Dr.

Gurjeet Singh Walia

Assistant Professor of Statistics
Department of Mathematics, Statistics & Physics
PAU Ludhiana
 Chapter-3

Small Sample Tests (n<30)

In this chapter, we will discuss following tests:
1. t-test for Significance of Single Mean

2. t-test for significance of Difference of Means

3. Paired t-test

4. F-test for Equality of Variances

t-Test for Significance of Single Mean
 Null Hypothesis
H 0 :   0

 Alternative Hypothesis
H1 :   0 or H1 :   0 or H1 :    0

 Test Statistic
x  0
t  tn 1
s n
1
 x  x
2
where s 
n 1
 Table value
tn 1, or tn 1, 2
 Conclusion
If tCal > Table value then H 0 may be rejected

 Confidence Interval


x  tn 1, 2 s n 
Two-tail table value
Ex5: A machinist is making engine parts with axle diameters of
0.700 inch. A random sample of 10 parts shows a mean diameter
of 0.742 inch with a standard deviation of 0.040 inch. Test
whether the work is meeting the specifications.
 Null Hypothesis
H 0 :   0.700
 Alternative Hypothesis
H1 :   0.700
 Test Statistic
x  0 0.742  0.700
t   3.15  t9
s n 0.0422 10
nS 2
where s  0.0422
n 1
 Table value
t9,0.05 2  2.26
 Conclusion
Since tCal > Table value So H 0 may be rejected
t-Test for Significance of Difference of Means
 Null Hypothesis
H 0 : 1   2

 Alternative Hypothesis
H1 : 1  2 or H1 : 1  2 or H1 : 1   2

 Test Statistic
x1  x2
t  tn1  n2  2
1 1
s   
2
p
 n1 n2  s 2

 n1  1 s12   n2  1 s22
where p
n1  n2  2
 Table value
tn1  n2  2, or tn1  n2  2, 2
 Conclusion
If tCal > Table value then H 0 may be rejected

 Confidence Interval
 1 
2 1
x1  x2  tn1  n2  2, 2  s p    
  n1 n2  
 
Two-tail table value
Ex6: The heights of 6 randomly chosen red roses are 63, 65, 68,
69, 71 and 72. the heights of 10 randomly chosen yellow roses are
61, 62, 65, 66, 69, 69, 70, 71, 72, 73. Test whether yellow roses are
on the average taller than red roses at 5% level of significance. Do
you think any of the assumption needed for testing have been
violated?

 Null Hypothesis H 0 :  R  Y
 Alternative Hypothesis H1 :  R  Y
 Test Statistic
x1  68 x2  67.8
s  12
2
1
s22  17.07

s 2

 n1  1 s12   n2  1 s22

5  12  9 17.07
 15.25
p
n1  n2  2 6  10  2
 x1  x2 68  67.8
t   0.099
1 1 1 1 
s   
2
15.25   
p
 n1 n2   6 10 

 Table value t14,0.05  1.76

 Conclusion
Since tCal < Table value so H 0 may not be rejected
Paired t-test
 Null Hypothesis
H 0 : 1   2

 Alternative Hypothesis
H1 : 1  2 or H1 : 1  2 or H1 : 1   2
 Test Statistic
d
t  tn 1
2
s n
d
1
1
  d d 
2
where d  x1  x2 ; d  d ; s 
2
d
n n 1
 Table value
tn 1, or tn 1, 2
 Conclusion
If tCal > Table value then H 0 may be rejected

 Confidence Interval

d  tn 1, 2  sd2 n 
Two-tail table value
Ex7: A certain stimulus administered to each of the 12 patients
resulted in the following increase in blood pressure: 5, 2, 8, -1, 3,
0, -2, 1, 5, 0, 4, 6. Can it be concluded that the stimulus will, in
general, be accompanied by an increase in blood pressure?

