LESSON 15- TEST OF HYPOTHESIS

The first thing a researcher will do is to choose a topic for his research. Next is to formulate the statement of the
problem. Then, he/she should enumerate the research questions and identify the target population. Another important thing
a researcher should do is to make assumptions about the population. These assumptions which may or may not be true are
called statistical hypotheses.

Statistical Hypotheses:
1. The null hypothesis, denoted by 𝐻0 , is a statement saying that there is no significant difference between
population parameter and the value that is being claimed. It is the hypothesis to be tested.
2. The alternative hypothesis, denoted by 𝐻𝑎 , is a statement saying that there is a significant difference between
the population parameter and the value that is being claimed. This is a statement that will be true once the
null hypothesis is rejected.

The Head of the Statistics Department of a certain high school claims that the mean height of Grade
EXAMPLE 1
7 students is 163 cm. The mean height of 45 randomly selected Grade 7 students is 161cm. using
0.01 significance level, can it be concluded that the mean height of grade 7 students is different
from 163 as claimed by the Head of Statistics Department? The following are the null and the
alternative hypotheses.
a. 𝐻0 ∶ 𝜇 = 163
b. 𝐻𝑎 ∶ 𝜇 ≠ 163

EXAMPLE 2 Last year the mean number of ladies’ bags produced by JS Company was 2,500 each day. This
year, the manager claims that there is an increase in the number of bags produced. A researcher
who wants to find out whether this is true counted the number of bags produced each day for a
period of one month. His computation resulted to mean of 2,515 ladies’ bags. At 0.05 significance
level, is there enough evidence to conclude that the mean number of ladies’ bags produced by JS
Company is greater than 2,500? The following are the null and alternative hypotheses.
a. 𝐻0 ∶ 𝜇 = 2,500
b. 𝐻𝑎 ∶ 𝜇 > 2,500

EXAMPLE 3 The manager of TV station claims that the mean number of people watching their new sitcom
Manila is 500,000 each day. A student researcher who wants statistical evidence on this claim
conducted her own survey. Her survey resulted to a mean of 499,995. Using 0.05 significance level,
can it be concluded that the mean number of people watching the new sitcom is less than 500,000?
The following are the null and alternative hypotheses.
a. 𝐻0 ∶ 𝜇 = 500,000
b. 𝐻𝑎 ∶ 𝜇 < 500,000

EXAMPLE 4 The LB Company produces an average of 4% defective bulbs each day. Recently, some of the
machines were upgraded. Out of 400 bulbs randomly selected only 14 bulbs were found defective.
Does this suggest that there is a decrease in the number of defective bulbs produced each day? Use
0.05 significance level. The following are the null and alternative hypotheses.
a. 𝐻0 ∶ 𝑝 = 0.04
b. 𝐻𝑎 ∶ 𝑝 < 0.04

✓ In each of the given examples, the null hypothesis is assumed to be true. For instance, in Example 1, the null
hypothesis is assumed to be true, that is the mean height of Grade 7 students is 163. If the researcher can gather
enough evidence that can result to the rejection of the null hypothesis then he/she can conclude that the mean height
of Grade 7 students is not equal to 163cm. A rejection of the null hypothesis results in the acceptance of the
alternative hypothesis.

TERMINOLOGIES
▪ Confidence Interval
o A confidence interval, also known as the acceptance region, is a set of values for the test statistic for which
the null hypothesis is accepted. i.e. if the observed test statistic is in the confidence interval then we accept
the null hypothesis and reject the alternative hypothesis.
▪ Significance Levels
o Confidence intervals can be calculated at different significance levels. We use α to denote the level of
significance and perform a hypothesis test with a 100(1−α)% confidence interval.
o Confidence intervals are usually calculated at 5% or 1% significance levels, for which α=0.05 and α=0.01
respectively. Note that a 95% confidence interval does not mean there is a 95% chance that the true value
being estimated is in the calculated interval. Rather, given a population, there is a 95% chance that choosing
 a random sample from this population results in a confidence interval which contains the true value being
estimated.
▪ Critical Region
o A critical region, also known as the rejection region, is a set of values for the test statistic for which the
null hypothesis is rejected. i.e. if the observed test statistic is in the critical region then we reject the null
hypothesis and accept the alternative hypothesis.
▪ Critical Values
o The critical value at a certain significance level can be thought of as a cut-off point. If a test statistic on
one side of the critical value results in accepting the null hypothesis, a test statistic on the other side will
result in rejecting the null hypothesis.

