Scribd
Upload
21 views

Chapter 6

This document outlines methods for statistical inference about two populations, including hypothesis testing and confidence intervals. It discusses using a t-test to compare means of independent samples when population variances are unknown. Examples are provided to demonstrate hypothesis testing to compare employee training methods and estimating coffee consumption differences. It also discusses using a t-test for related samples to test differences in company ratings before and after a video treatment.

Uploaded by

KHIEM HUOL GIA
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
21 views

Chapter 6

This document outlines methods for statistical inference about two populations, including hypothesis testing and confidence intervals. It discusses using a t-test to compare means of independent samples when population variances are unknown. Examples are provided to demonstrate hypothesis testing to compare employee training methods and estimating coffee consumption differences. It also discusses using a t-test for related samples to test differences in company ratings before and after a video treatment.

Uploaded by

KHIEM HUOL GIA
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 17

Chapter 6

Statistical Inferences
about Two
Populations
University of Economics
Ho Chi Minh City

Dang Van Thac 1/17


Outline

• Hypothesis Testing and Confidence Intervals about


Two Populations Means
𝟐
(Independent 𝐬𝐚𝐦𝐩𝐥𝐞𝐬, 𝝈 𝐔𝐧𝐤𝐧𝐨𝐰𝐧, 𝐭 𝐒𝐭𝐚𝐭𝐢𝐬𝐭𝐢𝐜)

• Statistical Inferences for Two Related Populations

Dang Van Thac 2/17


Hypothesis Testing and Confidence Intervals about Two Populations
Means (Independent samples, 𝝈𝟐 𝐔𝐧𝐤𝐧𝐨𝐰𝐧, 𝐭 𝐒𝐭𝐚𝐭𝐢𝐬𝐭𝐢𝐜)

• Hypothesis Testing:

𝑥1 − 𝑥2 − (𝜇1 − 𝜇2 )
𝑡=
𝑠12 𝑛1 − 1 + 𝑠22 𝑛2 − 1 1 1
+
𝑛1 + 𝑛2 − 2 𝑛1 𝑛2

df= 𝑛1 + 𝑛2 −2
The populations are normally distributed
The population variances are approximately equal
Dang Van Thac 3/17
Hypothesis Testing and Confidence Intervals about Two Populations
Means (Independent samples, 𝝈𝟐 𝐔𝐧𝐤𝐧𝐨𝐰𝐧, 𝐭 𝐒𝐭𝐚𝐭𝐢𝐬𝐭𝐢𝐜)

𝑥1 − 𝑥2 − (𝜇1 − 𝜇2 )
𝑡=
𝑠12 𝑠22
+
𝑛1 𝑛2

2 2
𝑠12 𝑠2
𝑛1 +𝑛
2
𝑑𝑓 =
2 2 2 2
𝑠1 𝑠2
𝑛1 𝑛2
+
𝑛1 − 1 𝑛2 − 1
The populations are normally distributed
The population variances are not equal
Dang Van Thac 4/17
Hypothesis Testing and Confidence Intervals about Two Populations
Means (Independent samples, 𝝈𝟐 𝐔𝐧𝐤𝐧𝐨𝐰𝐧, 𝐭 𝐒𝐭𝐚𝐭𝐢𝐬𝐭𝐢𝐜)

Example: Suppose managers of a company want to know


whether there is a difference between two methods of
employee training. The managers randomly select one group
of 15 newly hired employees to take the three-day seminar
(method A) and a second group of 12 new employees for
the two-day DVD method (method B). Using 𝛼 =.05, the
managers want to determine whether there is a significant
difference in the mean scores of the two groups. They
assume that the scores for this test are normally distributed
and that the population variances are approximately equal.
Dang Van Thac 5/17
Hypothesis Testing and Confidence Intervals about Two Populations
Means (Independent samples, 𝝈𝟐 𝐔𝐧𝐤𝐧𝐨𝐰𝐧, 𝐭 𝐒𝐭𝐚𝐭𝐢𝐬𝐭𝐢𝐜)

Step 1: 𝐻0 : 𝜇1 − 𝜇2 = 0
𝐻𝑎 : 𝜇1 − 𝜇2 ≠ 0

Step 2: The statistical test to be used is t test

Dang Van Thac 6/17


Hypothesis Testing and Confidence Intervals about Two Populations
Means (Independent samples, 𝝈𝟐 𝐔𝐧𝐤𝐧𝐨𝐰𝐧, 𝐭 𝐒𝐭𝐚𝐭𝐢𝐬𝐭𝐢𝐜)
Step 3: The value of alpha is .05.
Step 4: The test is two tailed test; df=15+12-2=25; 𝛼 = .05=>check the
table: 𝑡0.025,25 = ±2.060; the decision is to reject the null hypothesis if
the observed t value is greater than 2.060 or less than -2.060.

