Research Methods Exam 2

Card Set Information

Research Methods Exam 2
2014-11-10 01:51:35
suny geneseo research methods

exam 2 material
Show Answers:

  1. What are the components of a between-subjects design?
    • Making comparisons between 2 or more groups (usually assign subjects to a group)
    • Need for equivalent groups (clarify the effect of the IV)
  2. What are possible methods of creating equivalent groups?
    • Random Assignment
    • Block Randomization
    • Matching Strategy
  3. What are the components of random assignment?
    • Method for creating equivalent groups
    • Once subjects are selected, there's an equal chance of being assigned
    • Evenly distributed individual differences
    • Differences between groups are a result of IV, not EV
  4. What are the components of block randomization?
    • Method for creating equivalent groups
    • Defines order of assignment
    • Groups end up with equal numbers
  5. What are the components of matching strategy?
    • Method for creating equivalent groups
    • Ensures that groups are equivalent on the factor you're concerned about
    • Subjects are matched on relevant factor (matching variable)
    • Once matched, then randomly assigned
  6. What are the components of a within-subject design?
    • Making comparisons by looking at individuals across multiple conditions
    • Comparisons within subjects
    • Repeated measures design
    • Rather than recruit different groups, every subject experiences each of the conditions
  7. What are the advantages and disadvantages of a within-subject design?
    • Advantage: groups are equivalent because there's only one group
    • Disadvantages: sequence effects (progressive effects and carryover effects)
  8. What are the components of sequence effects?
    Once a participant has completed the first part of a study, the experience or altered circumstances could influence performance in later parts of the study
  9. What are the components of progressive effects?
    Sometimes repeated trials produce gradual fatigue or boredom, and performance gradually declines from trial to trial
  10. What are the components of carryover effects?
    In a study with 2 basic conditions, experiencing the first condition before the second might affect the person much differently than experiencing the second before the first
  11. What are the possible methods of controlling sequence effects?
  12. What are the two general categories of counterbalancing?
    • Testing once per condition
    • Testing more than once per condition
  13. What are the components of counterbalancing when testing once per condition?
    • Complete Counterbalancing
    • Partial Counterbalancing
  14. What are the components of complete counterbalancing?
    • Every possible sequence will be used at least once
    • The total number of sequences needed can be determined by calculating X! (X factorial, where X is the number of conditions)
    • Subjects in this study would then be randomly assigned to a sequence
  15. What might be an issue with complete counterbalancing?
    As the number of levels of the IV increases, the possible sequences needed increase dramatically
  16. What are the components of partial counterbalancing?
    • It can be accomplished by sampling from the complete set of all possible orders
    • Or by randomizing the order of conditions for each subject (balanced Latin Square)
  17. What is the Latin Square Strategy?
    • Type of partial counterbalancing
    • Subset of possible sequences
    • 2 things are true: 
    • -every condition occurs equally often in each position
    • -every condition precedes an follows every other condition exactly once
    • Allows even distribution of sequence effects
  18. What are the components of counterbalancing when testing more than once per condition?
    • Reverse Counterbalancing
    • Block Randomization
  19. What are the components of reverse counterbalancing?
    • The experimenter presents the conditions in one order, and then presents them again in the reverse order
    • If the researcher wants the participant to perform the task more than once, this sequence could be repeated as many times as necessary
  20. What is a disadvantage of reverse counterbalancing?
    There's a possibility that participants can predict what is coming next, especially if the reversals occur several times
  21. What are the components of block randomization?
    • The basic rule is that every condition must occur once before any condition can be repeated
    • Within each block, the order of conditions is randomized
    • This strategy eliminates the possibility that participants can predict what is coming next
  22. What is a cross-sectional study?
    • Takes a between-subjects approach
    • A design in which age is the IV and different groups of people are tested; each group is of a different group
  23. What is a longitudinal study?
    • Takes a within-subject/repeated-measures approach
    • Age is the IV
    • A single group of subjects is studied over time
  24. What is a potentially serious difficulty with cross-sectional studies?
    Cohort effects
  25. What are cohort effects?
    • A cohort is a group of people born at the same time
    • Cohort effects can reduce the internal validity of cross-sectional studies because differences between groups could result from the effects of growing up in different historical eras
  26. What is a potential problem with longitudinal studies?
  27. What is attrition?
    • A threat to the internal validity of a study
    • Occurs when participants fail to complete a study
    • Those finishing the study may not be equivalent to those who started it
  28. What is a cohort sequential design?
    • In such a study, a group of subjects is selected and retested over time
    • Different cohorts are continually being retested
  29. What are the 2 types of bias in experiments?
    • Experimenter Bias
    • Participant/Subject Bias
