You are on page 1of 15

Confidence Interval estimate for

1
-
2

Parameters/Estimates (Independent
Samples)
Parameter:
Estimator:
Estimated standard error:

N
1
= 100, Sample Mean = 50, s
1
= 6
N
2
= 150, sample mean = 65, s
2
= 8
Determine the 90% confidence interval for the
difference between population mean.
2 1
2 1 Y Y
2
2
2
1
2
1
n
S
n
S
+
Problem 1
Two cities are separated by a river. The chamber of
commerce in city A claims that the average family income
of that city is Rs.500/- more than that in city B. The
chamber of commerce in city B disputes this, and a
statistician is hired to settle the argument. He attacks the
problem by estimating the true difference between the
various family income in the two cities. One random
sample is drawn from each city, and the following results
are obtained :
From City A 100 families are selected and the average
family income found to be Rs. 1500 with variance 2260.
From city B 120 families are selected with average income
Rs. 1400 and variance 2100. Obtain a 99% confidence
interval estimate for the difference in mean.

Small-Sample Test for
1

2

Normal Populations
Case 1: Common Variances (o
1
2
= o
2
2
= o
2
)
Null Hypothesis:
Alternative Hypotheses:
1-Sided:
2-Sided:
Test Statistic:(where S
p
2
is a pooled estimate of o
2
)
0 2 1 0
: A = H
0 2 1
: A >
A
H
0 2 1
: A =
A
H
2
) 1 ( ) 1 (
1 1
) (
2 1
2
2 2
2
1 1
2
2 1
2
0 2 1
+
+
=
|
|
.
|

\
|
+
A
=
n n
S n S n
S
n n
S
y y
t
p
p
obs
Small-Sample Inference for
1

2

Normal Populations
Case 2: o
1
2
= o
2
2


Dont pool variances:

Use adjusted degrees of freedom (Satterthwaites
Approximation) :
2
2
2
1
2
1
2 1
n
S
n
S
S
y y
+ =

|
|
|
|
|
.
|

\
|

|
.
|

\
|
+

|
.
|

\
|
|
|
.
|

\
|
+
=
1 1
*
2
2
2
2
2
1
2
1
2
1
2
2
2
2
1
2
1
n
n
S
n
n
S
n
S
n
S
v
Problem 2
The makers of ink cartridges for color ink-jet
printers have developed a new system for storing
the ink. They think the new system will result in a
longer lasting product. In order to determine
whether this is the case, a test was developed in
which a sample of 35 of the new cartridges was
selected. They were put in a printer, and the test
pages were run until the cartridge was empty.
The same thing was done for a sample of 32
original cartridges. The following data were
observed.
New cartridge
mean 288 pages, standard deviation = 16.3 pages
Existing cartridge
Mean 279 pages, standard deviation = 15.91 pages
Based on the sample data and a significance level
equal to 0.1, determine if the new system will
result in a longer lasting product.
Problem
A reading test is given to an elementary school
class that consists of 12 south Indian children
and 10 north Indian children. The results of
the test are
North Indian : Mean 74, standard deviation 8
South Indian : Mean 70, standard deviation 10
Is the difference between the means of the two
groups significant at .05 level?
Behavioral research has developed an index designed to
measure managerial success. The index measure (in 100
point scale) is based on the managers level of time in the
organization and his/her level within the firm; the higher
the index, the more successful the manager. Suppose a
researcher wants to compare the average success index for
the two groups of managers at a large manufacturing plant.
Manager in group 1 engage a high volume of interactions
with people outside the managers work unit. Managers in
group 2 rarely interact outside their work unit. Independent
random samples of 12 and 15 managers are selected from
the groups 1 and 2, respectively, and the success index of
each recorded.
The results are as follows
Group 1: 65 58 78 60 68 69 66 70 53 71
63 63.
Group 2: 62 53 36 34 56 50 42 57 46 68
48 42 52 53 43
Use the data in the table to estimate the mean
difference between the success indexes of
managers in two groups. Use a 95% confidence
interval.
Is the difference between the means of the two
groups significant at .05 level?



Test Concerning
D

Null Hypothesis: H
0
:
D
=0

Test Statistic:
n s
d
t
d
obs
=
Problem
HomeGrocer.com is an online grocery store in the
Seattle area that has more than 10000
customers. The following table reports May 1999
prices for a shopping list of eight items from
HomeGrocer.com and local supermarket.
At .05 level of significance, is there any evidence of
a difference in the average price for products
purchased from HomeGrocer.com and the
supermarket.
Find the p-value.
Products Home-Grocer Super-Markets
Tide Detergent 6.99 6.99
Cookies 3.29 3.49
Formula cleaner 2.59 2.69
Pampers Diapers 10.79 10.99
Coke Classic 3.99 3.59
Colgate Toothpaste 3.49 3.49
Tropicana Orange Juice 3.59 3.49
Cereal 4.29 3.99
Problem

Marketing strategies would like to predict consumer
response to new products and their accompanying
promotional schemes. Consequently, studies the
examine the differences between buyers and
nonbuyers of a product are of interest. One study
showed that both the mean threshold size (number of
persons) and the mean threshold income were
significantly larger for purchaser than nonpurchaser. A
similar study of utilized independent random sample of
size 20 and yielded the data on the age of the
householder primarily responsible for buying
toothpaste.
Purchaser : 23 34 35 44 46 52 28 48 28
34 33 52 41 32 34 49 50 45 29 59
Nonpurchaser : 28 22 33 44 55 31 45 54
60 63 52 53 58 52 66 35 25 48 59
61
Do data present sufficient evidence to
conclude that there is a difference in the
mean age of purchasers and nonpurchasers?
Use = .10
Find the observed significance level of the
test.

You might also like