Research Methods in Psychology: Terms and Definitions, Quizzes of Psychology

Download Research Methods in Psychology: Terms and Definitions and more Quizzes Psychology in PDF only on Docsity! TERM 1 Naturalistic Observations DEFINITION 1 Goal --> To provide a complete and accurate picture (of behaviors, events, setting, etc) rather than to test hypotheses formed prior to the study - It analyzes observations and forms hypotheses "ad hoc", or as they are happening - Important issue --> how do you categorize events...w/out operational definitions how do you ensure observations are objective? -Participation/Concealment: participant or non-participant? - Robert Cialdini's studies of persuasion - EX: Low Ball Lab Study (24% full disclosure vs 53% commit first) TERM 2 Systematic Observations DEFINITION 2 Goal --> careful observation of one or more behaviors in a particular setting - Requirements: 1) interested in only specific behaviors, 2) quantifiable, 3) hypothesis-driven - Methods, components, issues --> 1) Coding system: how to measure behavior? (need recording equipment) 2) Reliability: inter-rater reliability of coding 3) Sampling: what segment of time to record - Limitations: 1) Reactivity: all these careful methods used to record and code the behavior can also affect behavior 2) Results may depend on the coding system and how the behavior is operationalized EX: Genital diddling study in baboons (+ correlation btw amount of time spent together and grooming/ the frequency of intense greetings) TERM 3 Case Studies DEFINITION 3 Goal --> to provide detailed descriptions of the behavior of an individual, usually in rare circumstances - Most case studies are qualitative vs. quantitative - Limitations: Conclusions drawn are often "post-hoc" (after the fact), difficult to determine causality - Examples: psychobiography, patients - EX: Patient Study - Paul Broca Goal of study --> to link brain activity to behavior (Modularity of Function) Looked at: Broca's Area --> language production TERM 4 Archival Research DEFINITION 4 Nature --> quantitative - Methods, components, issues: 1) Mining data = 3 types (statistical records, survey archives, written records) 2) Content analysis: devise coding systems that raters can use to quantify the data - Limitations: 1) The records can be difficult to obtain 2) Researcher cannot always be sure of the accuracy of the data - EX: Homicide Data (Martin Daly + Margo Wilson, patterns of homicide) - Used data from police departments/other governmental records: 1) reasoned that homicides are objective and serious enough that accurate records are likely to be kept 2) Official records can be obtained, at least w/ cooperation of police TERM 5 Reactivity DEFINITION 5 Carrying out the experiment and using careful methods may affect behavior during experiment b/c subject is being watched TERM 6 Costly Signal Theory DEFINITION 6 Signals can be regarded as more reliable and honest if they are more costly, expensive, and hard to fake TERM 7 Survey Research: Writing Questions (4) DEFINITION 7 1) Make the questions clear and concise (check grammar/spelling) - Keep it simple; avoid jargon and technical terms 2) Make sure the question is directly relevant to the hypothesis 3) Avoid loaded or leading questions 4) Avoid double-barreled questions TERM 8 Halo Effects DEFINITION 8 Avoid associating a position with a person so that responses may reflect feelings about the person rather than the position (President Bush - Osama Bin Laden threat) TERM 9 Double-barreled Questions DEFINITION 9 "Do you believe that airbags are unsafe AND expensive?" TERM 10 Open-ended question DEFINITION 10 Respondents answer in their own words ("What is the most important thing for children to prepare them for life?) Adv = Can discover unexpected answers, doesnt restrict answers Diasdv = Costly and time-consuming to code, respondents may not submit answers of interest to the experimenter TERM 21 Response Rate DEFINITION 21 Rate at which participants respond to partake in a study TERM 22 Selection Bias DEFINITION 22 Results when sampling frame is not representative of the population of interest (poor representation in Literary Digest Poll) TERM 23 Non-response Bias DEFINITION 23 When, say, 25% of 10 million people return surveys there exists a non-response bias. Non-respondents may have different perspectives than respondents TERM 24 Simple Random Sampling DEFINITION 24 Each member of the population has an equal chance of being included (probability sampling) TERM 25 Sampling Frame DEFINITION 25 The actual population of individuals from which a sample is drawn TERM 26 Stratified Random Sampling DEFINITION 26 The population is divided into strata (subgroups) followed by random sampling from each stratum (probability sampling) TERM 27 Cluster Sampling DEFINITION 27 Clusters of individuals are identified, then clusters are randomly selected. All individuals within a selected cluster are sampled. (probability sampling) TERM 28 Haphazard "convenience" sampling DEFINITION 28 Subjects are chosen in a haphazard way, usually based on whoever is available (nonprobability sampling) Ex: Standing outside the UCEN and testing those who pass TERM 29 Quota Sampling DEFINITION 29 A sample is chosen to reflect the numerical composition of various subgroups in a population (nonprobability sampling) EX: 25 people each --> Freshmen, Soph, Juniors, Seniors TERM 30 Posttest Only Design DEFINITION 30 IV variable is tested "posttest" as in after the experiment is done "Can exposure to females increase males' testosterone?" Limitations: 1) Posttest only for measuring testosterone responses was limited in sample size b/c rats had to be killed 2) Some studies failed to find significant effects of exposure to females using Posttest only designs 3) Many sources of variability in testosterone may have been masking the effect (pulsability of testosterone, circadian rhythms, individual differences) TERM 31 Pretest-Posttest Design DEFINITION 31 Testing the IV both before and after the experiment (test testosterone on rats before and after) Adv = For small sample sizes, can ensure groups are equal - Can measure changes within an individual instead of only across group as a whole (experimental manipulation may have different effects depending on different individuals) - Can assess effect of a manipulation in spite of "mortality" effects Disadv = Expensive - May affect the Posttest results TERM 32 Solomon 4-Group Design DEFINITION 32 Test for effects of pretest: 1) Posttest only control group 2) Posttest only experimental group 3) Pretest-Posttest control group 4) Pretest-Posttest experimental group TERM 33 Repeated Measures Design DEFINITION 33 Each participant takes part in each experimental condition (bloodletting) Participants --> control --> experimental Participants --> experimental --> control Adv = Since it compares each individual to themselves, it decreases effect of subject variability and makes effects of IV easier to detect Disadv = Order effects TERM 34 Matched Pairs Design DEFINITION 34 -Subjects are matched on a characteristic related to the DV and then randomly assigned to conditions -Technique to ensure that experimental groups are equal before being subject to the experimental manipulation - Usually used with small sample sizes EX: Researchers want to test the hypothesis that computerized tutorials will improve math performance more than written textbooks Adv = Decreases subject variability (similar to repeated measures) Disadv = Cost of identifying and measuring matching variable - procedure is worthless if matching variable is not related to the dependent measure - May be unnecessary with large enough sample size TERM 35 Complete Counterbalancing DEFINITION 35 Present the different conditions in every possible order 2 conditions (control + experimental)...then there are only 2 possible orders EX: randomized blocks