HYPOTHESIS TESTING

(Z-test and T-test)

BASIC STEPS:
1. State the hypotheses:
Ho :
Ha :
2. Type of Test: One-tailed or Two-tailed test?
3. Level of significance, a (commonly used values range from 0.01 to 0.10 particularly 5%(0.05) & 1%(0.01)
(To have a very small probability of rejecting the true null hypothesis due to random sample observations that might result to
high value of variation among sample statistics.)
4. Degrees of freedom, df (the formula depends on the type of test that will be used or sometimes is not applicable)
5. Critical/Tabular value (the value is simply obtained in the Critical Values Table for the chosen type of test)
6. Computed value…..(solve this by using the formula/equation for the chosen type of test)
7. Decision:
Make a decision. Compare the computed value to the critical value.
a. If the computed value is LESS than the critical value, ACCEPT the Null Hypothesis.
b. If the computed value is GREATER than or EQUAL to the critical value, REJECT the Null Hypothesis.
OR BY GRAPHICAL APPROACH
If the computed value in step 6 falls outside the colored area ACCEPT Ho!
If the computed value in step 6 falls within (inside) the colored area REJECT Ho!

Notes: The AREA of ACCEPTANCE is the WHITE area below the Normal Curve.
The AREA of REJECTION is the COLORED area below the Normal Curve.

8. Conclusion

A). Z-Test : The simplest and most common test on the significance of sample data.

a). One-Sample Mean Test (Z-test)

It is a test of hypothesis about the population mean – trying to compare the sample mean to the
perceived population mean. It requires the knowledge of the population mean and population standard
deviation. However, if the population standard deviation is not known, then the sample standard deviation
can be used as a substitute.
𝑿− 𝝁 𝒏 𝑿− 𝝁 𝒏
𝒁𝑪𝑶𝑴𝑷𝑼𝑻𝑬𝑫 = 𝒁𝑪𝑶𝑴𝑷𝑼𝑻𝑬𝑫 =
𝝈 𝒔
Where:
z = one sample z test Tabular Value of Z at 0.01 and 0.05 Level of Significance
𝐱 = 𝐬𝐚𝐦𝐩𝐥𝐞 𝐦𝐞𝐚𝐧
Level of Significance,a
µ = population mean Type of TEST
0.01 (1%) 0.05 (5%)
s = population standard deviation
ONE-TAILED test ±2.33 ±1.645
s = sample standard deviation
TWO-TAILED test ±2.575 ±1.96
n = number of observation in the sample

Assumptions in One Sample z test:

1. Subjects are randomly selected.
2. Population distribution is normal.
3. The population should be known.
4. Cases of the samples should be independent.
5. Sample size should be greater than or equal to 30.

Hypothesis Testing Page 1

(A). Z-test

𝑿− 𝝁 𝒏 𝑿− 𝝁 𝒏 Tabular Value of Z at 0.01 and 0.05 Level of Significance

𝒁𝑪𝑶𝑴𝑷𝑼𝑻𝑬𝑫 = 𝒁𝑪𝑶𝑴𝑷𝑼𝑻𝑬𝑫 =
𝝈 𝒔 Level of Significance,a
Type of TEST
0.01 (1%) 0.05 (5%)
= sample mean ONE-TAILED test ±2.33 ±1.645
µ = population mean TWO-TAILED test ±2.575 ±1.96
s = population standard deviation
s = sample standard deviation
n = number of observation in the sample

Example #1.
Suppose a sample size of 100 units has a mean = 2.7 and a standard deviation = 1.5. assuming
normality of the data, then test the null hypothesis that the population mean is equal to 3. Use level of
significance of 1%.

Given: Sample mean (𝑋 )= 2.7 Population mean (µ )= 3

Sample size ( n ) = 100 units Sample standard deviation ( s ) = 1.5
Level of Significance = 1% (0.01)

Solution:
1. State the
a). NULL (Ho) hypothesis: “The population mean is equal to 3”… or . .( µ = 3 )
b). ALTERNATIVE (Ha) hypothesis: : “The population mean is not equal to 3”…or..( µ ≠ 3 )
2. Determine if the test is One-Tailed or Two-Tailed = Two tailed.
3. Specify the Level of Significance (a) = (0.01) or (1%).
4. Determine the degree of freedom, df = for z test the degree of freedom is not applicable = (N-A).
5. Determine the TABULAR VALUE or CRITICAL VALUE (from the tabular value of Z) = +/-2.575
6. Determine the computed value (using the test statistics or Statistical Tool/Formula).
𝑿− 𝝁 𝒏 𝟐. 𝟕 − 𝟑 𝟏𝟎𝟎
𝒁𝑪𝑶𝑴𝑷𝑼𝑻𝑬𝑫 = = = −𝟐. 𝟎
𝒔 𝟏. 𝟓
7. Make a decision. Compare the computed value to the critical/tabular value.
a. If the computed value is LESS than the critical value, ACCEPT the Null Hypothesis.
b. If the computed value is GREATER than or EQUAL to the critical value, REJECT the Null
Hypothesis.
Since the computed value is less than the critical vale, therefore ACCEPT Ho!!!

OR BY GRAPHICAL APPROACH
If the computed value in step 6 falls outside the colored area ACCEPT Ho!
If the computed value in step 6 falls within (inside) the colored area REJECT Ho!

Notes:

The AREA of ACCEPTANCE is the WHITE area below the Normal Curve.

The AREA of REJECTION is the COLORED area below the Normal Curve.

From the figure, the computed value is in the WHITE area or is in the AREA of Acceptance,
Therefore, ACCEPT the NULL Hypothesis (ACCEPT Ho!!)

