AP Psychology Ms. Simon September 17-24, 2009 Introduction to Research Methods Hindsight Bias The tendency to believe, after learning an outcome, that one would have foreseen it Scientific Theories • Set of principles that organize and predict behaviors or events • Link observed facts • Imply hypotheses that offer testable predictions Subfields of Psychology • Basic Psychology- research • Applied Psychology- research put into practice as therapist • Psychiatry- a medical field- deals with mental disorders- prescribe medication There are three main types of research methods in psychology: Descriptive Correlational Experimental Descriptive Study: 1) Case Study- psychologists study one individual in great depth in hopes of revealing universal principles Case Study Pros • Detailed information • Unusual Cases • Inexpensive • Few ethical considerations The Problem with the Case Study: An individual may be atypical Cannot generalize results Difficult to Manipulate Variables Difficult to quantify data Naturalistic Observation • Observe subjects in natural habitats without interacting Naturalistic Observation Pros Cons Realistic No manipulat- Inexpensive Ion of variables Few ethical Observer Bias consideration Survey Method • Relies on questions answered by a group of people in interviews or questionnaires Survey Method • Experimenter must identify the population to study • Random sampling picking members from a population randomly to ensure a representative sample Survey Method Pros Cons Can gather lots Honest of data answers? Few ethical Need many considerations participants Inexpensive Wording Effects Wording Effects • In a study by AMNH, 88% of all respondents said that they were interested in plants and trees, but only 39% said they were interested in botany. • One out of five Americans (22 percent) doubted that the Holocaust had occurred. 12% said they weren’t sure What to Watch for… • Order of choices • Is the time frame specified? • How personal or direct is the wording? • Is there a cultural bias? Correlational Studies • Correlational studies assess the association between two or more characteristics of interest without ascribing causes • Is a correlational study an experiment? Correlation coefficient Example: R= + .37 Correlational Studies Correlational Studies Pros Cons Inexpensive Confounding variables Few ethical Illusory considerations correlation Time Does not Objective I mply causation Illusory Correlation • When we believe there is a relationship between two things, we are likely to notice and recall instances that confirm our belief What is the correlation? • 1) good looks/popularity • 2) self-esteem/depression • 3) brain size/intelligence • 4) money/happiness • 5) Education/length of life Correlation: determining causation There is a strong correlation between people who ate oatmeal for breakfast as a child and cancer versus people who ate Frosted Flakes for breakfast as a child Friday’s Exam: What to Study • About 40% Historical Approaches, 60% Research Methods • Study mostly from Class Discussion! • Format: Multiple Choice, One short AP exam style essay question, short answer and/or matching Research Methods Descriptive Correlational Experimental Explains behavior assess the Researcher using natural association between manipulates one observations two or more variable and characteristics of observes the effect interest on another variable 1) Case studies 1) Causation Experimental Design 2) Naturalistic 2) Illusory correlation Confounding 3) Surveys 3) Correlational Variables, double- Coefficient blind Experimental Method • Researcher manipulates one variable (independent variable) and observes the effect on another variable (dependent variable) • Allows one to show a causal relationship • Q: How is the experimental group different from the control group? • A: The experimental group receives or reacts to the independent variable and the control group does not receive the independent variable • Q: Why is a control group needed? • A: Provides baseline for comparison Confounding variable: external differences between the experimental group and the control group other than those resulting from the independent variable Confounding Variables 1) Placebo Effect experimental results caused by expectations alone Confounding Variables • Demand Characteristics- participants form an interpretation of the experiment's purpose and unconsciously change their behavior accordingly How can we control for confounding variables? How can we control for confounding variables? 1) Random Assignment method of assigning subjects to groups to minimize pre-existing differences between those groups This is an example of Between subjects design: Participants in the experimental and control group are different individuals How can be control for confounding variables? 2) Within subjects design Technique where subjects serve as control and experimental group. 3) Twin Studies: Confounding Variables • Experimenter bias- researcher’s expectations about the outcome of a study influence the results Q: How can we eliminate experimenter bias? How can we eliminate experimenter bias? 1. Multiple Experimenters 2. Double blind procedure- research design in which neither the experimenter or the participants know who is in the experimental versus control group AP Psychology Ms. Simon September 24, 2009 Experimental Statistics Do Now: • From your reading: Why do we need operational definitions? How do psychologists present data? • Frequency Distributions Statistics • Statistical significance (p) is the likelihood that the observed difference between groups results from a real difference rather than chance alone • What’s a good p value? When is data statistically significant? ) Large difference between the two means 1) Large difference between the two means When is data statistically significant? When is data statistically significant? 2) Small standard deviations But… what’s a standard deviation? A standard deviation is the degree by which a score varies from the mean You don’t need to know the equation! When is data statistically significant? When is data statistically significant? 3) Large Sample Size Mean, Median, Mode 6, 7, 8, 9, 10, 10, 10, 11, 11, 11, 11, 12, 12, 13 What’s the mode? What’s the median? Normal Distribution Skewed Data Homework: • Activity: design an experiment to see if aggression is related to violent TV watching Be sure to address random selection, random assignment, experimental versus control group, confounding variables, and how you will minimize the effects of experimental and observer bias.
Pages to are hidden for
"AP Psychology"Please download to view full document