1.28 S ± 1.645 S ± 1.96 S ± 2.33 S± 2.58
√𝑛 √𝑛 √𝑛 √𝑛 √𝑛

Example 1. Identify the confidence interval in which the sample mean µs lies
at 98% confidence level.

Solution
𝜎
S±Z /2 = Formula
√𝑛

𝜎
= S ± 2.33 2.33 is the confidence coefficient at 98% confidence
√𝑛
level

So, at 98% confidence level the sample mean µs lies in the confidence level S ±
𝜎
2.33 .
√𝑛

9
Computing the length of the Confidence Interval

A. Large Sample or n ≥30 Confidence Interval for a Population Mean

• If 𝜎 is known and the sample mean is specified, the formula for Confidence Interval
𝜎
is ± 𝑧𝛼/2 ∙ 𝑛
√
• If 𝜎 is unknown and the sample mean is specified, the formula for Confidence Interval
𝑠
is ± 𝑧𝛼/2 ∙ 𝑛
√

Steps

1. Determine the confidence coefficient

2. Find the maximum error E.
3. Find the lower and the upper confidence limits.
4. Describe the results.

(Belecina R.R., et.al., 2016)

Example 1. A sample of size 49 has sample mean 35 and sample standard

deviation 14. Construct a 98% confidence interval for the
population mean using this information. Interpret its meaning.

Solution:

Step 1. The confidence coefficient is 2.33 (see table 1.0)

Step 2. Find the maximum error E
𝑠
𝐸 = 𝑧𝛼/2 ∙ 𝑛 because s is the best estimate
√
for 𝜎 if unknown.
14
𝐸 = 2.33 ∙ by substitution
√49
𝐸 = 4.66

Step 3. Find the lower and the upper confidence limits.

𝑠 𝑠
– 𝑧𝛼/2 ∙ <µ< + 𝑧𝛼/2 ∙
√𝑛 √𝑛

35 – E < µ < 35 + E

35 – 4.66 < µ < 35 + 4.66

30.34 < µ < 39.66

10
Step 4. Describe the results.

We are 98% confident that the population mean µ lies in the interval
[30.34 , 39.66] in the sense that in repeated sampling 98% of all intervals constructed from
the sample data in this manner will contain µ.(Malate J.S., 2017)

B. Large Sample Estimation of a Population Proportion

Definition:

i. Let p denote the proportion of the population that lean towards a specific
proportion.
ii. To estimate p, a random sample should be chosen, the then p should be
estimated by the proportion of the sample.
iii. We call this estimator 𝑝̂ , we can express it by
𝑋
𝑝̂ = 𝑛 , where X is the number of members in the sample who lean towards
a specific proposition and n is the sample size.

iv. The complement of 𝑝̂ 𝑖𝑠 𝑞̂

𝑞̂ = 1 − 𝑝̂

Example: In a survey of 150 households, 60 have air conditioner. Find the estimator
𝑝̂ 𝑎𝑛𝑑 𝑞̂.

Solutions:

n = 150 X = 60
𝑋 60
𝑝̂ = = = 0.4
𝑛 150

𝑞̂ = 1 − 𝑝̂ = 1 − 0.4 = 0.6

(Malate J.S., 2017)

Confidence Interval Estimate for Proportions

𝑝̂ ∙𝑞̂
• The error of an estimate is 𝐸 = 𝑧 ∙ √ 𝑛
• The confidence interval is: 𝑝̂ − 𝐸 < 𝑝 < 𝑝̂ + 𝐸

11
Example:

A sample poll of 100 voters chosen at random from all voters in a given district
indicated that 55% of them were in favor of a particular candidate. Find 98% confidence
limits for the proportion of all the voters in favor of this candidate.

Solution:

Given: n = 100 𝑝̂ = 0.55 𝑞̂ = 1 − 0.55 = 0.45

Step 1. The confidence coefficient z = 2.33 at 98% level of confidence

(see table 1.0).

Step 2.

𝑝̂ ∙𝑞̂ (0.55)∙(0.45)
𝐸 = 𝑧∙√ = (2.33) ∙ √ = (2.33)√0.002475 = (2.33)(0.05) = 0.12
𝑛 100

Step 3. To find the lower and the upper confidence limits

𝑝̂ − 𝐸 < 𝑝 < 𝑝̂ + 𝐸

0.55 – 0.12 < p < 0.55 + 0.12

0.43 < p < 0.67 , 0.43 and 0.67 are the 98% confidence limits.

Step 4. We are 98% confident that the interval 43% to 67% contains the
true proportion of all the voters in favor of this candidate.

