\Calculated value | 233 Sowe Reject Hy
Conclusion:
Iz] > zac, we reject the Null Hypothesis.
SMALL SAMPLES
TEST OF HYPOTHESIS ABOUT THE POPULATION MEAN
‘The test statistic is defined as
5
A * with n=1 degrees of freedom
vn
with n —1 degrees of freedom
Example: 26
Ten oil tins are taken at random from an automatic filling machine, The mean weight of the tins
15.8 kg and standard deviation of 0.5 kg. Does the sample mean differ significantly from the
intended weight of 16 kg?
Solution:
Given thatn = 10, ¥= 15.8, s=0.50, 1=16
Null Hypothesis :Hg: #=16
Alternative Hypothesis : Hy : 4 # 16 (two tailed test)
The test statistic is given by
with n—1 degrees of freedom
m—1
158-16 -0.2_ -02
os ~ OS ~ 01667 ~~
vi0-1 V9
lel = 12
The critical value for t for a two tailed test at 5% level of significance with 10 — 1 = 9 degrees
of freedom is 2.26.
Calculated value=1.2_ and —Tabulated value =2.26
24|Calculated value | < Tabulated value then accept Hy
|1.2|<2.26 — acept Hy
Conclusion:
Itel < t, we accept Ho. That is sample mean is not differ from the intended weight.
Example: 27
A random sample of 10 boys had the following I.Q’s: 70, 120, 110, 101, 88, 83, 95, 98, 107, and
100. Do these data support the assumption of a population mean 1.Q of 100? Find the reasonable
range in which most of the mean 1.Q values of samples of 10 boys lie.
Solution:
% 7 | 120 | 10 | 11 | ee | as | 95 | 98 | 107 | 100 | S'x=972
xe | -272 | 228 | 128 | ae | -o2 | -142 |-22] 08 | 9 | 28
(u-x? | 73004 | si9a¢ | 16204 | 14.44 | 24.64 | 20164 | 404 | 64 | 9604 | 724 | 2,01 %)
= 1833.6
Dx _ 972
oh = = 972
n 10
_ UGi—%)? _ 1833.6
n-1 10-1
S = V203.7 = 14.27
97.2, $=14.27, w= 100
st = 203.7
Hence n= 10,
Null Hypothesis Ho? #=100
Alternative Hypothesis : Hy : 1+ 100 (two tailed test)
‘The test statistic is given by
2
af with n—1 degrees of freedom
—0.62
25‘The critical value for ¢ for a two tailed test at 5% level of significance with 10 — 1 = 9 degrees
of freedom is 2.26.
Calculated value =0.62 and Tabulated value =2.26
[Calculated value | < Tabulated value then accept Hy
|0.62|<2.26 acept Hy
Conclusion:
Itel < £, we accept Ho. That is the data are consistent with the assumption of mean 1.Q of 100 in
the population
Confidence Interval :
The confidence interval for the small sample mean is given by
=97.2 £10.19
87 64 (Right tailed test)
‘The test statistic is given by
=A * withn—1 degrees of freedom
vn
66-64 2
lel =
The critical value for t for a right tailed test at 5% level of significance with 10 — 1 = 9 degrees
of freedom is 1.833.
Calculated value=2 and Tabulated value =1.833
[Calculated value | < Tabulated value then accept Hy
But |2|>1833 Reject Hy
Conclusion:
[tl > t, we reject Mo. That is the average height is greater than 64 inches,
TESTING OF HYPOTHESIS ABOUT THE DIFFERENCE BETWEEN TWO MEANS
(USING T TEST)
ic for the difference between two means for small samples is given by
The test stat
Where #=2= and y= 2
‘Example: 29
Samples of two types of electric light bulbs were tested for length of life and the following data
were obtained
[ Type! Type Il
[sample size ny
7sample mean 234 hrs 036 hrs
sample S.D 5; 36 hrs Ss; 40 hrs
Is the difference in the means sufficient to warrant that type Tis superior to type II regarding
length of life?
Solution:
Given that my =8, m
1234hrs, ¥7= 1036 hrs s;=36, s,=40
Null Hypothesis: Ho fy = Hz i.e., the two types I & type Il of electric bulbs are same.
Alternative Hypothesis : Hy + 1 > Hz (Right tailed test)
The test statistic is given by
2
=
ea
my Me
with (ny +n — 2) degrees of freedom
Te
(+n)
My” M2,
lel =
The critical value for ¢ for a right tailed test at 5% level of significance with 8 + 7-2 = 13
degrees of freedom is 1.77.
Calculated value=9.39 and —Tabulated value =1.77
[Calculated value | > Tabulated value then Reject Ha
But |9.39]>1.77 Reject Hy
Coneh
Itael > £, we reject Ho. That is the type I is superior than type Il
Example: 30
In a test given to two groups of students the marks obtained were as follows.
First Group 18 | 20 | 36 [ 50 | 49 | 36 | 34 | 49 | 41 |
SecondGroup | 29 | 28 | 26 | 35 | 30 | 44 | 46 |
Examine the significant difference between the means of marks secured by students of the above
‘two groups
Solution:
28x as | 20 | 36 | so | a9 | 36 | 3a | as | at
xo |as) az} a] | a) a) 3] a2} a
Gq =a | asa | 2g9 | a | a69 | aaa] a | 9 | tae | a6 | Ye, 9F = 1136
% 29 | 2 | 26 | a5 | 30 | 4a | a6 | 238 y= 238
xy | 5s | sl] sefa | 4 [wl 2
(ms | 25 | 36 | 6a | 1 | a6 | 100 | 144 | 386 Dow? = 386
x, _ 333
Bx _ 338 and
and
«9 =VI4L75 =
Hence m=9, m=7, —=37,
=
‘Null Hypothesis Ho! Hi = Me
i.e, there is no significant difference between the mean marks secured by the two groups
iternative Hypothesis : H : ft; + plz (Two tailed test)
‘The test statistic is given by
with (m + nz — 2) degrees of freedom
‘The critical value for ¢ for a two tailed test at 5% level of significance with 9+ 7 — 2
degrees of freedom is 1.76.
Calculated valu
57 and —‘Tabulated value =1.76
|Calculated value | < Tabulated value then Accept Hy
But |0.57|<1.76 Accept Ho
Conclusion:
29Itael <¢, we Accept Ho. That is there is no significant difference between the mean marks
secured by the two groups.
Example: 31
Two independent samples of 8 and 7 items respectively had the following values.
Sample! | 9 | 11 [ 13 [11 | 15 | 9 | 12 | 14
Sampleti | 10 | 12 [ 10 | 14 | 9 | 8 | 10
Is the difference between the means of samples significant?
Solution:
x 9 | a | 13 | a fas | 9 | a2 | a x=
m-# | -275|-0.75| 125 |-075| 325 |-275| 025 | 225
@-x? | 7562 | 0563 | 1.563 | 0563 | 1056 | 7563 | anes | 5.063 | )"x 0? = 335
v w | a|wli|«wtls |e |. Yo-n
wn-F 0.43 | 157 | -0.43 | 357 | -143 | -243
G-9% | oes | 2.465 | 0.185 | 12.74 | 2045 | 5.905 | 0.185 Lon
San
73
and = = 10.43
7
and
8, =V479 = and
Hence n,=8, m=7, H=1L75, H=1043 s,=, y=
Null Hypothesis Ho? Hy = Me
ie, there is no significant difference between the mean of two samples.
Alternative Hypothesis : Hy + p11 + pty (Two tailed test)
The test statistic is given by
-%,
with (n, + nz —2) degrees of freedom
30