1. Part 2: Quantitative Methods October 9, 2006

2. Validity Face –Does it appear to measure what it purports to measure? Content –Do the items cover the domain? Construct –Does it measure the unobservable attribute that it purports to measure?

3. Validity Criterion –Predictive –Concurrent Consequential

4. Types of validity (cont.) The instrument The construct Here the instrument samples some and only of the construct

5. Types of validity The construct The instrument Here the instrument samples all and more of the construct

6. The construct The instrument Here the instrument fails to sample ANY of the construct

7. The construct The instrument Here the instrument samples some but not all of the construct

8. Perfection! The construct and the instrument!

9. Reliability and Validity

10. In groups of 3 to 4 Sampling –What is the target population? –What sampling procedure was used? –Do you think the sample is representative? Why or why not? Measurement –What types of reliability and validity evidence are provided? –What else would you like to know?

11. Ways to Classify Instruments Who Provides the Information? –Themselves: Self-report data –Directly or indirectly: from the subjects of the study –From informants (people who are knowledgeable about the subjects and provide this information)

12. Types of Researcher-completed Instruments Rating scales Interview schedules Tally sheets Flowcharts Performance checklists Observation forms

13. Excerpt from a Behavior Rating Scale for Teachers Instructions: For each of the behaviors listed below, circle the appropriate number, using the following key: 5 = Excellent, 4 = Above Average, 3 = Average, 2 = Below Average, 1 = Poor. A. Explains course material clearly. 12345 B. Establishes rapport with students. 12345 C. Asks high-level questions. 12345 D. Varies class activities. 12345

14. Excerpt from a Graphic Rating Scale Instructions: Indicate the quality of the student’s participation in the following class activities by placing an X anywhere along each line. AlwaysFrequentlyOccasionallySeldomNever 1. Listens to teacher’s instructions. Always Frequently Occasionally Seldom Never 2. Listens to the opinions of other students. Always Frequently Occasionally Seldom Never 3. Offers own opinions in class discussions.

15. Sample Observation Form

16. Discussion Analysis Tally Sheet

17. Performance Checklist Noting Student Actions

18. Types of Subject-completed Instruments Questionnaires Self-checklists Attitude scales Personality inventories Achievement/aptitude tests Performance tests Projective devices

19. Example of a Self-Checklist

20. Example of Items from a Likert Scale

21. Example of the Semantic Differential

22. Pictorial Attitude Scale for Use with Young Children

23. Sample Items from a Personality Inventory

24. Sample Items from an Achievement Test

25. Sample Item from an Aptitude Test

26. Sample Items from an Intelligence Test

27. Item Formats Questions used in a subject-completed instrument can take many forms but are classified as either selection or supply items. Examples of selection items are: True-false items Matching items Multiple choice items Interpretive exercises Examples of supply items are: Short answer items Essay questions

28. Norm-Referenced vs. Criterion- Referenced Instruments All derived scores give meaning to individual scores by comparing them to the scores of a group. The group used to determine derived scores is called the norm group and the instruments that provide such scores are referred to as norm-referenced instruments. An alternative to the use of achievement or performance instruments is to use a criterion-referenced test. This is based on a specific goal or target (criterion) for each learner to achieve. The difference between the two tests is that the criterion referenced tests focus more directly on instruction.

29. Experimental Research

30. The (Never-Ending) Search for Causation Establishing causation among variables : »Produces increased understanding of those variables »Results in the ability to manipulate conditions in order to produce desired changes

31. Experimental Research Can demonstrate cause-and-effect very convincingly Very stringent research design requirements Experimental design requires: »Random assignment to groups (experimental and control) »Independent treatment variable that can be applied to the experimental group »Dependent variable that can be measured in all groups

32. Quasi-Experimental Research Used in place of experimental research when random assignment to groups is not feasible Otherwise, very similar to true experimental research

33. Fundamentals of Experimental and Quasi- Experimental Research Cause and effect: »Incorporates a temporal element — the cause is a condition that exists prior to the effect; effect is a condition that occurs after the cause »There exists a “logical connection” — cause-and-effect is demonstrated when manipulation of the independent variable results in differences in the dependent variable (as evidenced by comparing the experimental group to the control group)

34. What Aids Our Causal Arguments? Theory –"causes certainly are connected to effects; but this is because our theories connect them, not because the world is held together by cosmic glue. The world may be glued together by imponderables, but that is irrelevant for understanding causal explanation." Hanson, 1958. Temporal Elements Design –"No causation without manipulation" Rubin & Holland