8, Conclusion.

a). NULL (Ho) hypothesis: “The population mean is equal to 3”… or . .( µ = 3 )

Hypothesis Testing Page 2

 Example #2.
A supplier sells ropes. He claims that the ropes have a mean strength of 34lbs and a variance of 64lbs.
A random sample of 32 ropes selected from a shipment yields a mean strength of 31lbs. Are you going
to reject the claim of the supplier at 5% level of significance?

Given: Sample mean strength (𝑋 )= 31 lbs Population mean strength (µ ) = 34 lbs

Sample size ( n ) = 32ropes Population variance strength ( v ) = 64 lbs
Level of Significance = 5% (0.05)

Solution:
1. State the
a). NULL (Ho) hypothesis: “The population mean strength is equal to 34”… or . .( µ = 34 )
b). ALTERNATIVE (Ha) hypothesis: : “The population mean strength is not equal to 34”…or..( µ ≠ 34 )
2. Determine if the test is One-Tailed or Two-Tailed = Two tailed.
3. Specify the Level of Significance (a) = (0.05) or (5%).
4. Determine the degree of freedom, df = for z test the degree of freedom is not applicable = (N-A).
5. Determine the TABULAR VALUE or CRITICAL VALUE (from the tabular value of Z) = +/-1.96
6. Determine the computed value (using the Test Statistics or Statistical Tool/Formula).
𝑿− 𝝁 𝒏 𝟑𝟏 − 𝟑𝟒 𝟑𝟐
𝒁𝑪𝑶𝑴𝑷𝑼𝑻𝑬𝑫 = = = −𝟐. 𝟏𝟐
𝝈 𝟖
7. Make a decision. Compare the computed value to the critical/tabular value.
a. If the computed value is LESS than the critical value, ACCEPT the Null Hypothesis.
b. If the computed value is GREATER than or EQUAL to the critical value, REJECT the Null Hypothesis.
Since the computed value is greater than the critical vale, therefore REJECT Ho!!!

OR BY GRAPHICAL APPROACH
If the computed value in step 6 falls outside the colored area ACCEPT Ho!
If the computed value in step 6 falls within (inside) the colored area REJECT Ho!

Notes:

The AREA of ACCEPTANCE is the WHITE area below the Normal Curve.

The AREA of REJECTION is the COLORED area below the Normal Curve.

From the figure, the computed value is in the COLORED area or is in the AREA of REJECTION,
Therefore, REJECT the NULL Hypothesis (REJECT Ho!!)

8, Conclusion.

“The population mean strength is not equal to 34”…or..( µ ≠ 34 )

Reject the suppliers claim!

Hypothesis Testing Page 3

 Example #3. (Z-test for Two-Sample Mean Test)
An admission test was administered to incoming freshmen in two colleges. Two independent samples of
150 students each are randomly selected and the mean scores of the given samples are: mean of
sample 1 = 88 and of sample 2 = 85. Assume that the variances of the test scores are 40 and 35,
respectively. Is the difference between the mean scores significant or can be attributed to chance? Use
1% level of significance.

The Test Statistics for Two-Sample Means:

𝑿𝟏 − 𝑿𝟐
𝒁𝑪𝑶𝑴𝑷𝑼𝑻𝑬𝑫 = =
𝑽⬚ 𝑽⬚
𝟏
+𝒏𝟐
𝒏𝟏 𝟐

Given: Sample mean 1 score (𝑋1 )= 88 Population variance 1 score (V1 ) = 40

Sample mean 2 score (𝑋2 )= 85 Population variance 2 score (V2 ) = 35
Sample size 1 ( n1 ) = 150 Sample size 2 ( n2 ) = 150
Level of Significance = 1% (0.01)

Solution:
1. State the
a). Ho: “The difference between the mean scores is not significant” or (µ1 = µ2)
b). Ha: “The difference between the mean scores is significant” …or (µ1 ≠ µ2)
2. Determine if the test is One-Tailed or Two-Tailed = Two tailed.
3. Specify the Level of Significance (a) = (0.01) or (1%).
4. Determine the degree of freedom, df = for z test the degree of freedom is not applicable = (N-A).
5. Determine the TABULAR VALUE or CRITICAL VALUE (from the tabular value of Z) = +/-2.575
6. Determine the computed value (using the Test Statistics or Statistical Tool/Formula).
𝑿 𝟏 − 𝑿𝟐 𝟖𝟖 − 𝟖𝟓
𝒁𝑪𝑶𝑴𝑷𝑼𝑻𝑬𝑫 = = = 𝟒. 𝟐𝟒
𝑽⬚ 𝑽⬚ 𝟒𝟎 𝟑𝟓
𝟏
+ 𝟐
+ 𝟏𝟓𝟎
𝒏𝟏 𝒏𝟐 𝟏𝟓𝟎
7. Make a decision. Compare the computed value to the critical/tabular value.
a. If the computed value is LESS than the critical value, ACCEPT the Null Hypothesis.
b. If the computed value is GREATER than or EQUAL to the critical value, REJECT the Null Hypothesis.
Since the computed value is greater than the critical value, therefore REJECT Ho!!!

OR BY GRAPHICAL APPROACH
If the computed value in step 6 falls outside the colored area ACCEPT Ho!
If the computed value in step 6 falls within (inside) the colored area REJECT Ho!

Notes:

The AREA of ACCEPTANCE is the WHITE area below the Normal Curve.

The AREA of REJECTION is the COLORED area below the Normal Curve.

From the figure, the computed value is in the COLORED area or is in the AREA of REJECTION,
Therefore, REJECT the NULL Hypothesis (REJECT Ho!!)

8, Conclusion.

Ha: “The difference between the mean scores is significant” …or (µ1 ≠ µ2)

Hypothesis Testing Page 4