Professional Documents
Culture Documents
Theory
SAMPLING THEORY
6.1 SOME IMPORTANT TERMS
ASSOCIATED WITH SAMPLING
6.1.1 Population and Sample
population or Universe. Population
in statistics means the whole of the information which
comes under the purview of statistical
investigation It is the totality of all the observations of a
statistical experiment or enquiry. In other
words, an aggregate of objects; animate or inanimate
under study is the population. It is also known as the universe. For example, the population of the
heights of students in a school, or the population
of the sum of points obtained in throwingthree
dice.
Finite or Infinite Population. A population
may_befiniteor infinite according as the number
ofouservations or items in it are finite or infinite. The populationof weights of studentsof class
Xll in a government school is an example of a unite population. The population of pressure at
different points in the atmosphere is an example of an infinite population.
Sample. A part of the population selectedfor study is called a sample In other words,the
selecrion of a group of individuals or itemsfrom a population in such way that this group
represents the population, is called a sample. For example,a housewifetests a small quantity of
rice to see that it has been cooked or not. This small quantity of rice is a sample and represents the
entire quantity of rice cooked. A sample is a selected portion of the population. A sample drawn
from a population provides a valuable information about its parent population. It gives a fairly
accurate result and a reliable picture of the total observationsunder investigation. It is always used
to measure and estimate the corresponding characteristicsof its parent population. When the
sample drawn is perfectly representative, it is identical with its parent population almost in every
respect except that it is smaller than the population.
Size of a Sample. The number of individuals or items included in a finite sample is called
the size of the sample.
6.3 SAMPLING
It is the procedure or process of selecting a sample from a population* sarnpling can also
be defined as the process of drawing a sample from a population and of compiling a suit,ble
statistic from such a sample in order to estimate the parameter of the parent population and totest
the significance of the statistic computed from such sample.
Mean:
Variance: Var(t) = •
If the population size is infinitely large or sampling is done with replacement, then the total
nurnber of possible samples of the same size which may be drawn from the population cannot be
determined. In such a case, a large number of repeated random samples from the population Of
fixed size can be drawn and the values of statisticfor these samples may be computed. These
values of the statistic can be used to form a frequency distribution. This frequency distribution
of the statistic is known as the sampling distribution of the statistic. The main characteristic Of
the Sampling distribution of a statistic is that it approaches normal distribution even when the
population distribution is not normal provided the sample size Is sufficiently large (greater than
30). Another important feature of the sampling distribution of statistic is that the mean and the
standard deviation of the sampling distribution of sample mean bear a definite relation to the
corresponding parameters, i.e., mean and standard deviation of parent populauon. These
charactensucs of the sampling distribution help us:
Estimation Theo
Sam Iin and
6.7
(i) To estimate the unknown
population parameter from the known statistic.
(ii) To set the confidence
limits of the parameter
expected to lie. within which the parameter values are
(iii) To test a hypothesis and to
draw a statistical inference from it.
6.9 SAMPLING DISTRIBUTION OF SAMPLE MEAN
1. If X1,
Theorem X3,.. . are n random samples
drawn from a finite population of size
N with mean and variance 02, and R .is
the mean of samples, then.
(a) Var (
N -n 02
) if the-samplingis without replacement
n
2
(b) var(R) if the sampling with replacement or the population
is infinite, i.e., or if N -9 00
6.10 STANDARD ERROR OF A STATISTIC
The statistical measure of standard deviation may be computedboth from the observations
of aæ population and also from the observationsof a sample. Also, we know that the standard
deviation is a measure of the average amount of the variabilityof all the observationsof variable
from their mean. When the average amount ofthe variability of the observationsof a population
is computed, it is called the standard deviation. But when the average amount of the variability
of the observations of a sampling distribution of Su statistic is computed,it is known as Standard
Error.• Thus the standard deviation computed from the observations of a sampling
distribution of a statistic is called the standard error of the statistic%In other words,the
standard deviation used to measure the variability of the values of a statistiCJromsample to sample
is called the standard error of the statistic. Thus,the standard deviation and standard error have
thesame meaning and same connection but are used in differentcases and differentcircumstances.
Both of them are used to measure the variability of observations.
Standard error is used to measure the variability of the values of a statistic computed
from the samples of the same size drawn from the population, whereas standard deviation is
used to measure the variability of the observationsof the populationitself.
fie following two standard errors are frequently used in statistics.
1. Standard Error of SampleMean. It is the standarddeviationof the sampling
distribution of sample means. It is denoted by and is given by where is the
standard deviation of population and n is the sample size.
computed from the proportions of all possible samples
2. Standard Error of Proportion. It is given by
denoted by s , and is
Ofthe same size drawn from a population. It is
, if P is known,
n
where P = population proportion, n = sample size.
of the sampling distribution of a statistic 't' is
In other words, the standard deviation by S.E. (t)
known as standard Error of t and is denoted
— •
S.E. (t) =
where n = size of the sample.
