1 / 37

Understanding the Scientific Method in Behavioral Sciences

Learn about the scientific method in behavioral sciences, including levels of analysis, experimental design, data analysis, and the importance of peer-reviewed publication.

dtrimble
Download Presentation

Understanding the Scientific Method in Behavioral Sciences

An Image/Link below is provided (as is) to download presentation Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author. Content is provided to you AS IS for your information and personal use only. Download presentation by click this link. While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server. During download, if you can't get a presentation, the file might be deleted by the publisher.

E N D

Presentation Transcript


  1. Chapter 2 Methodology in the Behavioral Sciences

  2. What is Science? • Knowledge based on observation and experimentation and validated by other scientists • Often (not always) uses an experiment to gain knowledge • Experiment: a test or trial to discover a cause-effect relationship

  3. The Scientific Method • A method for attaining knowledge based on observation and experimentation • attempt to find empirical answers

  4. Psychology as a Science:Levels of Analysis

  5. Psychology as a Science:Levels of Analysis • “Hard” vs. “Soft” science • molecular vs. molar levels • few vs. many antecedent conditions • relatively simple vs. relatively complex systems • Reductionism • explanation in terms of more molecular analysis

  6. Can science “prove” anything? • Which is a better explanation: molecular level or molar level? • Can science find “truth”? • any conclusion based on probabilistic reasoning • Scientific Method is self-correcting • use of programmatic research provides many partial answers to questions

  7. Four Goals of Psychology

  8. The Experimental Method 1. Questioning behavior 2. Generating a hypothesis 3. Designing the experiment 4. Conducting the experiment 5. Analyzing the results 6. Validating the experiment 7. Publishing the results

  9. Questioning Behavior • Generating a research question • based on observation, intuition and training • research training includes knowledge of background information and previous conclusions • what part of the question needs to be solved?

  10. Generating a Hypothesis • Hypothesis • a hunch, idea or theory that can be formally tested in an experiment • making predictions about outcome of an experiment • Operational Definition • defining something in terms of how it is measured • makes a theoretical question empirical

  11. Designing the Experiment • Experiment tests the hypothesis • Independent Variable • the variable that is manipulated by the experimenter • Dependent Variable • the variable that is measured - influenced by the independent variable

  12. Designing the Experiment • Experimental Subjects • receive the manipulation • Control Group(s) • does not receive the manipulation

  13. Designing the Experiment • Within-subjects design • the response of each subject before and after the manipulation of the independent variable is compared • all subjects receive the manipulation • Between-subjects design • experimental group receives the manipulation • compared with a control group that receives no manipulation

  14. Conducting the Experiment • Appropriate control must be maintained to ensure that data represent the original design • Want to avoid confounding variables • unknown or unidentified variable that causes the effect presumed to be caused by the independent variable

  15. Analyzing the Results • Data can be presented in graphs • Look for Functional Relationship • orderly relationship between the independent variable and the dependent variable

  16. Analyzing the Results:Statistical Tests • Begin with an assumption that the Null Hypothesis is correct • No differences exist between groups • Using statistics, can reject or accept the null hypothesis • based on the probability that differences would have occurred by chance anyway • Statistics cannot provide conclusions

  17. Validating the Experiment • Scientific results are peer-reviewed • reviewed by other scientists - often anonymously • assumes validation by consensus

  18. Publishing the Results • Following peer-review, results are published • provides information for other scientists to generate new experiments • open publication allows others to replicate and extend the original findings

  19. Non-experimentalResearch Methods • Individual differences • can be assessed through standardized tests • Results of a standardized test often produce a normal distribution

  20. The Normal Distribution

  21. The Normal Distribution • Characteristic of most biological and psychological measurements • Mean • midpoint (average) of the distribution • Standard Deviation • a measure of variability around the mean

  22. The Case Study • Intensive investigation of a single individual over time • Limited in generalizability • do the results apply to other people?

  23. Surveys • Assessing groups of individuals • often used to determine attitudes and abilities • Usually use a sample rather than an entire population

  24. Correlational Research • Finding the relationship between two variables • Often described in the scatterplot • a distribution of data points that vary in two dimensions

  25. Scatterplot Table 2.1

  26. Correlation Coefficient • A measure of the relationship between two variables • Range: +1.0 : perfect positive correlation 0.0 : no correlation -1.0 : perfect negative correlation • Coefficient usually not perfect • e.g. +0.7

  27. Positive Correlation

  28. No Correlation Math Performance Shoe Size

  29. Negative Correlation Reliability Age of Car

  30. What do Correlations mean? • Imply that two scores are related • Does not imply causation

  31. Biases • Observer Expectancy Effects • Observer Bias • the tendency of an experimenter to make biased observations • Subject Expectancy Effects • Demand Characteristics • the expectations a subject brings that may influence the outcome of an experiment

  32. Controls for Biases • Double-Blind Experiment • neither the experimenter nor the subject are aware of the treatment condition • reduces observer bias and subject expectancy • Matched-Groups Design • matching groups of subjects to control for variables that might influence outcome • e.g. subjects in both groups matched for age or sex

  33. Epidemiological Research • The use of correlational techniques for establishing relationships between behavior and health • e.g. relationship between smoking and mortality • Limited in determining causal connections • Cannot control confounding variables • e.g. genetic predispositions

  34. Inventories and Questionnaires • Tests that correlate with other skills • e.g. SAT, ACT, MCAT, WAIS • Often administered as “Paper and Pencil” tests

  35. Reliability • Extent to which repeating a test will generate a similar result • test-retest reliability • alternate-form reliability • split-half reliability

  36. Validity • The ability of a test to measure what it was designed to measure • face validity • criterion-related validity

  37. Ethical Issues • Institutional Review Boards (IRBs) review research to consider issues like: • Does the research consider the welfare of the subjects? • Is it justifiable? • Is privacy ensured? • Is the subject informed of the outcome? • can the subject give informed consent?

More Related