Sampling. Population Well-defined set with specified properties –People –Animals –Events –Sport teams –Clinical units –Communities –Schools –Specimens.

Sampling

Population

• Well-defined set with specified properties– People– Animals– Events– Sport teams– Clinical units

– Communities– Schools– Specimens– Charts– Historical

documents

Census

• Investigation of all individual elements that make up a population

Sample

Why sample?

• Generally difficult to study entire population

(Cost + Speed)• Able to make

generalizations to population from appropriately derived sample.

Sampling

Procedure by which some members of the population are selected as representatives of the entire population

Sample

• Subset of a larger population

Population

Sample

Sampling Frame

Who do you want Who do you want to generalize to?to generalize to?Who do you want Who do you want to generalize to?to generalize to?

The Theoretical The Theoretical PopulationPopulation

The Theoretical The Theoretical PopulationPopulation

What population can What population can you get access to?you get access to?

What population can What population can you get access to?you get access to?

The Study The Study PopulationPopulationThe Study The Study PopulationPopulation

How can you get How can you get access to them?access to them?How can you get How can you get access to them?access to them?

The Sampling The Sampling FrameFrame

The Sampling The Sampling FrameFrame

Who is in your study?Who is in your study?Who is in your study?Who is in your study? The SampleThe SampleThe SampleThe Sample

Types of samples

• Nonprobabilistic– Nonrandom selection– Can not assure every element has an equal

chance for being included

• Probabilistic– Uses some form of random selection– More likely to result in representative

sample

Probability Sampling

1. Simple random sampling

2. Stratified random sampling

3. Systematic Sampling

4. Cluster sampling

Simple Random Sampling

– the purest form of probability sampling. – Assures each element in the population has

an equal chance of being included in the sample

– Random number generators

List of ResidentsList of ResidentsList of ResidentsList of Residents

Simple Random Sampling

List of ResidentsList of ResidentsList of ResidentsList of Residents

Random SubsampleRandom SubsampleRandom SubsampleRandom Subsample

Simple Random Sampling

STATISTICAL TABLES: Table A Random Digits

Example: Simple random sampling

1 Albert D.2 Richard D.3 Belle H.4 Raymond L.5 Stéphane B.6 Albert T.7 Jean William V.8 André D.9 Denis C.10 Anthony Q.11 James B.12 Denis G.13 Amanda L.14 Jennifer L.15 Philippe K.16 Eve F.17 Priscilla O.18 Thomas G.19 Brian F.20 Hellène H.21 Isabelle R.22 Jean T.23 Samanta D.24 Berthe L.

25 Monique Q.26 Régine D.27 Lucille L.28 Jérémy W.29 Gilles D.30 Renaud S.31 Pierre K.32 Mike R.33 Marie M.34 Gaétan Z.35 Fidèle D.36 Maria P.37 Anne-Marie G.38 Michel K.39 Gaston C.40 Alain M.41 Olivier P.42 Geneviève M.43 Berthe D.44 Jean Pierre P.45 Jacques B.46 François P.47 Dominique M.48 Antoine C.

SIMPLE RANDOM SAMPLING

Systematic Random SamplingSystematic Random Sampling1 26 51 762 27 52 773 28 53 784 29 54 795 30 55 806 31 56 817 32 57 828 33 58 839 34 59 8410 35 60 8511 36 61 8612 37 62 8713 38 63 8814 39 64 8915 40 65 9016 41 66 9117 42 67 9218 43 68 9319 44 69 9420 45 70 9521 46 71 9622 47 72 9723 48 73 9824 49 74 9925 50 75 100

N = 100N = 100N = 100N = 100

want n = 20want n = 20want n = 20want n = 20

N/n = 5N/n = 5N/n = 5N/n = 5

select a random number from 1-5: select a random number from 1-5: chose 4chose 4

select a random number from 1-5: select a random number from 1-5: chose 4chose 4

Systematic Random SamplingSystematic Random Sampling1 26 51 762 27 52 773 28 53 784 29 54 795 30 55 806 31 56 817 32 57 828 33 58 839 34 59 8410 35 60 8511 36 61 8612 37 62 8713 38 63 8814 39 64 8915 40 65 9016 41 66 9117 42 67 9218 43 68 9319 44 69 9420 45 70 9521 46 71 9622 47 72 9723 48 73 9824 49 74 9925 50 75 100

N = 100N = 100N = 100N = 100

want n = 20want n = 20want n = 20want n = 20

N/n = 5N/n = 5N/n = 5N/n = 5

select a random number from 1-5: select a random number from 1-5: chose 4chose 4

select a random number from 1-5: select a random number from 1-5: chose 4chose 4

start with #4 and take every 5th unitstart with #4 and take every 5th unitstart with #4 and take every 5th unitstart with #4 and take every 5th unit

Stratified Random SamplingStratified Random Sampling

List of ResidentsList of ResidentsList of ResidentsList of Residents

Stratified Random SamplingStratified Random Sampling

List of ResidentsList of ResidentsList of ResidentsList of Residents

StrataStrataStrataStrata

surgicalsurgical Non-clinicalNon-clinicalmedicalmedical

Stratified Random SamplingStratified Random Sampling

List of ResidentsList of ResidentsList of ResidentsList of Residents

Random Subsamples of n/NRandom Subsamples of n/NRandom Subsamples of n/NRandom Subsamples of n/N

StrataStrataStrataStrata

surgicalsurgical Non-clinicalNon-clinicalmedicalmedical

Cluster Sampling

– The primary sampling unit is not the individual element, but a large cluster of elements. Either the cluster is randomly selected or the elements within are randomly selected

– Why? – Frequently used when no list of population

available or because of cost

Example: Cluster sampling

Section 4

Section 5

Section 3

Section 2Section 1

Non-Probability Sampling

1. Convenience

2. Quota

3. Purposive

4. Snowball

Convenience

• Available subjects enter study until sample size reached

• Inexpensive, quick, easy• Large risk of bias• Questionable representativeness• Examples:

– First 30 patients who enter a clinic with arthritis

– Parents of children in a shopping mall

Purposive sampling

• Handpick cases • Conscious effort to include specific

elements in sample• May pick subjects with diverse views,

specific characteristics• Easy, bias present, limited

representativeness• Used in qualitative research

Purposive Sample Examples:

• Specific populations:– Victims of child abuse– Parents of children with rare illness

• Diverse views:– Those who support/don’t support a public

policy (e.g., abortion)

Quota Sampling

• Include specific number of elements in pre-determined categories– Based on known pop. characteristics

• Relatively easy• Bias present

Quota Sampling - Example

1 0 0 fem a les

1 0 00 fe m a les

5 0 m a les

5 0 0 m a les

P op u la tion1 50 0 e lder ly liv in g in a res ide n tia l se tt ing

Quota Sample

Snowball Sampling

• Networking sampling (snowballing)– Ask for referrals

from identified case

Classification of Sampling Methods

SamplingMethods

ProbabilitySamples

SimpleRandom

Cluster

Systematic Stratified

Non-probability

QuotaPurposive

Convenience Snowball

Sample Size

• Should be determined by researcher before quantitative study is conducted

• Use the largest sample possible