SAMPLING METHODS

ELEMENTS

Population - is the set of all the elements of interest.

A sample - is a subset of the population.

An element - is the entity on which data are collected.

A frame is a list of the elements that the sample will be selected from.

• The reason we select a sample is to collect data to answer a research question about a population.

THREE CRITERIA IN DETERMINING SAMPLE SIZE

• Level of precision: estimates value of a population, also known as sampling error

• Level of confidence: also known as risk level, the probability that the sample is representative of the true population value

• Degree of Variability: distribution of attributes in the population. 

  • More heterogenous population = larger sample size needed to obtain level of precision

Probability sampling 

• Every element of a population is given an equal chance of being selected

  • Simple random: drawing lots or using a random function of a calculator. 

  • Systematic random: random selection of first k elements in an ordered population

    • You want to pick n items from a population with N total items.

    • You divide N by n to get a number — this tells you how often to pick.

      • Example: If N = 100 and n = 10 → 100 ÷ 10 = every 10th item

    • Randomly pick one item from the first 10 (or whatever your interval is).

    • Then keep picking every 10th item after that in the list.

  • Stratified random: selecting a simple random sample from each of a given number of subpopulations/strata. 

    • It's a method of sampling where the population is divided into groups, called strata.

    • Then you take a random sample from each group.

  • Cluster: sampling to a smaller area, divided by regions, divisions or districts.

Selecting a sample

• From a Finite population

  • It’s a group with a limited number of items or people

  • Without replacement (most common):

    • Once something is picked, it’s not put back.

  • With replacement:

    • After picking something, it’s put back, so it might be picked again.

• From a Process 

  • Some populations come from ongoing processes — they don’t stop or end

  • These are called infinite populations, because you can’t list all the items.

    • Each item in the sample must be independent (not affected by the others)

    • Each item must follow the same pattern or distribution as the rest of the population

Non-probability sampling

• Convenience Sampling

  • not everyone has a known or equal chance of being picked.

  • You just pick whoever is easiest to reach or available.

• Judgement Sampling

  • The person doing the research chooses the people or items they think best represent the whole group.

• Quota Sampling

  • collect data from specific groups of people.

  • The goal is to make sure certain types of people are included in the sample

• Snowball sampling

  • It’s a non-probability sampling method often used in qualitative research.

  • It works like a referral system — one person leads you to the next.