Sampling for Drug Use

Indicators Study

1
Sampling for Drug Use
Indicators Study: Objectives

• Describe the principles upon which

sampling is based.
• Identify and describe different sampling
methods.
• Select a sample of health facilities
from a list of such facilities using
at least two different methods.
• Compare the the results of the methods.
• Instruct others how to sample for
drug use studies.
Sampling to Study Drug Use 2
What is Sampling?

• Sampling is a
process by which
we study a small
part of a population
to make judgements
about the entire
population.

Sampling to Study Drug Use 3

Sampling involves selecting a number of
units from a defined population.

Sampling to Study Drug Use 4

Sampling Definitions

• Sampling Unit
- The thing which is sampled, for example, a person,
a clinical episode, or a health facility
• Study Population
- All the sampling units which could possible be
included in the sample
• Sampling Frame
- A list of all the available sampling units in the study
population

Sampling to Study Drug Use 5

A Representative Sample

A representative sample has all the

important characteristics of the
study population from which it is
drawn.

Sampling to Study Drug Use 6

Sampling Methods

• Two categories of sampling

methods:
- Non probability sampling
- Probability sampling

Sampling to Study Drug Use 7

 Non Probability Sampling
Methods

• Convenience Sampling
- study units available at
the time of data collection
are selected for the sample

• Quota Sampling
- different categories of
sample units are included
until a certain number has
been reached in each
category
Sampling to Study Drug Use 8
Probability Sampling Methods

• Simple Random Sampling

• Systematic Sampling
• Stratified Sampling
• Cluster Sampling
• Multistage Sampling

Sampling to Study Drug Use 9

Simple Random Sampling

• Used in situations where

the number of sampling
units is relatively small
• Process:
- Identify all possible units
available for sampling
- Decide on the size of the
sample
- Choose units by a lottery
method

Sampling to Study Drug Use 10

Systematic Sampling With
Equal Probability
• Numbered list of all possible units.
• # units ÷ desired sample size = sampling interval.
– For example, to select 20 health centers from a list of 46, the
sampling interval is 46/20 = 2.3
• Random # x sampling interval = random start.
– For example, if the random number is 0.183 calculate 0.183 × 2.3
= 0.421, which rounds upward to 1
• Round number up to choose sample unit.
• Add sampling interval to random start for subsequent units.
– For example,
0.421 + 2.3 = 2.721 or Facility 3
2.721 + 2.3 = 5.021 or Facility 6
5.021 + 2.3 = 7.321 or Facility 8 and so forth.
Sampling to Study Drug Use 11
Systematic Sampling With
Probability Proportional To Size
• List where the units are sorted in decreasing order
by some measure of size (like population or number
of visits)
• Calculate the cumulative total.
• Cumulative total ÷ sample size = sampling interval.
• Random # x sampling interval = random start.
• Choose first unit with cumulative total result.
• Add sampling interval to previous total for
subsequent units.
Sampling to Study Drug Use 12
Stratified Sampling

• Used when the sampling frame contains clearly

different categories (strata).
–For example:
• Urban and rural facilities
• Facilities with and without doctors
• Government and mission facilities
• Process:
- Organize the list of sampling units by stratum
- Select units within each stratum using a random
method (simple random sampling or systematic
sampling)
Sampling to Study Drug Use 13
Cluster Sampling

• Used when for logistic reasons it is easier to select

sample units in groups
• Process
- Select a cluster of sample units-
– Example: health center with multiple prescribers
• Include the entire cluster or select a sub- sample
– OR
- Select a random sample unit to start each cluster (a
house, a patient, etc.)
- Include neighboring sample units until a certain cluster
size is reached

Sampling to Study Drug Use 14

Multistage Sampling

• Randomly select primary sampling units at the first

stage:
– specific communities
– specific health facilities
• Within the primary sampling units, randomly select the
final sampling units at the second stage:
– drug use encounters
– patients
– households
• Sometimes in complex samples, additional stages are
needed
Sampling to Study Drug Use 15
Sample Size

• The optimal sample size is often a compromise

between what is statistically Desirable and
what is practically Feasible.

In general, a minimum
sample size is 30.

Sampling to Study Drug Use 16

Sample Size

Confidence Intervals
If the real figure is 50%

• Sample size • Range of Confidence

50 36 - 64%
100 40 - 60%
200 43 - 57 %
500 45 - 55 %
1000 47 - 53 %
Sampling to Study Drug Use 17
Conclusion

• Principles of sampling should be

understood by everyone involved in drug
use studies.
• Eumerators and supervisors should
understand that any facility, any
prescription, or any patient should have a
chance to be included.
• Make every effort to avoid bias in selecting
units for study.
Sampling to Study Drug Use 18
Activity One

Sample Selection
In this exercise, groups will use
the different sampling methods
on a real data set to select a
sample. The results of the
different sampling methods will
be compared.
Sampling to Study Drug Use 19