❖ REJECTION REGION, CRITICAL VALUE and LEVEL OF SIGNIFICANCE

The researcher should follow some steps and rules to help him/her decide whether or not to reject the null
hypothesis. For instance, in Example 1, the researcher should compute for the sample mean which in the problem is the best
point estimate for the population mean of 163 cm. is it enough to compare the sample mean with the population mean of
163 cm and then make a decision? Is there a difference between the mean and the population mean? If there is, how
significant is the difference between the mean and the population mean? These are some of the questions he/she should
consider before making a decision.
The researcher needs to convert the sample mean to a value called test statistic. This value would help him/her make
a decision and draw a conclusion. He/she should establish a rejection region. In the figure below, the rejection region and
the non-rejection region are indicated.

Critical Value Critical Value

Rejection Rejection
Region Region
Non-rejection region

Separating the two regions is a point called the critical value which is derived from the level of significance.
If the test statistic or computed value falls in the rejection region, that is, it falls beyond the critical point, then the null
hypothesis is rejected. The level of significance, alpha 𝛼 corresponds to the rejection region and the difference of one and
the alpha (1- 𝛼 ) corresponds to the area of the curved occupied by the non-rejection region. The most commonly used
values for alpha are 0.01, 0.05, and 0.10. If the level of significance used in Example 2 is 5% or 0.05, then there is a 5%
chance or 5 chances in 100 that the null hypothesis would be rejected when it should be accepted. That is whenever the null
hypothesis is true, the researcher 95% confident that he/she would make the correct decision. The level of significance is
the probability that the test statistic would fall in the rejection region when in fact the null hypothesis is actually true.

TYPES OF ERRORS:

1. Type I error
A type I error is committed when the researcher rejects a null hypothesis when in fact it is true. The
probability of committing Type I error is also called the level of significance. For a 90% confidence level, the level
of significance or the value of the alpha is 0.01. This means that there is a 10% probability that the researcher will
reject a true null hypothesis. For a 99% confidence level, the level of significance is 0.01. This means that there is
1% probability that the researcher will reject the null hypothesis that is true. But if the researcher rejects null
hypothesis that is false, then he has reached a correct decision. Alpha α is used to represent the probability of a Type
I error.
2. Type II error
A type II error is committed when the researcher fails to reject a null hypothesis that is false. But if the
researcher fails to reject a true hypothesis, then, there is no error committed. Beta 𝛽 is used to represent the
probability of a Type II error.
Decision True State of Nature
The null hypothesis is true. The null hypothesis is false.
Reject the null hypothesis Type I error Correct decision
H0.
Accept the null hypothesis Correct decision Type II error
H0.

❖ ONE-TAILED or TWO-TAILED TESTS

If you’re lucky enough to be given a picture, you’ll be able to tell
if your test is one-tailed or two-tailed by comparing it to the image
above. However, most of the time you’re given questions, not
pictures. So it’s a matter of deciphering the problem and picking
out the important piece of information. You’re basically looking
for keywords like equals, more than, or less than.
Example question #1: A government official claims that the dropout rate for local schools is 25%. Last year, 190 out of
603 students dropped out. Is there enough evidence to reject the government official’s claim?
Example question #2: A government official claims that the dropout rate for local schools is less than 25%. Last year,
190 out of 603 students dropped out. Is there enough evidence to reject the government official’s claim?
Example question #3: A government official claims that the dropout rate for local schools is greater than 25%. Last year,
190 out of 603 students dropped out. Is there enough evidence to reject the government official’s claim?

Step 1: Read the question.

Step 2: Rephrase the claim in the question with an equation.
1. In example question #1, Drop out rate = 25%
2. In example question #2, Drop out rate < 25%
3. In example question #3, Drop out rate > 25%.

Step 3: If step 2 has an equals sign in it, this is a two-tailed test. If it has > or < it is a one-tailed test.
What is the critical value when the test is two-tailed, the level of significance is 0.05, the variance
EXAMPLE 1 is known, and the n = 35?

SOLUTION:
If the test is two-tailed, divide the level of significance by 2 and then subtract the quotient from 0.5. Since the
variance is known, and n >30, use the Areas under the Normal Curve.
𝛼
= 0.025
2
0.5 – 0.025 = 0.475 or 0.4750
The area 0.4750 is under the column headed 6. Move along this row to the left until 1.9 under the column headed z
is reached. Therefore, 𝑧𝛼 = 1.96. At 5% level of significance, the critical value is ±1.96.
2
(In example 1, if the test is one-tailed, the level of significance will not be divided by two)

What is the critical value when the test is two-tailed, and the level of significance is 0.05, the
EXAMPLE 2 variance is unknown, and n = 20?

SOLUTION:
If the variance is unknown, and n <30, use the Table of T-Critical values. There is a need to find the degrees of
freedom: df = n – 1 = 20 – 1 = 19. Divide 𝛼 = 0.05 by 2. In the “Table of Critical Values of t” locate 19 in the first column
df. Because the test is two-tailed with 𝛼 = 0.05, refer to the column indicating an area of 0.05 in two-tails. The critical value
is 2.093.