Sampling Methods

Sampling:

It is the procedure by which some members are selected as representative of the entire population.

Some sampling terms:

Population:
Collection of units sharing common characteristics 
Ex:
Finite: Possibility of counting all units such as students in a school.
Infinite: such as RBCs of an individual.

Sample:

A subset of a population obtained to investigate properties of the parent population.

Target population:

Population upon which the results of the study will be generalized.

Sampling population:

Population from which the sample was taken.

Sampling unit:

Population unit used for sampling

Subject under observation on which information is collected such as: Children events. years, hospital discharges health.

Study population:

The population selected to be sampled it is a subset of the target population

Sampling frame:

Any list of all the sampling units in the population: List of households, health care units.

Sampling scheme:

Method of selecting sampling units from sampling frame Randomly, convenience sample.

Let's give example to understand: 

I want to make a research on medical students in Portsaid university especially those from Sharkia and their age range is 20-22, so my target population is medical students, my study population is medical student from Sharkia whose age is from 20 to 22 from which I am able to take my sample.

The sampling frame is all medical students in Portsaid university from which sampling units(from Sharkia) are taken. The sampling scheme is the way that I used to determine my sampling units. 

Why we need sampling:

Data on large population at relatively low cost and at greater speed.

2)     Provided measure of the amount of error introduced in the sampling process.

3)     More accurate data.

4)     Method to acquire data that might otherwise be impossible to gain.

Good sample saves time, money, and effort and assures data collection and valid estimates of population characteristics.

Basic types of sampling:

Probability (Random) sampling:

 

Simple Random sampling:

Each element in population has equal and independent chance of selection in sample.

Advantages:

a)      Represent the total sampling population. And can be generalized.

b)     Some statistical tests are based on theory of probability can be applied only to data collected from random samples.

Methods:

Conditions:

1)     Applied when population is small, homogeneous and readily available.

2)     All subsets of the frame are given an equal probability and also each element.

3)     Used in lotteries.

Procedures:

1)     Number each element using separate slips of paper for each element.

2)     Put all slips into box and pick them out one by one without looking.

Systematic random sampling:

Properties:

1)     Relies on arranging the target population according to some ordering scheme and then selecting elements at regular intervals through that ordered list.

2)     Systematic sampling involves a random start and then proceeds with the selection of every kth element from then onwards. In this case, k= (population size/sample size).

3)     There is a gap, interval between each selected unit in sample.

                                           As you see in figure.

Stratified Random Sampling:

1)     Where population embraces a number of distinct categories, the frame can be organized into separate "strata." Each stratum is then sampled as an independent sub-population, out of which individual elements can be randomly selected.

2)     Every unit in a stratum has same chance of being selected.

5)     Each stratum is homogenous inside, heterogeneous to outside.

 As you see in figure.

Cluster sampling:

1)     The researcher divides the population into separate groups, called clusters. Then, a simple random sample of clusters is selected from the population.

2)     Each cluster is heterogeneous inside, homogeneous to outside.

 As you see in figure.

Difference between stratum and cluster that we take a sample from stratum but in cluster we take it a whole as sample. Another difference that strata from inside is homogenous and outside is heterogenous while clusters are vice versa. 

Multistage sampling:

Large clusters of population are divided into smaller clusters in several stages in order to make primary data collection more manageable.

For example:

Your research objective is to evaluate online spending patterns of households in the US through online questionnaires. You can form your sample group comprising 120 households in the following manner:

Choose 6 states in the USA using simple random sampling (or any other probability sampling).

Choose 4 districts within each state using systematic sampling method (or any other probability sampling). 

Choose 5 households from each district using simple random or systematic sampling methods. This will result in 120 households to be included in your sample group.

Non-probability sampling:

Probability of being included in the sample is not known and not equal for the sampling units.

Such as:

a)     Convenient.

b)     Quota.

c)      Snow ball.

d)     Accidental sampling.

e)     Purpose / judgmental sampling.  

f)      Expert sampling.

Quota sampling:

The population is first segmented into mutually exclusive sub-groups.

Then judgment used to select subjects or units from each segment based on a specified proportion

For example: 

if you want 100 girl and 100 boy for job interview and their age ranges are 25-50. first, you will divide them into subgroups with age range (25-30) (30-35) (35-40) (40-45) (45-50). second, you will determine proportion for example half of people in group (25-30) and third from (40-45) and so on 

Purpose sampling:

You go only to those who are in your opinion are likely to have required information.

Convenience sampling:

It depends on convenience and guided by some visible characteristics.

For example:

If you are teacher in class and you want to make average for age of 20 males in the class, so as a teacher, you will stand at the entrance of class (convenience) and each one enters the class, ask him for age (characteristic).