When you want to do more than simply make inferences about a population!

NON-PROBABILITY SAMPLING METHODS

PROBABILITY SAMPLING
What you want to talk about

Population

What you actually observe in the data

Sampling Process Sampling Frame

Sample

Inference

Using data to say something (make an inference) with confidence, about a whole (population) based on the study of a only a few (sample).

PROBABILITY SAMPLING
Probability sampling is designed to allow extrapolation from a small, highly representative sample, to a larger population. This statistical inference allows us to describe a population. Used when you want to answer the where and how many questions.

NON-PROBABILITY SAMPLING

Used when you want to say something about a discrete phenomena, a few select cases (people, places, objects, etc.) or when you want to answer the how and why questions.

SELECTION OF PARTICIPANTS

TYPE OF SAMPLING Convenience

SELECTION STRATEGY Select cases based on their availability for the study.

PURPOSE
Saves time, money and effort; but at the expense of information and credibility.

SELECTION OF PARTICIPANTS

TYPE OF SAMPLING Critical case

SELECTION STRATEGY Select cases that are key or essential for overall acceptance or assessment.

PURPOSE
Permits logical generation and maximum application of information to other cases.

SELECTION OF PARTICIPANTS

TYPE OF SAMPLING Snowball or chain referral

SELECTION STRATEGY Group members identify additional members to be included in the sample.

PURPOSE
Identifies cases of interest to people who know people, who know what cases are informationrich.

SELECTION OF PARTICIPANTS

TYPE OF SAMPLING Politically important cases

SELECTION STRATEGY Include or exclude informants that are connected with politically sensitive issues.

PURPOSE
Attracts desired attention or avoids attracting undesired attention.

SELECTION OF PARTICIPANTS

TYPE OF SAMPLING Typical case

SELECTION STRATEGY Select cases that are known before-hand to be useful and not too extreme.

PURPOSE
Highlights what is known to be normal or average.

SELECTION OF PARTICIPANTS

TYPE OF SAMPLING Maximum variation

SELECTION STRATEGY Select outlier cases to see if main patterns still hold (negative instances, variations).

PURPOSE
Captures wide variation, identifies key common factors, examines a range of perspectives.

SELECTION OF PARTICIPANTS

TYPE OF SAMPLING Intensity

SELECTION STRATEGY Select informants with in-depth understanding of the phenomenon under study

PURPOSE
Information-rich cases that manifest the phenomenon intensively, but not EXTREMELY.

SELECTION OF PARTICIPANTS

TYPE OF SAMPLING Quota

SELECTION STRATEGY Select a sample that yields the same proportions as the population proportions on easily identified variables.

PURPOSE
Taking a set number of cases from each subgroup to raise analytic confidence and representativen ess.

SELECTION OF PARTICIPANTS

TYPE OF SAMPLING Theoretical saturation (sequential)

SELECTION STRATEGY Finds as many relevant cases as possible.

PURPOSE
Reach saturation point; when no new information emerges.

SELECTION OF PARTICIPANTS

TYPE OF SAMPLING Most similar/ dissimilar cases

SELECTION STRATEGY Select cases that are judged to represent either similar or very different conditions.

PURPOSE
Elaborating initial analysis, seeking exceptions, looking for variation.

SELECTION OF PARTICIPANTS

TYPE OF SAMPLING Comparable case

SELECTION STRATEGY Select multiple individuals, sites, and groups on the same relevant characteristics over time.

PURPOSE
Be able to compare across cases, or over time (pseudo replication).

SELECTION OF PARTICIPANTS

TYPE OF SAMPLING Criterion

SELECTION STRATEGY All cases that meet some criteria.

PURPOSE
Useful for quality assurance.