# Sampling Techniques – Random, Systematic, Stratified etc

Hello! Good to see you again!

In this class I will explain the various sampling techniques you need to know. We would also consider examples of the technique as well as  the advantages and disadvantages of each technique

Content
• Basics of Sampling
• Simple Random Sampling
• Convenient Sampling
• Systematic Sampling
• Cluster Sampling
• Stratified Sampling

Basics of Sampling
To find things out about the population of interest, we need to take a sample from that population. A sample is a selection of some of the objects of the population as a representative of the population. The technique chosen for sampling depends on factors such as the nature of the population being samples as well as the amount of resources available in terms of time and money.
The idea is for each object in the population to be equally likely to be chosen as part of the sample, this is called unbiased sample.

Simple Random Sampling
This is theoritically the ideal method of sampling. In this, case you list all member of the population and used random numbers to determine which objects are to be selected.
This produces an unbiased sampling
It could be difficult to take simple random samples when dealing with peoples
It is suitable if the population is geographically concentrated and a sampling frame exists.
A sampling frame is a list of all the people or objects in the population

Convenient Sampling
In this case, you do what is convenient or easy.
Ask people nearby or people who walk past in a shopping mall
Take 20 objects coming off the production line
This is most times biased in some biased
Can have self-selection bias where people choose to participate if they have interest in the subject in question.
Convenient sampling provides a quick and convenient way to take samples.

Systematic Sampling
Choose a certain point at random and systematically take objects at certain number apart.
For example, if there is a population of 1000 and you want to take a sample of 5 objects, you can start from the first object and take after every 20 objects
Easier to carry out than Simple Random Sampling and a good approximation of SRS.
If there is a pattern, then a particular type of object could be chosen more often than others.

Cluster Sampling
Population is divided into clusters which are then chosen at random
Within each cluster, all objects in the cluster are included in the sample
Can be more convenient and practical than simple random sampling

Stratified Sampling
Resembles cluster sampling, but the strata or groups are chosen specifically to represent different characteristics of the population