Dang Van Thac 7/17


Hypothesis Testing and Confidence Intervals about Two Populations
Means (Independent samples, 𝝈𝟐 𝐔𝐧𝐤𝐧𝐨𝐰𝐧, 𝐭 𝐒𝐭𝐚𝐭𝐢𝐬𝐭𝐢𝐜)
Step 5: Calculate the samples statistics:

47.73−56.5 −(0)
Step 6: 𝑡 =
19.495 15−1 +18.273 12−1 1 1
25
+
15 12
= −5.20
Step 7: Because -5.20 <-2.06 => reject 𝐻0

Dang Van Thac 8/17


Hypothesis Testing and Confidence Intervals about Two Populations
Means (Independent samples, 𝝈𝟐 𝐔𝐧𝐤𝐧𝐨𝐰𝐧, 𝐭 𝐒𝐭𝐚𝐭𝐢𝐬𝐭𝐢𝐜)

• Confidence Intervals:

𝑠12 𝑛1 − 1 + 𝑠22 𝑛2 − 1 1 1
𝑥1 − 𝑥2 −𝑡 + ≤ 𝜇1 − 𝜇2
𝑛1 + 𝑛2 − 2 𝑛1 𝑛2

𝑠12 𝑛1 − 1 + 𝑠22 𝑛2 − 1 1 1
≤ 𝑥1 − 𝑥2 +𝑡 +
𝑛1 + 𝑛2 − 2 𝑛1 𝑛2

df= 𝑛1 + 𝑛2 −2

Dang Van Thac 9/17


Hypothesis Testing and Confidence Intervals about Two Populations
Means (Independent samples, 𝝈𝟐 𝐔𝐧𝐤𝐧𝐨𝐰𝐧, 𝐭 𝐒𝐭𝐚𝐭𝐢𝐬𝐭𝐢𝐜)

Example: A
coffee manufacturer is interested in estimating the difference in
the average daily coffee consumption of regular-coffee drinkers and
decaffeinated-coffee drinkers. Its researcher randomly selects 13
regular-coffee drinkers and asks how many cups of coffee per day they
drink. He randomly locates 15 decaffeinated-coffee drinkers and asks
how many cups of coffee per day they drink. The average for the
regular-coffee drinkers is 4.35 cups, with a standard deviation of 1.20
cups. The average for the decaffeinated-coffee drinkers is 6.84 cups, with
a standard deviation of 1.42 cups. The researcher assumes, for each
population, that the daily consumption is normally distributed, and he
constructs a 95% confidence interval to estimate the difference in the
averages of the two populations.
Dang Van Thac 10/17
Hypothesis Testing and Confidence Intervals about Two Populations
Means (Independent samples, 𝝈𝟐 𝐔𝐧𝐤𝐧𝐨𝐰𝐧, 𝐭 𝐒𝐭𝐚𝐭𝐢𝐬𝐭𝐢𝐜)

95% confidence interval =>check t table: 𝑡.025,26 = 2.056


The confidence interval is:
1.202 12 +1.422 14 1 1
4.35 − 6.84 ± 2.056 +
13+15−2 13 15
-2.49 ±1.03 => −3.52 ≤ 𝜇1 − 𝜇2 ≤ −1.46
=> The researcher is 95% confident that the difference in
population average daily consumption of cups of coffee
between regular- and decaffeinated-coffee drinkers is between
1.46 cups and 3.52 cups.
Dang Van Thac 11/17
Statistical Inferences for Two Related Populations
• Hypothesis Testing:

𝑑−𝐷
𝑡= , df = n − 1
𝑠𝑑 / 𝑛

n= number of pairs
D = mean population difference
𝑠𝑑 = standard deviation of sample difference
𝑑 = mean sample difference

Dang Van Thac 12/17


Statistical Inferences for Two Related Populations
• Example: Consumers are asked to rate a company both before
and after viewing a video on the company twice a day for a week.
Use an alpha of .05 to test to determine whether there is a
significant increase in the ratings of the company after the one-
week video treatment. Assume that differences in ratings are
normally distributed in the population.

Dang Van Thac 13/17


Statistical Inferences for Two Related Populations
Step 1: 𝐻0 : 𝐷 = 0
𝐻𝑎 : 𝐷 < 0
Step 2: The statistical test is t test for dependent
samples
Step 3: The value of alpha is .05
Step 4: The test is one tailed test. Check the t table:
the critical value 𝑡.05,6 = −1.943. The decision rule is
to reject the null hypothesis if the observed t value
is less than -1.943.
Step 5: Calculate the sample statistics

Dang Van Thac 14/17


Statistical Inferences for Two Related Populations
Step 6: the observed t value:

−5.857 − 0
𝑡= = −2.54
6.0945/ 7

Step 7: because -2.54<-1.943


=> Reject the null hypothesis

Dang Van Thac 15/17


Statistical Inferences for Two Related Populations

• Confidence Intervals:

𝑠𝑑 𝑠𝑑
𝑑−𝑡 ≤𝐷 ≤𝑑+𝑡 , df=n-1
𝑛 𝑛

Dang Van Thac 16/17


Statistical Inferences for Two Related Populations
Example: Construct a 95% confidence interval to estimate D from the
following sample information. Assume the differences are normally
distributed in the population.
95% confidence interval => 𝑡.05,6 = 1.943
𝑑 = 5.857
𝑠𝑑 = 6.0945
n=7
6.0945 6.0945
5.857 − 1.943 ≤ 𝐷 ≤ 5.857 + 1.943
7 7

5.857 − 4.475 ≤ 𝐷 ≤ 5.857 + 4.475

1.382 ≤ 𝐷 ≤ 10.332
Dang Van Thac 17/17

You might also like