Lecture - 13

t – distribution
  the probability density function of the t- distribution
is given by f(t) = .( )
-
properties of t-distribution:
(1) the t- distribution is the exact distribution and total area under it is unity.
(2) the t- distribution does not depend upon the population , varieance , but contains
only one parameter r called the degree of freedom , this is the cheief merit of t – distribution.
Population:
The population is the totality of the observation in which we are concerned. A population can either be finite
or infinite.
Size of population:
The number of observations in a population is said to be the size of population denoted by N. Sample:
The subset of population is called sample.
Sampling:
It is a statistically technique which is used to collect information and on the basic of this information. We
form inferences (results) about the characteristics of the population.
Examples:
(i)The number of cards in a deck.
(ii)The height of residence in a certain city.
(iii)The number of students in mathematics department.
(Iv)The population of all points on a line.
(v)The number of germs on the body of sick patient.
 Remark:
(i), (ii) and (iii) are examples of finite population while (iv) and (v) are examples of infinite population.

Sampling unit:
An individual member of the population is called sampling unit or simple unit.
A sampling unit from which information is required, may be a college student, and animal, or tree, a
business etc.
A set of ‘n’ sampling units selected from a given population is called a sample of size ‘n’ and process of
selecting a sample is called sampling.
Random sample:
It is defined as a subset of the statistical population in which each of the member of the subset has equal
probability when it is selected.
Parameter:
A numerical value such as mean, median and standard deviation calculated from the population is said to
be parameter of the population. Statistics:
A numerical value such as mean, median and standard deviation calculated from a sample is called
statistics.
Note:
 
The parameter has fixed value i.e. it is constant and it is denoted by a Greek letter ,for the population
mean and standard deviation of the population, while on the other hand the statistics varies from sample
to sample of the same population and denoted by , for sample mean and standard deviation of the
sample.
Level of 0.10 0.05 0.01 0.005 0.002
significance
,

Critical -1.28 -1.64 -2.33 -2.58 -2.88

valueof z Or Or Or Or Or
for one tail 1.28 1.64 2.33 2.58 2.88
test
Critical
Critical -1.64
-1.64 -1.96
-1.96 -2.58
-2.58 -2.81
-2.81 -3.08
-3.08
valueof
valueof zz and
and and
and and
and and
and and
and
for
for two
two tail
tail 1.64
1.64 1.96
1.96 2.58
2.58 2.81
2.81 3.08
3.08
test
test
 Hypothesis
  The Procedere which enable us to decide on basis os sample
informations whether to accept or reject a statistical hypothesis
is called testing of Hypothesis .
Hypothesis Testing procedure :
step (1) to formulate null and alternatives hypothesis . A hypothesis which is to be tested
for possible rejection under the assumption that it is true is called null hypothesis
denoted by , Hypothesis which we accept when Null Hypothesis is rejected
is called alternative Hypothesis denoted by .
Null Hypothesis Alternative Hypothesis

: =30 Vs : 30

: 30 Vs :

: 30 Vs : 30
Step (2) Level of significant :
 
The probability of Rejecting True Null Hypothesis is called level of significance
denoted by .
Common values of =15% ,10% ,1% etc
step (3) Test Statistics :
Statistics ( I .s a value obtained from the sample data ) used to test the Null Hypothesis
is called Test Statistics .
e ,g z = to test
Q: A random sample of n= 25 value,s gives x = 83 . Can this sample be regarded
as drawn from a normal population with mean = 80 , = 7 .
Solution : to solve the above problem we used the following steps
step (1) we formulate our Null Hypothesis Alternative Hypothesis as
: = 80
: 80
step (2) level of significant :
Here = 0.05
Step (3) Test Statistics :
 
To test in case of normal distribution and is known we use
z= (1)
step (4) Computation :
Give that
n= 25 , x = 83 , = 80 , = 7
put in eqs(1) we get
z= = 2.14.
step(5) Critical Region :

Since Alternatives Hypothesis is of the form

so we used two tail test
= 0.05
= = 0.025
= 1.96 ( by inverse Normal Table)
Step (6)
 
Since our calculated value of Z = 2.14 falls in rejection region , so we have sufficient
evidence against the Null Hypothesis , therefore we accept i.s 80
Q: Test the Hypothesis that the mean of a normal population with known variance
70 is 31 , If a sample of size 13 gave x=34. let the alternatives Hypothesis be
: 31 and let = 0.10
solution :
step (1) we formulate our Null Hypothesis Alternative Hypothesis as
: = 31
: 31
step (2) level of significant :
Here = 0.10
Step (3) Test Statistics :
To test in case of normal distribution and is known we use
z= (1)
step (4) Computation :
Give that
n= 13 , x = 34 , = 31 , =
put in eqs(1) we get
 z = = 1.29
 step(5) Critical Region :
Since Alternatives Hypothesis is of the form
so we used Right tail test
= 0.10

= 1.28 ( by inverse Normal Table )

Step (6)
Since our calculated value of Z = 1.29 falls in critical region , so we have sufficient
evidence against the Null Hypothesis , therefore we accept i.s 31 population
mean is greater than 31
Q: The marks obtained by students at a large number of colleges are known to be
 
normally Distributed with a mean of 25 . A random sample of 36 students showed an average number of
marks of 27 with a standard deviation of 5 .what conclusion
should be drawn ?
Solution : step (1) we formulate our Null Hypothesis Alternative Hypothesis as
: = 25
: 25
step (2) level of significant :
Here = 0.05
Step (3) Test Statistics :
To test in case of normal distribution and is known we use
z= (1)
step (4) Computation :
Give that
n= 36 , x = 27 , = 25 ,
put in eqs(1) we get
z= = 2.40
step(5) Critical Region :
 
Since Alternatives Hypothesis is of the form
so we used two tail test.
= = 0.025
= 1.96 = 1.96

Step (6)
Since our calculated value of Z = 2.40 falls in rejection region , so we have sufficient
evidence against the Null Hypothesis , therefore we accept i.s 25
population, mean is not equal to 25.