6.8 Common Proficiency Test: Quantitative Aptitude Statisti
of S' to be written as S.E. (X ) and is equal to ' when sampling is with replacement.
3. The term is termed as finite population correction (fpc). We note that fpc
tends to become closer and closer to unity as population size becomes larger and larger.
4. As a general rule, fpc may be taken to be equal to unity when sample size is less than
5% of population size, i.e., n < 0. 05N.
var(p) = E =
n n
6.12 BASIC STATISTICAL LAWS
Sample survey is the study of the
unknown population on the basis of a proper sample drawn
fromit. The four popular and well defined
statistic laws which indicate the utility of larger size of
the sample for the purpose of reducing samplingerrors are:
1. Law of Statistical Regularity 3. Principle of Optimization
2. Law of Inertia of Large Numbers 4. Principleof Validity
l. Law of Statistical Regularity
It states that a reasonably larger number of items selectedat random from a large group
of items, will on the average, represent the characteristics of the group. In the words of the
statisticianW. I. King. "The law of statistical regularity lays down that a moderatelylarge
numberof@temschosen at random from a large group, are almost sure (on the average) to
possessthe cithracter@sticsof the large group".
This law explains that if a reasonable large sample is selected at random without bias (i.e.,
probabilitysampling), it is almost certain that on an average, the sample so chosen, shall have the
samecharacteristics as those of the parent population from where the units constituting the sarnple
havebeen drawn, It is on the basis of this theory that the law of statistical theory tells us that a
undomselection is very likely to give a representativesample.
I Law of Inertia of Large Numbers
It states that "large groups or aggregate of data show high degree of stabilitybecause there
compensated by the extremes on the
a greater possibility that the extremes on one side are
ther side. "
to the law of statisticar regularity. It
The law of inertia of large number is a corollary
more stable and more reliable than small ones.
nphasizes the fact that large numbers are relatively
would move in only one direction. Thus, the greater
a large number, it is unlikely that the data or tendency to neutralise one another
e size Of the sample, the greater will be the compensation
result. For example, the birth rate, death rate etc. may
EdCOnsequentlymore stable would be the
a whole country, they will be found some what
ry from Place to place in India but in India as
lbleover a number of years.
6.10 Common Proficiency Toot: Aptitv49
ne simplest method of increasing the accuracy of a sample is to increase its size. Thelarge,
the see of the sample. the mote reliable is the result. The other things remaining Unchanged,
sanvling is inversely proportional to the root of the number of items in the sample.
The Law of Statistical Regularity and the Law of the Inertia of Large Numbershave
great importance in the theory of sampling as the sampling error is reduced to minimumif the,
laws are correctly applied. e
12 +3 2 +5 2 +7 2 +9 2 165
-25=8.
Variance: 02 — — -( 5)2 =
5
without
(i) The total number of samples of size n = 2 in simple random sampling
replacement (srwor) is:
2!
= 10 . These ten samples are given below:
Sam lin and EstimationTheo
6.11
Sample No. 2 3 4
Sample Values (x) • (l, 3) (l, 5) (l,
7) (1,9) (3,5) (5, 7) (5, 9) (7,9
Sample Mean (i)
5 4 5 6 7
6 8
= (i -51 2 . 9 4
0 4 9
Also, = 50,
Mean and Variance : 30.
(ii) Mean : 50 50
-4 The mean of the sampling
distribution of the sample mean is equal to the population
Var (E) 1
30 30
5C2 10
Hence the variance of the sampling
distribution of the sample mean is 3.
(iil) Comparing this result with part (ii), we
get:
Var (F)
(22)2
S.D. of population: =
4 - (25)2 - = 2.236.
Mean: = 1
16 16 16 16 16 16
627.5-252 = ES = 1.581
Case Il. When the sampling is without Replacement
When random samples of size 2 are drawn without replacement,ye have : n
Sample No. Sample Values (R) Sample No. Sample Valu (R)
1 22, 24 23 4 24, 26 25
2 22, 26 24 5 24, 28 26
3 22, 28 25 6 26, 28 27
1
Since all the samples are equally likely, the probability of each value is
Thus, we can write the sampling distribution of R as .
R 23 24 25 26 27 Total
1
Sample Mean: = E(R) [23 + 24 + 25 x 2 + 26 + 27] = 25.
To find S.E. (R), we first find E(R 2) :
3760
E(R 2) —1232 + 24 2 + 205 2 + 262 + 27] = = 626.67.
6
g Ex = —(2+3+6+8+
1
11) 30
N 5
02 = Ecx-R)2 1
54
2
54
S.E.(R) = = =2.3238. = 21
Case 2. Sampling without replacement: If we have to draw sanples
then N = sc, = 10. In this case the variance of the sampling distribution of(F)
will be given by
54 10-2 54 8
Var(R) = n IV-I
10-1 10 9