Hypothesis Testing – Small Samples

• TEST OF SIGNIFICANCE FOR SMALL SAMPLES:

 When the size of the sample is less than 30, then the sample is called
small sample.
 The tests used in case of large samples are not applicable for small
samples because the assumptions on which they are based do not hold
good for small samples.
 In small samples, population standard deviation is not known and as such
it is estimated from the random sample drawn from the population.

• THE ‘t’ DISTRIBUTION OR STUDENT’S ‘t’ DISTRIBUTION:

 It is very important and useful test of significance for the small samples
 The 't test is mainly applied in testing the significance of the:
(i) mean of the sample,
(ii) difference between the means of two independent/dependent samples,
(iii) observed coefficient of correlation
• Here the population standard deviation is not known
 Degree of Freedom
 For a fixed value of the mean the number of free choices is
called degree of freedom

 For example, in a distribution 2, 3, 5, 8, 7 the mean is 5. To

have a distribution containing 5 values with mean 5, 4 values
can be independently chosen but the 5th value has to be taken
in such a way that the mean is 5. So, the degree of freedom is 4

 We have defined degree of freedom for a fixed value of mean

but in certain situations like Chi-square test, degree of freedom
is calculated in different way.
  Properties of t-distribution
 t-distribution is unimodal distribution
 The probability distribution curve is symmetrical about the line t = 0.
 It is bell shaped curve just like a normal curve with its tail a little
higher above the abscissa than the normal curve. Its spread increases
as degree of freedom ‘k’ increases.
  Properties of t-distribution
 t-distribution has only one parameter k, the degree of freedom
 The constants of t distribution are as follows:
Mean = 0 for 𝑘 ≥ 2
𝑘
Variance 𝜎 2 = for 𝑘 ≥ 3
𝑘−2
 The area under t-distribution curve for 𝑡 < 𝑡0 , is determined by
the equation
𝑡0
𝑃 𝑡 < 𝑡0 = 𝑓 𝑡 𝑑𝑡
−∞
Students need not integrate actually for the area as the tables
of area under the curve for different values of t are available and
vice versa, (see table for student’s ‘t’ distribution).
 t-distribution tends to normal distribution as 𝑘 increases. For
practical purposes, t is taken as equivalent to the normal
distribution provided k > 30. t-distribution has tremendous utility in
testing of hypothesis about one population mean or about equality
of two population means when standard deviation of population is
not known.
  Applicatiopn of t-distribution

 To test the significance of the mean of a random sample

 To test the difference between mean of two independent

samples

 To test the difference between mean of two dependent

samples (Paired t-Test)

 To test the significance of an observed correlation coefficient

  To Test the Significance of the Mean of a Random
Sample

 Suppose a random sample 𝑥1 , 𝑥2 , … , 𝑥𝑛 of size 𝑛(𝑛 ≥ 2) has

been drawn from a normal population whose variance 𝜎 2 is
unknown. On the basis of this random sample the aim is to
test
 Ho: There is no significant difference between the sample
mean 𝑥 and the population mean 𝜇
i.e. 𝜇 = 𝜇0
 Test Statistics
𝑥−𝜇
𝑡= where 𝑥 is the mean of sample
𝑠/ 𝑛
1
And 𝑠2 = 𝑥−𝑥 2
with degree of freedom 𝑛 − 1
𝑛−1
 The table giving the value of t required for significance at
various levels of probability and for different degree area
called t-tables which are given in statistical tables by Fishers
and Yates.
 The t-distribution has a different values for each degree of
freedom and when the degrees of freedom are infinitely large,
the t-distribution is equivalent to normal distribution and the
probabilities shown in the normal distribution tables are
applicable
 The computed value is compared with the tabulated value at
5% or 1% levels of significance and at (n − 1) degree of
freedom and accordingly the null hypothesis is accepted or
rejected.
 Example 1

A random sample of size 20 from a normal

population has mean 42 and standard deviation
of 5. Test the hypothesis that the population
mean is 45. Use 5% level of significance.
 Example Solution:
Here n = 20, 𝑥 = 42
𝜇 = 45, 𝑠 = 5

Let us assume null hypothesis that There is no significant difference

between the sample mean and population mean
H0: μ = 45
a = 0.05
H1: μ ≠ 45 (Two tailed test) t Value : 𝟐. 𝟔𝟖𝟑
𝑥−𝜇 42−45
𝑡= = = −2.683
𝑠/ 𝑛 5/ 20

As tabulated value of t at 5% level for 19 degree of freedom is 𝑡0.05 =

2.09. As the calculated value of 𝑡 = 2.683 > 𝑡0.05 for 19 degree of
freedom Ho is rejected
Conclusion:
Decision: Reject Ho at
There is significant difference
a = 0.05(At 5%)
between the sample mean and
population mean
 Example 2

The lifetime of electric bulbs for a random

sample of 10 from a large consignment gave the
following data:
Item 1 2 3 4 5 6 7 8 9 10
Life in 4.2 4.6 3.9 4.1 5.2 3.8 3.9 4.3 4.4 5.6
‘000
hours

Can we accept the hypothesis that the average

lifetime of bulb is 4000 hours?
 Example Solution:
Here n = 10, 𝜇 = 4000
Let us assume null hypothesis that There is no significant difference
between the sample mean and population mean
H0: μ = 4000 hrs
H1: μ ≠ 4000 hrs (Two tailed test)
Applying t- test

𝑥 44
Here 𝑥 = = = 4.4
𝑛 10
𝑥 4.2 4.6 3.9 4.1 5.2 3.8 3.9 4.3 4.4 5.6
𝑥−𝑥 - 0.2 0.2 -0.5 -0.3 0.8 -0.6 -0.5 -0.1 0 1.2
2
𝑥−𝑥 0.04 0.04 0.25 0.09 0.64 0.36 0.25 0.01 0 1.44

𝑥−𝑥 2 3.12
𝑠= = = 0.589
𝑛−1 9
 𝑥−𝜇 4.4−4
𝑡= = = 2.123
𝑠/ 𝑛 0.589/ 10

As tabulated value of t at 5% level for 9 degree of freedom is

𝑡0.05 = 2.26. As the calculated value of 𝑡 = 2.123 < 𝑡0.05 for 9 degree
of freedom Ho is Accepted
a = 0.05, t Value :
𝐭 𝟎.𝟎𝟓 = 𝟐. 𝟐𝟔

Conclusion:
Decision: Accept Ho at
a = 0.05(At 5%) The average life time of bulbs
could be 4000 hrs
 Example 3
An automobile tyre manufacturer claims that the
average life of a particular grade of tyre is more
than 20,000 km when used under normal
conditions. A random sample of 16 tyres was
tested and a mean and standard deviation of
22,000 km and 5,000 km, respectively were
computed. Assuming the life of the tyres in km
to be approximated normally distributed, decide
whether the manufacturer's claim is valid
 Example 4
The nine items of a sample had the following
values:
45, 47, 50, 52, 48, 47, 49, 53, 51
Does the mean of nine items differ significantly
from the assumed population mean of 47.5?