Sampling

1. Sampling CSC 426 � Week 6 Zahra Ferdowsi 5th May 2009

2. External Validity Sampling Terminology Statistical Terms in Sampling Probability Sampling Non-probability Sampling Agenda 2

3. External validity is related to generalizing Validity : approximate truth of propositions, inferences, or conclusions External validity: approximate truth of conclusions that involve generalizations External Validity 3

4. Proximal Similarity Model Developing theory about similar contexts to your study Settings that have people who are more or less similar to the people in your study (holds for times and places) Place different contexts in terms of gradient of similarity Generalize the results of your study to other persons, places or times that are more similar to your study Sampling Model Provide Evidence for Generalization 4

5. How to do: Identifying the population you would like to generalize to Draw a fair sample Conduct your research with the sample Automatically generalize your results back to the population Threats Don�t know who you might ultimately like to generalize to Drawing a fair or representative sample Sample across all times (like next year). Sampling Model 5

6. How you might be wrong in making a generalization People Places Times Improving External Validity Good job of drawing a sample from a population Random selection rather than a nonrandom procedure Replicate your study in a variety of places, with different people and at different times Threats to External Validity 6

7. Population: The group you wish to generalize to Theoretical Population Accessible Population Sampling Frame: listing of the accessible population The Sample: who you select to be in your study Sampling Terminology 7

8. Response: a specific measurement value that a sampling unit supplies Statistic Parameter Statistical Terms in Sampling 8

9. The distribution of an infinite number of samples of the same size as your sample Normal Distribution: The bar graph of infinite samples would be well described by the bell curve shape Sampling Distribution 9

10. Standard deviation the spread of the scores around the average in a single sample Standard error (Sampling error) the spread of the averages around the average of averages in a sampling distribution Low sampling error means that your sample is close to the actual population itself. Sampling Distribution (Cont.) 10

11. 68% of cases are between plus-and-minus one standard units from average 95% Rule: plus-and-minus two units 99% Rule: plus-and-minus three units General Rules in Normal Distribution 11

12. Sampling that utilizes �random selection� Some Definitions: N = the number of cases in the sampling frame n = the number of cases in the sample NCn = the number of combinations (subsets) of n from N f = n/N = the sampling fraction Probability Sampling 12

13. Simple Random Sampling To select n units out of N such that each unit has an equal chance of being selected. Easy to accomplish Easy to explain to others Not get good representation sometimes (luck of the draw) Stratified Random Sampling Dividing your population into homogeneous groups and then taking a simple random sample in each group Able to represent key subgroups of the population More statistical precision (when groups are homogeneous) Probability Sampling Methods 13

14. Systematic Random Sampling Number the units in the population from 1 to N Decide on the n (sample size) that you want or need k = N/n = the interval size Randomly select an integer between 1 to k Take every Kth unit Probability Sampling Methods (Conts.) 14

15. Cluster (Area) Random Sampling Divide population into clusters (usually along geographic boundaries) Randomly sample clusters Measure all units within sampled clusters Multi-Stage Sampling Combine sampling methods Probability Sampling Methods (Conts.) 15

16. Does not involve random selection May or may not represent the population well Probabilistic or random sampling methods are more accurate and rigorous Sometimes probabilistic sampling is not feasible, practical or theoretically sensible Nonprobability Sampling 16

17. Accidental Sampling Who are available to us use of college students in much psychological research Asking for volunteers Purposive Sampling Have one or more specific predefined groups Females between 30 and 40 years old in market research Likely to get the opinions of your target population, but you are also likely to overweight subgroups Nonprobability Sampling Methods 17

18. Modal Instance Sampling Mode: the most frequently occurring value in a distribution sampling the most frequent case, or the "typical" case what the "typical" or "modal" case is? For example: average age, educational level, and income in the population What if other variable is an important discriminator? Expert Sampling Sample of persons with known or demonstrable experience and expertise Elicit the views of persons who have specific expertise Provide evidence for the validity of another sampling Purposive Sampling Methods 18

19. Quota Sampling Select people nonrandom proportional quota sampling Non-proportional quota sampling Heterogeneity Sampling (diversity) Is used in many brainstorming or nominal group opposite of modal instance sampling Snowball Sampling Identifying someone who meets the criteria for your study and then ask them to recommend others Specially when population is inaccessible or hard to find Purposive Sampling Methods (Cont.) 19

20. Questions? 20