C. Small Sample Estimation of a Population Mean

The confidence interval formulas in the previous examples are based on the
Central Limit Theorem, the statement that for large samples is normally distributed
𝜎
with mean µ and standard deviation . According to the Central Limit Theorem, the
√𝑛
sampling distribution of a statistic (like a sample mean) will follow a normal
distribution as long as the sample size is sufficiently large. Therefore, when we
know the standard deviation of the population, we can compute a z-score, and use the
normal distribution to evaluate probabilities with the sample mean.
But sample sizes are sometimes small, and often we do not know the standard
deviation of the population. When either of these problems occur, we use t score
whose formula is given as:
𝑥̅ −𝜇
𝑡= 𝑠
√𝑛

12
Where is the sample mean, 𝜇 is the population mean, s is the standard
deviation of the sample, and n is the sample size. The distribution of the
t statistic is called the t distribution or the Student t distribution.
(Malate J.S., 2017)

The maximum error of the estimate is given by the formula for E as:

𝑠
𝐸 = 𝑡𝛼/2
√𝑛

The limits for the confidence interval is given as:

– E<µ< +E

Example:

A sample of size 15 drawn from a normally distributed population has a sample mean
of 35 and a sample standard deviation of 14. Construct a 95% confidence interval for the
population mean and interpret its meaning.

Solution:

Given: n = 15 = 35 s = 14

Step 1: The confidence level 95% means that 𝛼 = 1 – 0.95 = 0.05 so

𝛼/2 = 0.05/2 = 0.025
Since the sample size is n = 15, there are n – 1 = 15 – 1 = 14
degrees of freedom. By the student’s t distribution table below
the confidence coefficient t 𝛼/2 = t0.025 = 2.145

Step 2: To find E,

𝑠 14
𝐸 = 𝑡𝛼/2 = (2.145) = (2.145)(3.61478) = 7.75 ≈ 7.
√𝑛 √15

Step 3: To find the lower and the upper confidence limits,

– E<µ< +E
35 – 7.8 < µ < 35 + 7.8
27.2 < µ < 42.8 Confidence Interval

Step 4. We are 95% confident that the interval 27.2 to 42.8 contains the true population
mean.

13
Sample Size Considerations

14
Minimum Sample Size for Estimating a Population Mean

The estimated minimum sample size n needed to estimate a population mean µ to

within E units at 100(1 – 𝛼)% confidence is.

𝑧𝛼/2 σ 2
𝑛=( )
𝐸

Example Find the minimum sample size necessary to construct a 99%

confidence interval for µ with a margin of error E = 0.2. Assume
that the population standard deviation is σ = 1.3

Solution.

Step 1. Determine the confidence level:

The confidence level is 99%.

Step 2. Determine the confidence coefficient:

With a 99% confidence level, 𝛼 = 0.01, so 𝑧𝛼/2 = 2.58 (see table 1.0)

Step 3. Determine the margin of error E.

𝐸 = 0.2

Step 4. Compute n using the formula:

𝑧𝛼/2 σ 2 (2.58)(1.3) 2 3.354 2
𝑛=( ) =( ) =( ) = (16.77)2 = 281.2329 ≈ 282(Round up
𝐸 0.2 0.2
the resulting
So, the required minimum sample size is 282.

Minimum Sample Size for Estimating a Population Proportion

The estimated minimum sample size n needed to estimate a population proportion p

to within E units at 100(1 – 𝛼)% confidence is.
2
(𝑧𝛼/2 ) ∙𝑝̂(1−𝑝̂ )
𝑛=
𝐸2

15
 Steps in Solving the Sample Size Involving Proportions

Step 1. Determine the confidence level.

Step 2. Determine the confidence coefficient.
Step 3. Determine the margin of error E.
Step 4. Determine 𝑝̂ .
Step 5. Solve n by substituting the values in the formula.
Step 6. Round up the resulting value.

Example: Find the necessary minimum sample size to construct a 98% confidence interval
for p with a margin of error E = 0.05,

a. Assuming that no prior knowledge about p is available; and

b. Assuming that prior studies suggest that p is about 0.1

Solutions:

Step 1. The confidence level is 98%.

Step 2. The confidence coefficient 𝑧𝛼/2 = 2.33. (see table 1.0)

Step 3. The margin of error E = 0.05.

Step 4. Since p ≈ 0.1we estimate 𝑝̂ = 0.1

Step 5. Solving for n;

2
(𝑧𝛼/2 ) ∙ 𝑝̂ (1 − 𝑝̂ ) (2.33)2 ∙ (0.1)(1 − 0.1 ) 5.4289 ∙ (0.1)(0.9 )
𝑛= = = = 195.44
𝐸2 0.052 0.0025

Step 6. Rounding up the result 195.44 ≈196

So, the necessary minimum sample size is 196.

