1. © 2009 Pearson Prentice Hall, Salkind. Chapter 4 Sampling and Generalizability

2. © 2009 Pearson Prentice Hall, Salkind. CHAPTER OVERVIEW Populations and Samples Probability Sampling Strategies Nonprobability Sampling Strategies Sampling, Sample Size, and Sampling Error

3. © 2009 Pearson Prentice Hall, Salkind. POPULATIONS AND SAMPLES Inferential method is based on inferring from a sample to a population Sample—a representative subset of the population Population—the entire set of participants of interest Generalizability—the ability to infer population characteristics based on the sample

4. © 2009 Pearson Prentice Hall, Salkind. CHOOSING A REPRESENTATIVE SAMPLE Probability sampling—the likelihood of any member of the population being selected is known Nonprobability sampling—the likelihood of any member of the population being selected is unknown

5. © 2009 Pearson Prentice Hall, Salkind. PROBABILITY SAMPLING STRATEGIES Simple random sampling  Each member of the population has an equal and independent chance of being chosen  The sample should be very representative of the population

6. © 2009 Pearson Prentice Hall, Salkind. 1. Jane18. Steve35. Fred 2. Bill19. Sam36. Mike 3. Harriet20. Marvin37. Doug 4. Leni21. Ed. T.38. Ed M. 5. Micah22. Jerry39. Tom 6. Sara23. Chitra40. Mike G. 7. Terri24. Clenna41. Nathan 8. Joan25. Misty42. Peggy 9. Jim26. Cindy43. Heather 10. Terrill27. Sy44. Debbie 11. Susie28. Phyllis45. Cheryl 12. Nona29. Jerry46. Wes 13. Doug30. Harry47. Genna 14. John S.31. Dana48. Ellie 15. Bruce A.32. Bruce M.49. Alex 16. Larry33. Daphne50. John D. 17. Bob34. Phil 1. Define the population 2. List all members of the population 3. Assign numbers to each member of the population 4. Use criterion to select a sample CHOOSING A SIMPLE RANDOM SAMPLE

7. © 2009 Pearson Prentice Hall, Salkind. 1. Select a starting point 2. The first two digit number is 68 (not used) 3. The next number, 48, is used 4. Continue until sample is complete 23157485590183725993 05545504301053743508 14871036503240436223 38976497519405175853 97312176189975530870 11742691834433947512 43361828591101645623 93806043383826804491 49540311810842984187 36768762333794821569 USING A TABLE OF RANDOM NUMBERS

8. © 2009 Pearson Prentice Hall, Salkind. KEYS TO SUCCESS IN SIMPLE RANDOM SAMPLING Distribution of numbers in table is random Members of population are listed randomly Selection criterion should not be related to factor of interest!!

9. © 2009 Pearson Prentice Hall, Salkind. USING SPSS TO GENERATE RANDOM SAMPLES 1. Be sure that you’re in a data file 2. Click Data > Select Cases 3. Click Random sample of Cases 4. Click the Sample Button 5. Define Sample Size a. Click Continue b. Click OK (in next dialog box)

10. © 2009 Pearson Prentice Hall, Salkind. 1. Divide the population by the size of the desired sample: e.g., 50/10 = 5 2. Select a starting point at random: e.g., 43 = Heather 3. Select every 5 th name from the starting point SYSTEMATIC SAMPLING 1. Jane18. Steve35. Fred 2. Bill19. Sam36. Mike 3. Harriet20. Marvin37. Doug 4. Leni21. Ed. T.38. Ed M. 5. Micah22. Jerry39. Tom 6. Sara 23. Chitra40. Mike G. 7. Terri24. Clenna41. Nathan 8. Joan25. Misty42. Peggy 9. Jim26. Cindy43. Heather 10. Terrill27. Sy44. Debbie 11. Susie28. Phyllis45. Cheryl 12. Nona29. Jerry46. Wes 13. Doug30. Harry47. Genna 14. John S.31. Dana48. Ellie 15. Bruce A.32. Bruce M.49. Alex 16. Larry33. Daphne50. John D. 17. Bob34. Phil

11. © 2009 Pearson Prentice Hall, Salkind. STRATIFIED SAMPLING The goal of sampling is to select a sample that is representative of the population But suppose—  That people in the population differ systematically along some characteristic?  And this characteristic relates to the factors being studied? Then stratified sampling is one solution

12. © 2009 Pearson Prentice Hall, Salkind. STRATIFIED SAMPLING The characteristic(s) of interest are identified (e.g., gender) The individuals in the population are listed separately according to their classification (e.g., females and males) The proportional representation of each class is determined (e.g., 40% females & 60% males) A random sample is selected that reflects the proportions in the population(e.g., 4 females & 6 males)

13. © 2009 Pearson Prentice Hall, Salkind. STRATIFICATION ON MORE THAN ONE FACTOR Grade Location135Total Rural 1,200 [120] 1,200 [120] 600 [60] 3,000 [300] Urban 2,800 [280] 2,800 [280] 1,400 [140] 7,000 [700] Total 4,000 [400] 4,000 [400] 2,000 [200] 10,000 [1000]

14. © 2009 Pearson Prentice Hall, Salkind. CLUSTER SAMPLING Instead of randomly selecting individuals  Units (groups) of individuals are identified  A random sample of units is then selected  All individuals in each unit are assigned to one of the treatment conditions Units must be homogeneous in order to avoid bias

15. © 2009 Pearson Prentice Hall, Salkind. NON PROBABILITY SAMPLING STRATEGIES Convenience sampling  Captive or easily sampled population  Not random  Weak representativeness Quota sampling  Proportional stratified sampling is desired but not possible  Participants with the characteristic of interest are non- randomly selected until a set quota is met

16. © 2009 Pearson Prentice Hall, Salkind. Summary of the different types of probability and nonprobability strategies

17. © 2009 Pearson Prentice Hall, Salkind. SAMPLES, SAMPLE SIZE, AND SAMPLING ERROR Sampling error = difference between sample and population characteristics Reducing sampling error is the goal of any sampling technique As sample size increases, sampling error decreases

18. © 2009 Pearson Prentice Hall, Salkind. HOW BIG IS BIG? The goal is to select a representative sample—  Larger samples are usually more representative  But larger samples are also more expensive  And larger samples ignore the power of scientific inference

19. © 2009 Pearson Prentice Hall, Salkind. ESTIMATING SAMPLE SIZE Generally, larger samples are needed when  Variability within each group is great  Differences between groups are smaller Because  As a group becomes more diverse, more data points are needed to represent the group  As the difference between groups becomes smaller, more participants are needed to reach “critical mass” to detect the difference

20. © 2009 Pearson Prentice Hall, Salkind. HAVE WE MET THE OBJECTIVES? CAN YOU: Apply the following concepts?  Population  Sample  Random  Generalization (generalizability) Differentiate between probability and nonprobability sampling techniques?

21. © 2009 Pearson Prentice Hall, Salkind. OBJECTIVES, CONTINUED CAN YOU: Identify four (4) probability sampling strategies?  Simple Random Sampling  Systematic Sampling  Stratified Sampling  Cluster Sampling Identify two (2) nonprobability sampling strategies?  Convenience Sampling  Quota Sampling

22. © 2009 Pearson Prentice Hall, Salkind. OBJECTIVES, CONTINUED CAN YOU: Explain sampling error?  List ways researchers can reduce sampling error  Summarize the effect of sample size on sampling error