Chapter 15 Sampling and Sample Size Winston Jackson and Norine Verberg Methods: Doing Social...

18
Chapter 15 Sampling and Sample Size Winston Jackson and Norine Verberg Methods: Doing Social Research, 4e

Transcript of Chapter 15 Sampling and Sample Size Winston Jackson and Norine Verberg Methods: Doing Social...

Page 1: Chapter 15 Sampling and Sample Size Winston Jackson and Norine Verberg Methods: Doing Social Research, 4e.

Chapter 15Sampling and Sample Size

Winston Jackson and Norine Verberg

Methods: Doing Social Research, 4e

Page 2: Chapter 15 Sampling and Sample Size Winston Jackson and Norine Verberg Methods: Doing Social Research, 4e.

15-2 © 2007 Pearson Education Canada

The Rationale of Sampling

Sampling a segment of a population can save time and money, yet provide an accurate description of a population Key issue: sample must be representative Poorly selected samples misrepresent the

population Literary Digest poll failed to predict outcome

of 1936 American election: Landon versus Roosevelt Used large sample – polled subscribers Subscribers not representative of population

Page 3: Chapter 15 Sampling and Sample Size Winston Jackson and Norine Verberg Methods: Doing Social Research, 4e.

15-3 © 2007 Pearson Education Canada

Key Distinctions

Population (also called universe): the entire group one wishes to describe E.g., American electors, students living in residence

Sampling frame: the list from which a sample is selected Ideally, sampling frame is same as population, but

seldom possible; creates challenges Sample: units (e.g., individuals) selected for a study

Variation in sampling techniques Response rate: the percentage of delivered

questionnaires completed and returned

Page 4: Chapter 15 Sampling and Sample Size Winston Jackson and Norine Verberg Methods: Doing Social Research, 4e.

15-4 © 2007 Pearson Education Canada

Probability Sampling Techniques

Techniques for selecting sampling units so that each unit has a known chance of being included Also called random sample because sampling

units are selected “at random” Tests of significance only valid for probability

samples

Page 5: Chapter 15 Sampling and Sample Size Winston Jackson and Norine Verberg Methods: Doing Social Research, 4e.

15-5 © 2007 Pearson Education Canada

Probability Sampling Techniques

Four types: Simple random sample Systematic sample Stratified sample Multi-stage area sample

Page 6: Chapter 15 Sampling and Sample Size Winston Jackson and Norine Verberg Methods: Doing Social Research, 4e.

15-6 © 2007 Pearson Education Canada

Simple Random Sample

Each unit in the population has an equal chance of being selected from a list

Requires having a list of potential participants List of eligible voters, companies, students, libraries

Process: Number the units on the list Use table of random numbers or computer to make

selection

Page 7: Chapter 15 Sampling and Sample Size Winston Jackson and Norine Verberg Methods: Doing Social Research, 4e.

15-7 © 2007 Pearson Education Canada

Systematic Sample

Each sampling unit has an equal chance of being selected, by choosing the nth case, starting randomly E.g., units listed in phone book, directories, street map

Process Secure list: map, diagram, list Divide sample required into number on the list to

determine the skip interval Choose a random number used to begin randomly

then every nth number selected

Page 8: Chapter 15 Sampling and Sample Size Winston Jackson and Norine Verberg Methods: Doing Social Research, 4e.

15-8 © 2007 Pearson Education Canada

Stratified Sample

Sampling within subgroups to ensure an adequate representation of each subgroup Important when subgroup is small in number Employs a random selection method

Example: Tracey Adams’ study of gender and dentistry The sample was stratified by gender to ensure

that enough female dentists and dental specialist were included in the study for comparison with males

Page 9: Chapter 15 Sampling and Sample Size Winston Jackson and Norine Verberg Methods: Doing Social Research, 4e.

15-9 © 2007 Pearson Education Canada

Stratified Sampling (cont’d)

Process: Determine sample size needed for subgroups Obtain list for each subgroup Use either simple random or systematic

sampling select respondents Within SPSS it is possible to weight cases to

return the sample so it can represent the larger population

Page 10: Chapter 15 Sampling and Sample Size Winston Jackson and Norine Verberg Methods: Doing Social Research, 4e.