16
 is It

The concept of the degrees of freedom is used in the t-distribution. The

degrees of freedom, denoted by df, are the numbers of values that are free to
vary after a sample statistic has been computed.

Properties of the t-distribution are as follows:

1. The t-distribution is bell shaped and symmetric about the mean.

2. The t-distribution is a family of curves, each determined by a parameter called

the degrees of freedom. The degrees of freedom are the number of free
choices left after a sample statistic is calculated. When you use a t-distribution
to estimate a population mean, the degrees of freedom are equal to one less
than the sample size, df = n-1.
3. The total area under a t-curve is 1 (or 100%).

4. The mean, median, and mode of the t-distribution are equal to zero.

5. As the degrees of freedom increase, the t-distribution approaches the normal

distribution. After 30 df the t-distribution is very close to the standard normal
z-distribution.

Degrees of Freedom

A degree of freedom occurs for every data value which is allowed to vary
once a statistic has been fixed. For a single mean, there are n – 1 degrees of
freedom. This value will change depending on the statistic being used.

If the population standard deviation, sigma is unknown, then the mean has
a student t distribution and the sample standard deviation and the sample
standard deviation is used instead of the population standard deviation.

What is ta/2, and why must we use it when n < 30 and 𝜎 is unknown?

When n < 30, the quantity does not have an approximately standard
normal distribution, even though we assume here that the population is normal.
Instead, t has a “Student’s t distribution with n- 1 degrees of freedom”.

There is a different t distribution for each value for the degrees of freedom
(df). These distributions are not normal, although they are symmetrical around
zero, and mound shaped.

17
 The quantity 𝑡𝛼/2 denotes the t-value such that the area to its right under
the Student’s t distribution (with df = n-1) is 𝛼/2.

Example No. 1

1. Find the 𝑡𝛼/2 for a 99% confidence interval when the sample size is 20.

Solution:

𝑑𝑓 = 𝑛 − 1

= 20-1 = 19

Find 19 in the left column and 99% in the row labeled confidence
intervals. The intersection where the two meets gives the value for 𝑡𝛼/2 which is
2.861.

Confidence 0.800 0.900 0.950 0.980 0.990 0.998 0.999

interval
d.f. 0.100 0.050 0.025 0.010 0.005 0.001 0.0005
1
2
3

19 2.861

How to find the Percentiles of the t-Distribution

When you want to find percentiles for a t-distribution, you can use the t-
table. A percentile is a number on a statistical distribution who is less-than the
probability in the given percentage; for example, the 95 th percentile of the t-
distribution with n – 1 degrees of freedom is that value of whose left-tail (less
than) probability is 0.05.

The t-table shows right-tail probabilities for selected t-distributions. You

can use it to solve the following problems.

Example No. 2

18
 Suppose you have a sample size 10 and you want to find the 95 th
percentile of its corresponding t-distribution. You have n – 1 = 9. The 95 th
percentile is the number where 95% of the values lie below it and 5% lie above
it, so you want the right-tail area to be 0.05. Move across the row, find the
column for 0.05, and you get 1.8331. This is the 95 th percentile of the t-
distribution with 9 degrees of freedom.
Now, if you increase the sample size to n = 20, the value of the 95 th
percentile decreases; look at the row for 20 – 1 =19 degrees of freedom, and in
the column for 0.05 (a right-tail probability of 0.05) you find 1.7291.

The t-distribution

The t-distribution is a probability distribution that arises when estimating

the mean of a normally distributed population in situations where the sample size
is small, and population standard deviation is unknown.

The concept of the degrees of freedom is used in the t-distribution. The

degrees of freedom, denoted by df, are the numbers of values that are free to vary
after a sample statistic has been computed.

Properties of the t-distribution are as follows:

6. The t-distribution is bell shaped and symmetric about the mean.

7. The t-distribution is a family of curves, each determined by a parameter called

the degrees of freedom. The degrees of freedom are the number of free
choices left after a sample statistic is calculated. When you use a t-distribution
to estimate a population mean, the degrees of freedom are equal to one less
than the sample size, df = n-1.
8. The total area under a t-curve is 1 (or 100%).

9. The mean, median, and mode of the t-distribution are equal to zero.

10. As the degrees of freedom increase, the t-distribution approaches the

normal distribution. After 30 df the t-distribution is very close to the standard
normal z-distribution.

19
Degrees of Freedom

A degree of freedom occurs for every data value which is allowed t o vary
once a statistic has been fixed. For a single mean, there are n – 1 degrees of
freedom. This value will change depending on the statistic being used.