 Null Hypothesis H 0 :  Before   After

 Alternative Hypothesis H1 :  Before   After

 Test Statistic
d: 5, 2, 8, -1, 3, 0, -2, 1, 5, 0, 4, 6
1 1
d   d  2.58   d  d   9.5382
2
s 
2
d
n n 1
 d 2.58
t   2.89  t11
2
s n
d
9.5382 12
 Table value
t11,0.05  1.80
 Conclusion
Since tCal > Table value so H 0 may be rejected
F-Test for Equality of Variance
 Null Hypothesis
H 0 :  12   22

 Alternative Hypothesis
H1 :  12   22

 Test Statistic
s12
F  2  Fn1 1,n2 1
s2
provided s12  s22
 Table value
Fn1 1,n2 1, or Fn1 1,n2 1, 2
 Conclusion
if FCal  Fn 1,n 1, , reject H 0
1 2
Ex6: The heights of 6 randomly chosen red roses are 63, 65, 68,
69, 71 and 72. the heights of 10 randomly chosen yellow roses are
61, 62, 65, 66, 69, 69, 70, 71, 72, 73. Test whether yellow roses are
on the average taller than red roses at 5% level of significance. Do
you think any of the assumption needed for testing have been
violated?

 Null Hypothesis H 0 :  12   22
 Alternative Hypothesis H1 :  12   22
 Test Statistic
s12  12 s22  17.07
Since s22 is greater than s12 so
s22 17.07
F 2   1.42  F9,5
s1 12
 Table value
F9,5,0.05  4.77
 Conclusion
Since FCal < Table value, So H 0 may not be rejected
Practice Test
Ex 1. The mean weekly sales of soap bars in departmental
stores was 146.3 bars per store. After an advertising
campaign, the mean weekly sales in 22 stores for a typical
week increased to 153.7 with a standard deviation of 17.2.
Was the advertising campaign successful?
Ex 2. In a survey of buying habits, 400 women shoppers are
chosen at random in super market A. Their average weekly
food expenditure is Rs. 250 with a standard deviation of Rs.
40. For another 400 women shoppers chosen at random in
super market B, the average weekly food expenditure is Rs.
220 with a standard deviation of Rs. 55. Test at 1% level of
significance whether the average weekly food expenditure
of the two populations of shoppers are equal.
Ex 3. Five Soil samples are used to determine if there is a
difference between a Laboratory Chemical Analysis and an
X-Ray Fluorescence Analysis of the iron content. Each
sample was split into two sub-samples and the two types of
analysis were applied. Following coded data shows the iron
content analysis:
X-RaY 2.0 2.0 2.3 2.1 2.4
Chemical 2.2 1.9 2.5 2.3 2.4

Test at 1% level of significance whether the two methods of

analysis give the same result.
Ex 1. The mean weekly sales of soap bars in departmental
stores was 146.3 bars per store. After an advertising
campaign, the mean weekly sales in 22 stores for a typical
week increased to 153.7 with a standard deviation of 17.2.
Was the advertising campaign successful?
Sol: H 0 :   146.3
H1 :   146.3
x  0 153.7  146.3
t   1.97  t21
s n 17.60 22
t21,0.05  1.72

Since calculated value is more than table value, so Null

Hypothesis may be rejected.
Ex 2. In a survey of buying habits, 400 women shoppers are chosen at
random in super market A. Their average weekly food expenditure is
Rs. 250 with a standard deviation of Rs. 40. For another 400 women
shoppers chosen at random in super market B, the average weekly food
expenditure is Rs. 220 with a standard deviation of Rs. 55. Test at 1%
level of significance whether the average weekly food expenditure of
the two populations of shoppers are equal.
Sol: H :  
0 A B
H1 :  B   B
x A  xB 250  220
Z   8.82
 2
 2
402
55 2
A
 B

nA nB 400 400
Z 0.01  2.575
Since calculated value is more than table value, so Null Hypothesis may
be rejected
Ex 3. Five Soil samples are used to determine if there is a difference between a
Laboratory Chemical Analysis and an X-Ray Fluorescence Analysis of the iron
content. Each sample was split into two sub-samples and the two types of
analysis were applied. Following coded data shows the iron content analysis:
X-Ray 2.0 2.0 2.3 2.1 2.4
Chemical 2.2 1.9 2.5 2.3 2.4
Test at 1% level of significance whether the two methods of analysis give the
same result.
Sol: H :   H : 
0 X  Ray Chem. 1 X  Ray Chem

d: 0.2, -0.1, 0.2, 0.2, 0

d  0.01 sd2 
d
t  tn 1
sd2 n
Table Values