Reliability Validity Sampling Review Levels of Measurement Review
Reliability & Validity Sampling
Review: Levels of Measurement
Review: Levels of Measurement
Reliability and Validity • Reliability – How dependable and consistent is the indicator? • Validity – Does the indicator capture the meaning of the construct?
Types of Reliability • Stability Reliability – Reliable across time – Test-retest method • Representative Reliability – Across subpopulations or groups – Subpopulation analysis • Equivalence Reliability – Consistent across different indicators – Split-half method
Improving Reliability 1. Clearly conceptualize constructs 2. Use a precise level of measurement 3. Use multiple indicators 4. Use pilot tests
Types of Measurement Validity • Face Validity • Does it appear to measure what it intends? • Content Validity • Does it capture the entire meaning? • Construct • Is the measure related to other measures as indicated by prior research? • Criterion Validity • Does it agree with external sources? – Concurrent – Predictive
Sampling • Random Sampling Population Random Process Sample • Random Assignment Pool of Subjects Random Process 1. Experimental Group 2. Control Group
• • Sampling Element Population/Universe Target Population Sampling Ratio: Population = 50, 000 Sample = 150 Sampling Ratio 150/50, 000 =. 003 Population = 500 Sample =100 Sampling Ration 100/500 =. 20
Examples of Populations 1. All CEOs of U. S. based multinational corporations living in the states on April 15, 1999. 2. All crime investigations conducted by the U. S. Securities and Exchange Commission from 1980 through 1999. 3. All persons arrested for insider trading in the U. S. from 1995 through 1999.
Nonprobability Sampling 1. Haphazard/Convenience/Availability 2. Quota 3. Purposive 4. Snowball
Probability Sampling 1. Simple Random Samples 2. Systematic Random Samples 3. Stratified Random Samples 4. Multistage Cluster Samples
Sample Size • • • Statistical equations Rule of thumb The smaller the population, the bigger the sampling ratio has to be for an accurate sample 1. Degree of accuracy required 2. Degree of variability in the population 3. The number of different variables
Baby boys to baby girls ratio • There are two hospitals: in the first one, 120 babies are born every day, in the other, only 12. On average, the ratio of baby boys to baby girls born every day in each hospital is 50/50. However, one day, in one of those hospitals twice as many baby girls were born as baby boys. In which hospital was it more likely to happen? (Nisbett, et al. , 1987).
- Slides: 15