Research Method-2019092310154512345.pptx

RESEARCH METHOD

1. 2 Scientific Methods in Psychology

2. Psychological Science Psychology differs from other scientific fields. One way is its history. Other sciences began gradually from the work of amateurs. Psychology, in contrast, began as a deliberate attempt to start a new science. Another issue is ethics. Psychologists dealing with people have stringent limits.

3. Gathering Evidence A scientific study goes through the following sequence of steps: 1. Hypothesis – a clear predictive statement Method Results Interpretation

4. Figure 2.1 ▲ Figure 2.1 An experiment tests the predictions that follow from a hypothesis. Results either support the hypothesis or indicate a need to revise or abandon it.

5. Replicability Replicable results – data that anyone can obtain, at least approximately, by following the same procedures Meta-analysis – procedure of taking the results of many experiments, weighting each one in proportion to the number of participants, and determining the overall average effect

6. Evaluating Scientific Theories Theory – an explanation or model that fits many observations and makes accurate predictions

7. General Research Principles Problems faced by psychological researchers: Sampling A group of people being studied might be unusual in some way. Behavior of participants People who know they are in a research study often behave differently just because they are being observed.

8. Operational Definitions Operational definition – a definition that specifies the operations (or procedures) used to produce or measure something, ordinarily a way to give it a numerical value

9. Table 2.1 Types of Samples Sample Individuals Included Advantages and Disadvantages Convenience sample Anyone who is available Easiest to get, but results may not generalize to the whole population Representative sample Same percentage of male/female, white/black, etc., as the whole population Results probably similar to whole population, although sample may be representative in some ways but not others Random sample Everyone in population has same chance of being chosen Difficult to get this kind of sample, but it is the best suited for generalizing to the whole population Cross-cultural sample People from different cultures Difficulties include language barriers, cooperation problems, etc., but essential for studying many issues

10. Figure 2.6 ► Figure 2.6 In a naturalistic study, observers record the behavior in a natural setting. Here noted biologist Jane Goodall records her observations on chimpanzees. By patiently staying with the chimps, Goodall gradually won their trust and learned to recognize individual animals.

11. Case Histories Case history – a thorough description of someone, including abilities and disabilities, medical condition, life history, unusual experiences, and whatever else seems relevant

12. Surveys Survey – a study of the prevalence of certain beliefs, attitudes, or behaviors based on people’s responses to specific questions Getting a random or representative sample is especially important with surveys. The seriousness of those being interviewed and the wording of questions affect survey results. Surveyor bias happens when an organization words the questions of a survey to encourage the answers they hope to receive.

13. Correlational Studies (slide 1 of 2) Correlation – a measure of the relationship between two variables A variable is anything measurable that differs among individuals, such as age, years of education, or reading speed. The Correlation Coefficient Correlation coefficient – a mathematical estimate of the relationship between two variables Scatter plot – graph in which each dot represents a given individual, with one measurement for that individual on the x -axis (horizontal) and another measurement on the y -axis (vertical)

14. Figure 2.8 ◄ Figure 2.8 Each dot represents one country. The value along the x -axis indicates the amount of seafood that an average person eats in a year. The value along the y -axis indicates the probability of developing major depression. As seafood consumption increases, the probability of depression decreases.

15. Figure 2.9 ▲ Figure 2.9 In these scatter plots, each dot represents measurements of two variables for one person. (a) Scores on first test and scores on final exam (correlation = +0.72). (b) Times absent and scores on final exam (correlation = –0.44) (c) Last three digits of Social Security number and scores on final exam (correlation = –0.08).

16. Correlational Studies (slide 2 of 2) Illusory Correlations Illusory correlation – an apparent relationship based on casual observations of unrelated or weakly related events Sometimes people think they see a correlation that doesn’t really exist. People see what they expect to see (e.g ., sugar and activity levels ) Correlation ≠ Causation A correlation indicates how strongly two variables are related to each other. It does not tell us why they are related.

17. Experiments Experiment – a study in which the investigator manipulates at least one variable while measuring at least one other variable Independent variable – the item that an experimenter changes or controls Dependent variable – the item that an experimenter measures to determine the outcome Experimental group – the group that receives the treatment that an experiment is designed to test Control group – a set of individuals treated in the same way as the experimental group except for the procedure that the experiment is designed to test Random assignment – a chance procedure, such as drawing names out of a hat, to make sure that all participants have the same probability of being assigned to a given group

18. Table 2.2 Comparison of Five Methods of Research Observational Studies Case Study Detailed description of single individual; suitable for studying rare conditions Naturalistic Observation Description of behavior under natural conditions Survey Study of attitudes, beliefs, or behaviors based on answers to questions Correlation Description of the relationship between two variables that the investigator measures but does not control; determines whether two variables are closely related but does not address questions of cause and effect Experiment Determination of the effect of a variable controlled by the investigator on some other variable that is measured; the only method that can inform us about cause and effect

19. Reducing the Influence of Expectations Experimenter Bias and Blind Studies Experimenter bias – the tendency of an observer (unintentionally, as a rule) to misperceive the results Blind observer – someone who records data without knowing the researcher’s predictions Single-blind study – procedure in which either the observer or the participants are unaware of which participants received which treatment Double-blind study – research in which both the observer and the participants are unaware of which participants received which treatment Demand Characteristics Demand characteristics – cues that tell participants what is expected of them and what the experimenter hopes to find

20. Problems with a Before-and-After Study Researchers give children language training and find that their language skills improve over the next few months @ They provide therapy for patients with depression and find that many become gradually less depressed. A before-and-after study often leads to results that are hard to interpret. It is better to compare the results for different groups.

21. Descriptive Statistics Descriptive statistics – mathematical summaries of results Three ways of representing the central score: 1. Mean – the sum of all the scores divided by the total number of scores 2. Median – middle score in a list of scores arranged from highest to lowest 3. Mode – the score that occurs most frequently

22. Inferential Statistics (slide 1 of 3) Inferential statistics – statements about a large population based on an inference from a small sample Certain kinds of statistical tests determine the probability that purely chance variation would achieve a difference as large as the one observed. The result is summarized by a p (as in probability) value. The smaller the p value, the more impressive the results.

23. Inferential Statistics (slide 2 of 3) The usual agreement is that, if p is less than 0.05, researchers consider the results statistically significant or statistically reliable. Statistically significant (or statistically reliable ) results – results that chance alone would be unlikely to produce Statistical significance depends on three factors: Size of the difference between the groups Number of research participants in each group Amount of variation among individuals within each group

24. Replicability Issues Because researchers generally publish only the results that look impressive, an unknown number of the reported results may have arisen by accident. Psychologists are becoming more interested in trying to replicate results.

25. Ethical Concerns with Humans Research on human participants should not proceed until the participants have given their informed consent. Informed consent – a statement that a participant has been told what to expect and agrees to continue Psychologists try to minimize risk to their participants, but they sometimes face difficult ethical decisions, such as temporary deception.

26. Ethical Concerns with Nonhumans Researchers use nonhumans in the following situations: If they want to control aspects of life that people will not let them control If they want to study behavior continuously over weeks or months (longer than people are willing to participate) If the research poses health risks Animal research is controversial. Animals cannot give informed consent.