CHAPTER FOUR

Stratified Sampling
Outline
1 Basic concepts of stratification
2 Major advantages of stratification
3 Estimation of population mean and total
4 Allocating samples to strata
5 Relative precision of stratified random sampling and SRS
6 Relative gain in precision
7 Stratified sampling for proportion
8 Estimation of sample size
9 Design effect
4.1 Basic concepts of stratification
• An important objective in any estimation problem is to obtain an estimator of a population
parameter that can take care of the salient features of the population.
• If the population is homogeneous with respect to the characteristic under study, then the
method of simple random sampling will yield a homogeneous sample, and in turn, the
sample mean will serve as a good estimator of the population mean.
• Thus, if the population is homogeneous with respect to the characteristic under study, then
the sample drawn through simple random sampling is expected to provide a representative
sample.
• Moreover, the variance of the sample mean not only depends on the sample size and
sampling fraction but also on the population variance.
• To increase the precision of an estimator, we need to use a sampling scheme that can
reduce the heterogeneity in the population.
• If the population is heterogeneous with respect to the characteristic under study, then one
such sampling procedure is stratified sampling.
Simple Random Sampling :

Population of balls of size 10

1 2 3 4 5 6 7 8 9 10

Sample 1 7 4 9 1
Choose any sample

Sample 2 2 7 1 5
Simple Random Sampling:
• Population of 42 balls

• Sample 1 Is this representative?

• Sample 2 Is this representative?

Stratified Random Sampling :
Population of 42 balls

• Divide the balls into homogeneous groups.

• Consider the colour of ball as a variable for creating the homogeneous groups.
• For example, shades of blue, red, green etc.
Stratified Random Sampling :

Shades of red colour

Shades of blue colour

Shades of green colour

Shades of yellow colour

Stratified Random Sampling :
Population of 42 balls
Group 1 (Stratum 1)
All red shaded balls

Group 2 (Stratum 2)
All blue shaded balls

Group 3 (Stratum 3)
All green shaded balls

Group 4 (Stratum 4)
All yellow shaded balls
Stratified Random Sampling :
• Draw Sample from each group
Procedure of Selection of a Random Sample:
The basic idea behind stratified sampling is to
• divide the whole heterogeneous population into smaller groups or subpopulations such that
the sampling units are
− homogeneous with respect to the characteristic under study within the subpopulation
and
− heterogeneous with respect to the characteristic under study between/among the
subpopulations. Such subpopulations are termed as strata.
• Treat each subpopulation as a separate population and draw a sample by SRS from each
stratum.
[Note: ‘Stratum’ is singular, and ‘strata’ is plural].
Difference between stratified and cluster sampling schemes

• In stratified sampling, the strata are constructed such that they are
• within homogeneous and
• among heterogeneous.

• In cluster sampling, the clusters are constructed such that they are
• within heterogeneous and
• among homogeneous.

• [Note: We discuss the cluster sampling later.]

Notations:
• Divide the population of N units into L strata. Let the hth stratum has Nh, 1, 2,..., L number
of units.
• Strata are constructed such that they are non-overlapping and homogeneous with respect to
the characteristic under study
We use the following symbols and notations:
• N : Population size
• L : Number of strata
• Nh : Number of sampling units in hth strata 𝑁 = 𝐿ℎ=1 𝑁𝑖
• Draw a sample of size nh from hth (h=1, 2,...,L ) stratum using SRS (preferably WOR)
independently from each stratum.
• nh : Number of sampling units to be drawn from hth stratum.
• All the sampling units drawn from each stratum will constitute a stratified sample of size
𝑛 = 𝐿ℎ=1 𝑛𝑖
 Population (N units)

𝐿
Stratum 1 Stratum 2 Stratum L
𝑁= 𝑁𝑖
N1 units N2 units ……… NL units ℎ=1

Sample Sample Sample 𝐿

1 2 ……… L 𝑛= 𝑛𝑖
n1 units n2 units nL units ℎ=1
 Population (N units)