If the population standard deviation, sigma is unknown, then the mean has
a student t distribution and the sample standard deviation and the sample standard
deviation is used instead of the population standard deviation.

What is t a/2, and why must we use it when n < 30 and 𝜎 is unknown?

When n < 30, the quantity does not have an approximately standard normal
distribution, even though we assume here that the population is normal. Instead, t
has a “Student’s t distribution with n- 1 degrees of freedom”.

There is a different t distribution for each value for the degrees of freedom
(df). These distributions are not normal, although they are symmetrical around
zero, and mound shaped.

The quantity 𝑡𝛼/2 denotes the t-value such that the area to its right under the
Student’s t distribution (with df = n-1) is 𝛼/2.

Example No. 1

2. Find the 𝑡𝛼/2 for a 99% confidence interval when the sample size is 20.

Solution:

𝑑𝑓 = 𝑛 − 1

= 20-1 = 19

Find 19 in the left column and 99% in the row labeled confidence intervals.
The intersection where the two meets gives the value for 𝑡𝛼/2 which is 2.861.

20
 Confidence 0.800 0.900 0.950 0.980 0.990 0.998 0.999
interval
d.f. 0.100 0.050 0.025 0.010 0.005 0.001 0.0005
1
2
3

19 2.861

How to find the Percentiles of the t-Distribution

When you want to find percentiles for a t-distribution, you can use the t-
table. A percentile is a number on a statistical distribution who is less-than the
probability in the given percentage; for example, the 95 th percentile of the t-
distribution with n – 1 degrees of freedom is that value of whose left-tail (less
than) probability is 0.05.

The t-table shows right-tail probabilities for selected t-distributions. You

can use it to solve the following problems.

Example No. 2

Suppose you have a sample size 10 and you want to find the 95 th percentile
of its corresponding t-distribution. You have n – 1 = 9. The 95 th percentile is the
number where 95% of the values lie below it and 5% lie above it, so you want the
right-tail area to be 0.05. Move across the row, find the column for 0.05, and you
get 1.8331. This is the 95 th percentile of the t-distribution with 9 degrees of
freedom.

Now, if you increase the sample size to n = 20, the value of the 95 th
percentile decreases; look at the row for 20 – 1 =19 degrees of freedom, and in
the column for 0.05 (a right-tail probability of 0.05) you find 1.7291.

21
 ’s More

Activity 1. Supply the Missing Piece!

Find the missing value. Use the t-distribution Table.
1. Given: 90𝑡ℎ 𝑝𝑒𝑟𝑐𝑒𝑛𝑡𝑖𝑙𝑒, 𝑠𝑎𝑚𝑝𝑙𝑒 𝑠𝑖𝑧𝑒 𝑛 = 10
Find the following:
a) 𝛼
b) t – value
c) df
2. Given: t-value = 2.492
Find the following:
a) sample size n
b) df
c) 𝛼
d) Percentile

I Have Learned

Activity 2
A. Find the values for each of the following degree of freedom and t-values with
the given percentile. Write your answer on the space provided.

1. 𝑡𝛼/2 and n = 16 for the 99% confidence interval

df = __________ 𝑡(.005,15) = ________________
2. 𝑡𝛼 and n = 25 for the 98% confidence interval
2
df = __________ 𝑡(.01,24) = ________________
3. 𝑡𝛼/2 and n = 8 for the 95% confidence interval
df = __________ 𝑡(.025,7) = ________________
4. 𝑡𝛼/2 and n = 12 for the 90% confidence interval
df = __________ 𝑡(.05,11) = ________________
5. 𝑡𝛼/2 and n = 20 for the 99% confidence interval
df = __________ 𝑡(.005,19) = ________________

22
B. Summarize the lesson by completing the sentences below:
1. When asked of an estimation of population mean but population standard
deviation is unknown, the _______________can be used.
2. The t-distribution is similar to the standard normal distribution in the
following ways:

2.1 __________________________________________
2.2 __________________________________________
2.3 __________________________________________
2.4 __________________________________________

I Can Do

Activity 3

(NOTE: For Students who can access Microsoft excel)

Use of Microsoft Excel in finding the t-value given degrees of freedom and
level of significance.

A. Finding the t-value given level significance (alpha) and degrees of freedom
v(nu)

(Note: The computer t-value is for two-tailed, thus α must be multiplied by 2.

Example t(0.01,14) = 2.624494

1. Highlight A1;
2. On A1, Type [=TINV(0.01*2,14)];→ 14-degrees of freedom;
3. Press ENTER
4. You will find the value 2.624494 on A1;
5. Good Luck!

23