Introduction to Sampling Theory

Lecture 12
Stratified Random Sampling

Shalabh
Department of Mathematics and Statistics
Indian Institute of Technology Kanpur

Slides can be downloaded from

http://home.iitk.ac.in/~shalab/sp
1
Procedure of Selection of a Random Sample:

Population (N units)

Stratum 1 Stratum 2 Stratum k

k
N1 units N2 units … … … Nk units N   Ni
i 1

𝑌 𝑌 𝑌

Sample 1 Sample 2 Sample k k

… … … N  Ni
n1 units n2 units nk units i 1

𝑦 𝑦 𝑦

2
Stratified Random Sampling: Example
• Find the average height of the students in a school of class 1 to 12.

• Height varies. Students in class 1 are around 6 years old and

students in class 10 are around 16 years old.

• Divide the students into different subpopulations or strata such as

 Students of class 1, 2 and 3: Stratum 1
 Students of class 4, 5 and 6: Stratum 2
 Students of class 7, 8 and 9: Stratum 3
 Students of class 10, 11 and 12: Stratum 4
3
Stratified Random Sampling: Example
• Draw the samples by SRS from each of the strata 1, 2, 3 and 4.

• All the drawn samples combined together will constitute the final
stratified sample.

4
Advantages of Stratified Sampling :
1.Data of known precision may be required for certain parts of the
population. This can be accomplished with a more careful
investigation to few strata.

Example: In order to know the direct impact of hike in petrol

prices, the population can be divided into strata like lower
income group, middle income group and higher income group.
Obviously, the higher income group is more affected than the
lower income group. So more careful investigation can be made
in the higher income group strata.

5
Advantages of Stratified Sampling :
2. Sampling problems may differ in different parts of the
population.

Example: To study the consumption pattern of households, the

people living in houses, hotels, hospitals, prison etc. are to be
treated differently.

6
Advantages of Stratified Sampling :
3. Administrative convenience can be exercised in stratified
sampling.

Example: In taking a sample of villages from a big state, it is more

administratively convenient to consider the districts as strata so
that the administrative setup at district level may be used for this
purpose. Such administrative convenience and the convenience in
organization of field work are important aspects in national level
surveys.

7
Advantages of Stratified Sampling :
4. Full cross‐section of population can be obtained through
stratified sampling. It may be possible in SRS that some large part
of the population may remain unrepresented. Stratified sampling
enables one to draw a sample representing different segments of
the population to any desired extent. The desired degree of
representation of some specified parts of population is also
possible.

5. Substantial gain in the efficiency is achieved if the strata are

formed intelligently.

8
Advantages of Stratified Sampling :
6. In case of skewed population, use of stratification is of
importance since larger weight may have to be given for the few
extremely large units which in turn reduces the sampling
variability.

7. When estimates are required not only for the population but also
for the subpopulations, then stratified sampling is helpful.

8. When the sampling frame for subpopulations is more easily

available than the sampling frame for whole population, then the
stratified sampling is helpful. 9
Advantages of Stratified Sampling :

9. If population is large, then it is convenient to sample separately

from the strata rather than the entire population.

10. The population mean or population total can be estimated with

higher precision by suitably providing the weights to the

estimates obtained from each stratum.

10
Stratified Random Sampling:
We use the following symbols and notations:
N : Population size
k : Number of strata
Ni : Number of sampling units in ith strata
k
N   N i Total population size
i 1

ni : Numbers of sampling units to be drawn from ith stratum.

k
n   ni : Total sample size
i 1

11
Stratified Random Sampling:
Let
Y : characteristic under study,
yij : value of jth unit in ith stratum j = 1,2,…,ni, i = 1,2,...,k,

1 Ni
Yi 
Ni
y
j 1
ij : population mean of i th
stratum, j  1, 2,, ni , i  1, 2,..., k ,

1 ni
yi 
ni
 ij
y
j 1
: sample mean of units from i th
stratum

1 k k
Ni
Y 
N

i 1
N iYi   wiYi : population mean where wi  .
i 1 N

12
Stratified Random Sampling:
There are k independent samples drawn through SRS from each of
the stratum.

There will be k estimators of parameter but the ultimate goal is to

have a single estimator.

How to combine the different sample information together into one

estimator which is good enough to provide the information about
the parameter.

13
Estimation of Population Mean:
In case of stratified sampling, the population mean is defined as
the weighted arithmetic mean of stratum means where the
weights are provided in terms of strata sizes.
1 k
Y   NiYi ,
N i 1

Find the sample mean of the units drawn from each startum.

Find their weighted mean, called as stratified mean.

Use stratified mean as to estimate the population mean as

1 k
yst   Ni yi .
N i 1 14
Unbiased Estimator of Population Mean:
Since the sample in each stratum is drawn by SRS, so

E ( yi )  Yi ,

1 k
yst   Ni yi .
N i 1
1 k
E ( yst )   Ni E ( yi )
N i 1
1 k
  Ni Y i
N i 1
 Y.

15
Biased Estimator of Population Mean:
Since the sample in each stratum is drawn by SRS, so

E ( yi )  Yi ,

1 k
y   ni yi
n i 1

1 k
E ( y )   ni E ( yi )
n i 1
1 k
  ni Yi
n i 1
1 k
  ni Y i
n i 1
Y
16
Variance of Stratum Mean:
k k ni
Var ( yst )   wi2 Var ( yi )    w w Cov( y , y )
i j i j
i 1 i (  j ) 1 j 1

Since all the samples have been drawn independently from each
of the strata by SRSWOR, so
Cov( yi , y j )  0, i  j
Ni  ni 2
Var ( yi )  Si
Ni ni
where
1 Ni
Si2  
Ni  1 j 1
(Yij  Y i .
) 2

17
Variance of Stratum Mean:
k k ni
Var ( yst )   wi2 Var ( yi )    w w Cov( y , y )
i j i j
i 1 i (  j ) 1 j 1

Thus
k
Ni  ni 2
Var ( yst )   w 2
i Si
i 1 Ni ni
k
 n  S 2
  wi2 1  i  i .
i 1  Ni  ni

18
How to Construct Strata:
k
 n  S 2
Var ( yst )   wi2 1  i  i .
i 1  Ni  ni

Variance is small when 𝑺𝟐𝒊 is small.

This suggests how to construct the strata.

If 𝑺𝟐𝒊 is small for all i = 1,2,...,k, then variance will also be small.

That is why the strata are constructed such that they are within

homogeneous, i.e., 𝑺𝟐𝒊 is small and among heterogeneous.