15-10 © 2007 Pearson Education Canada

Multi-Stage Area Sample

This method is used when study involves a large population such as provinces or a whole country for which no list exists Identify primary sampling units: select

sample (country, provinces, counties) Identify sub-units within selected units (city

blocks, square kilometers etc.): select sample Identify households within sub-units: select

sample Within household select respondents Selection is always done randomly

Page 11: Chapter 15 Sampling and Sample Size Winston Jackson and Norine Verberg Methods: Doing Social Research, 4e.

15-11 © 2007 Pearson Education Canada

Non-Probability SamplingNon-Probability Sampling

Non-probability samples do not provide an equal or a known chance of being selected Hence, no assurance that the sample will be

representative of the study population Four types:

Quota sample Convenience sample Snowball sample

Page 12: Chapter 15 Sampling and Sample Size Winston Jackson and Norine Verberg Methods: Doing Social Research, 4e.

15-12 © 2007 Pearson Education Canada

Quota Sample

Respondents are selected on the basis of meeting certain criteria

No list of potential respondents is required: usually done on a first-come, first-included basis until quota is filled Sampling stops when enough are included in

each category Cannot claim that the sample represents the

population

Page 13: Chapter 15 Sampling and Sample Size Winston Jackson and Norine Verberg Methods: Doing Social Research, 4e.

15-13 © 2007 Pearson Education Canada

Convenience Sampling

Sample selection motivated by convenience to the researcher E.g., using all those in attendance at a

meeting or a class; interviewing people in a mall

Strong potential for recruiting a non-representative sample

Page 14: Chapter 15 Sampling and Sample Size Winston Jackson and Norine Verberg Methods: Doing Social Research, 4e.

15-14 © 2007 Pearson Education Canada

Snowball Sampling

Sample selection depends upon current participants recruiting other potential participants into the study Also known as “referral sampling”

Used when participants with specific characteristics are difficult to locate, such as people involved in deviant groups (motorcycle gang) or activities (bank robbery) or people with certain life experience (bride-to-be, homeless) or occupation (First Nations fisher)

Page 15: Chapter 15 Sampling and Sample Size Winston Jackson and Norine Verberg Methods: Doing Social Research, 4e.

15-15 © 2007 Pearson Education Canada

Sample Size Determination

Sample size determination involves a series of tradeoffs between precision, cost, and the numbers necessary to do appropriate analyses

Textbook provides steps in determining sample size for a ratio variable or for a nominal variable Each procedure involves deciding on the

confidence level to be used (95% precision is established norm)

Estimating sample size is simple to do

Page 16: Chapter 15 Sampling and Sample Size Winston Jackson and Norine Verberg Methods: Doing Social Research, 4e.

15-16 © 2007 Pearson Education Canada

Sample Size and Accuracy

Statistical procedures are sensitive to sample size In effect, sample size influences the precision

of estimations (the confidence intervals used in statistical procedures)

This applies only to probability samples General rule of thumb: to double accuracy,

you quadruple sample size

Page 17: Chapter 15 Sampling and Sample Size Winston Jackson and Norine Verberg Methods: Doing Social Research, 4e.

15-17 © 2007 Pearson Education Canada

The Impact of Refusals

Tests of significance assume:1. A probability sampling technique was used to

collect the data and

2. There is no systematic bias in the sample (i.e., measurement error is random, not systematic)

Although non-response is common, it is not clear how it affects the precision of the results Every effort should be made to have a good

response rate

Page 18: Chapter 15 Sampling and Sample Size Winston Jackson and Norine Verberg Methods: Doing Social Research, 4e.

15-18 © 2007 Pearson Education Canada

Confirming Representativeness

Steps can be taken to confirm the sample represents the population

One can compare the age, gender, and marital status distributions of one’s sample to known distributions for the population If the sample is not wholly representative,

there are techniques for weighting the results Or, one can note that the results may not

reflect the group that was underrepresented (e.g., results may not represent views of X)