35. Fundamentals of Experimental and Quasi- Experimental Research Random selection and random assignment : »Distinguish between “selection” and “assignment” »Random selection helps to assure population validity »If you incorporate random assignment Experimental research »If you do not use random assignment Quasi-experimental research

36. Fundamentals of Experimental and Quasi- Experimental Research (cont’d.) When to use experimental research design : »If you strongly suspect a cause-and-effect relationship exists between two conditions, and »The independent variable can be introduced to participants and can be manipulated, and »The resulting dependent variable can be measured for all participants

37. Internal and External Validity “Validity of research” refers to the degree to which the conclusions are accurate and generalizable Both experimental and quasi-experimental research are subject to threats to validity If threats are not controlled for, they may introduce error into the study, which will lead to misleading conclusions

38. Threats to External Validity External validity — extent to which the results can be generalized to other groups or settings »Population validity — degree of similarity among sample used, population from which it came, and target population »Ecological validity — physical or emotional situation or setting that may have been unique to the experiment »If the treatment effects can be obtained only under a limited set of conditions or only by the original researcher the findings have low ecological validity.

39. Threats to External Validity Selection bias –if sample is biased you cannot generalize to the population. Reactive effects –Experimental setting - differs from natural setting. –Testing – pretest influences how subjects respond to the treatment. Multiple-treatment inference –If the subjects are exposed to more than one treatment, then the findings could only be generalized to individuals exposed to the same treatments in the same order of presentation.

40. Threats to Internal Validity Internal validity — extent to which differences on the dependent variable are a direct result of the manipulation of the independent variable »History—when factors other than treatment can exert influence over the results; problematic over time »Maturation—when changes occur in dependent variable that may be due to natural developmental changes; problematic over time »Testing—pretest may give clues to treatment or posttest and may result in improved posttest scores »Instrumentation – Nature of outcome measure has changed.

41. Threats to Internal Validity (cont’d.) »Regression – Tendency of extreme scores to be nearer to the mean at retest »Differential selection of participants — participants are not selected/assigned randomly »Attrition (mortality) — loss of participants »Experimental treatment diffusion – Control conditions receive experimental treatment.

42. Experimental and Quasi-Experimental Research Designs Commonly used experimental design notation : » X 1 =treatment group » X 2 =control/comparison group » O=observation (pretest, posttest, etc.) » R=random assignment

43. Common Experimental Designs Single-group pretest-treatment-posttest design: OXOOXO »Technically, a pre-experimental design (only one group; therefore, no random assignment exists) »Overall, a weak design »Why?

44. Common Experimental Designs (cont’d.) Two-group treatment-posttest-only design: RX1ORX2ORX1ORX2O »Here, we have random assignment to experimental, control groups »A better design, but still weak—cannot be sure that groups were equivalent to begin with

45. Common Experimental Designs (cont’d.) Two-group pretest-treatment-posttest design: ROX1OROX2OROX1OROX2O »A substantially improved design—previously identified errors have been reduced

46. Common Experimental Designs (cont’d.) Solomon four-group design: ROX1OROX2ORX1ORX2OROX1OROX2ORX1ORX2O »A much improved design—how?? »One serious drawback—requires twice as many participants

47. Common Experimental Designs (cont’d.) Factorial designs: ROX1OROX2 OROX1 OROX2 OROX1OROX2 OROX1 OROX2 O »Incorporates two or more factors »Enables researcher to detect differential differences (effects apparent only on certain combinations of levels of independent variables)

48. Common Experimental Designs (cont’d.) Single-participant measurement-treatment-measurement designs: O O O | X O X O | O O O »Purpose is to monitor effects on one subject »Results can be generalized only with great caution

49. Common Quasi-Experimental Designs Posttest-only design with nonequivalent groups: X1OX2OX1OX2O »Uses two groups from same population »Questions must be addressed regarding equivalency of groups prior to introduction of treatment

50. Common Quasi-Experimental Designs (cont’d.) Pretest-posttest design with nonequivalent groups: OX1OOX2OOX1OOX2O »A stronger design—pretest may be used to establish group equivalency

51. Similarities Between Experimental and Quasi-Experimental Research Cause-and-effect relationship is hypothesized Participants are randomly assigned (experimental) or nonrandomly assigned (quasi-experimental) Application of an experimental treatment by researcher Following the treatment, all participants are measured on the dependent variable Data are usually quantitative and analyzed by looking for significant differences on the dependent variable