Stratum 1 Stratum 2 Stratum L 𝐿

N1 units N2 units NL units 𝑁= 𝑁𝑖
………
𝜇1 𝜇2 𝜇𝐿 ℎ=1

Sample1 Sample 2 Sample L 𝐿

n1 units n2 units ……… nL units 𝑛= 𝑛𝑖
𝑦1 𝑦2 𝑦𝐿 ℎ=1
Example: In order to find the average height of the students in a school of class 1 to class
12, the height varies a lot as the students in class 1 are of age around 6 years, and students in
class 10 are of age around 16 years. So, one can divide all the students into different
subpopulations or strata, such as
Students of classes 1, 2, and 3: Stratum 1
Students of classes 4, 5, and 6: Stratum 2
Students of classes 7, 8, and 9: Stratum 3
Students of classes 10, 11, and 12: Stratum 4
Now 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 for further analysis.
• In stratified random sampling, the simplest form of stratified sampling, we independently
take an SRS from each stratum, so that nh observations are randomly selected from the Nh
population units in stratum h. The total sample size is
𝐿

𝑛ℎ = 𝑛1 + 𝑛2 + ⋯ + 𝑛𝐿 = 𝑛
ℎ=1
• Notation for Stratification
‒ yhi is the value of the ith unit in stratum h. The stratum weight is defined as
𝑁ℎ
𝑊ℎ =
𝑁
‒ Sampling fraction in stratum h is defined as
𝑛ℎ
𝑓ℎ =
𝑁ℎ
‒ The population mean, total and variance for stratum h are
𝑁ℎ 𝑁ℎ 𝑁ℎ
1 2 1 2
𝜇ℎ = 𝑌ℎ𝑖 , 𝜏ℎ = 𝑌ℎ𝑖 = 𝑁ℎ 𝜇ℎ , 𝑎𝑛𝑑 𝑆ℎ = 𝑌ℎ𝑖 − 𝜇ℎ
𝑁ℎ 𝑁ℎ − 1
𝑖=1 𝑖=1 𝑖=1
4.2 Major Advantages of Stratification
1. Data of known precision may be required for certain parts of the population. This can be
accomplished with a more careful investigation of a few strata.
Example: To know the direct impact of the hike in petrol prices, the population can be
divided into strata, such as lower income group, middle-income group, and higher
income group. Obviously, the higher-income group is more affected than the lower-
income group. So, a more careful investigation can be conducted in the higher-income
group strata.
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, prisons, etc., are to be treated differently.
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 set up at the district
level may be used for this purpose. Such administrative convenience and the convenience
of organizing fieldwork are important aspects of national-level surveys.
4. Full cross-section of the 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 population
segments to any desired extent. The desired degree of representation of some specified
parts of the population is also possible.
5. Substantial gain in efficiency is achieved if the strata are formed intelligently.
6. In the case of a skewed population, the use of stratification is of importance since a 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 for the population and the subpopulations, then stratified
sampling is helpful.
8. When the sampling frame for subpopulations is more easily available than the sampling
frame for the whole population, then stratified sampling is helpful.
9. If the population is large, 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.
Example 4.1. An advertising firm, interested in determining how much to emphasize television
advertising in a certain county, decides to conduct a sample survey to estimate the average number of
hours each week that households within the county watch television. The county contains two towns,
A and B, and a rural area. Town A is built around a factory, and most households contain factory
workers with school-age children. Town B is an exclusive suburb of a city in a neighboring county and
contains older residents with few children at home. There are 155 households in town A, 62 in town B,
and 93 in the rural area. Discuss the merits of using stratified random sampling in this situation.
• Solution: The population of households falls into three natural groupings, two towns and a rural
area, according to geographic location. Thus, to use these divisions as three strata is quite natural
simply for administrative convenience in selecting the samples and carrying out the fieldwork. In
addition, each of the three groups of households should have similar behavioral patterns among
residents within the group. We expect to see relatively small variability in number of hours of
television viewing among households within a group, and this is precisely the situation in which
stratification produces a reduction in a bound on the error of estimation.
• The advertising firm may wish to produce estimates on average television viewing hours for each
town separately. Stratified random sampling allows for these estimates.
4.3 Estimation of Population Mean and Total
• The overall population mean (μ) and total (τ ) are

and

• For the population mean per unit, the estimate used in stratified sampling is 𝑦𝑠𝑡 (st stands
for stratified)

where 𝑦ℎ is the sample mean of stratum h

4.4 Allocating Samples to Strata
4.5 Relative Precision of Stratified Random Sampling and SRS
2.6 Relative Gain in Precision
4.7 Stratified Sampling for Proportion
4.8 Estimation of Sample Size
Estimation of Sample Size—Estimating Population Mean
4.9 Design Effect