  30. What can experimental bias be influenced by?
    • Knowing the hypotheses
    • Knowing the group membership
  31. What are research protocols?
    • A detailed description of the sequence of events in a research session
    • Used by an experimenter to ensure uniformity of treatment of research participants
  32. What are the solutions for experimenter bias?
    • Experimenter blindness
    • Standardized procedures
  33. What are the components of experimenter bias?
    • Double blind procedure
    • Neither the experimenter nor the participants are told the hypotheses and information on group membership
  34. What are the components of standardized procedures?
    Treat each subject the same way by following the script
  35. What can influence participant/subject bias?
    • Hawthorne effect
    • Demand characteristics
    • Social desirability (evaluation apprehension)
  36. What is the Hawthorne effect?
    A form of participant bias in which a participant's behavior is influenced by the mere knowledge of being in an experiment and therefore important to the experimenter
  37. What are demand characteristics?
    Features of the experimental design or procedure that increases the chances that participants will detect the true purpose of the study
  38. What is social desirability bias?
    • A type of response bias in survey research
    • Occurs when people respond to a question by trying to put themselves in a favorable light
  39. What is evaluation apprehension?
    A form of anxiety experienced by participants that leads them to behave so as to evaluated positively by the experimenter
  40. What are solutions to participant bias?
    • Placebo control group
    • Manipulation check
    • Field research
  41. What is a manipulation check?
    • In debriefing, a procedure to determine if subjects were aware of a deception experiment's true purpose
    • Also a procedure that determines if systematic manipulation have the intended effect on participants
  42. What is field research?
    Research that occurs in any location other than a scientific laboratory
  43. What are single factor designs?
    • Experimental designs with a single independent variable
    • Composed of four basic research designs (independent groups, matched groups, nonequivalent groups / ex post facto, repeated measures)
  44. What does an independent groups design consist of?
    • A between-subjects design
    • Manipulated IV
    • At least 2 groups to which subjects are randomly assigned
  45. What does a matched groups design consist of?
    • Between-subjects design
    • Manipulated IV
    • At least 2 groups of participants
    • Subjects are matched on some variable assumed to affect the outcome
    • Random assignment
  46. What does a nonequivalent groups / ex post facto design consist of?
    • Between-subjects design
    • At least 2 groups of participants
    • Uses a subject variable
    • Creates nonequivalent groups
  47. What does a repeated measures design consist of?
    • Within-subjects design
    • Participants are tested in each of the experiment's conditions
    • Fewer participants
    • More sensitive to small differences between means
    • Typically uses counterbalancing to control for sequence effects
  48. What should be something to look out for in an independent groups design?
    Outlier - in a data set, a data point so deviant from the remaining points that the researcher believes it cannot reflect reasonable behavior and its inclusion will distort the result; often considered a score more than three standard deviations from the mean
  49. What is the defining feature of a two-level independent group design?
    Random assignment of participants to groups
  50. What are the important control procedures that can be used to minimize human error and bias?
    • Extensive training for researchers
    • Double blind procedures
    • Interobserver reliability
  51. What is interobserver reliability?
    The degree of agreement between two or more observers of the same event
  52. When do researchers often use two-level matched group design?
    • Small number of subjects
    • They're concerned that some attribute of these subjects could affect the outcome
    • They have a good way of measuring that attribute
  53. What is a methodological concern in ex post facto designs?
    External validity - the extent to which the findings of a study generalize to other populations, other settings, and other times
  54. What are the methods used to analyze single-factor, two-level designs?
    • Nonparametric tests
    • t-tests
  55. What are nonparametric tests?
    • A test for homogeneity of variance
    • It can be used if the standard deviation of one group is significantly larger than the standard deviation of the other group
    • Common example: Mann-Whitney U test
  56. What are the two varieties of t-tests for comparing two sets of scores?
    • Independent samples t-test
    • Dependent samples t-test
  57. Which designs should use the independent samples t-test?
    • Independent groups design
    • Ex post facto design
  58. Which designs should use the dependent samples t-test?
    • Matched groups design
    • Repeated-measures design
  59. What is an advantage to single-factor multilevel designs?
    Nonlinear effects - outcomes that do not form a straight line when graphed
  60. What are the three choices in deciding how to present the data?
    • Sentence form (can make for tedious reading as amount of data increases)
    • Table of results
    • Graph
  61. What are the types of graphs and when is it appropriate to use them?
    • If continuous variable: line graph preferred; bar graph acceptable
    • If discrete variable: use a bar graph; line graph is inappropriate
  62. How should single-factor, multilevel designs be analyzed?
    One-Way Analysis of Variance (One-Way ANOVA)
  63. What is required to determine precisely where the significance lies in an ANOVA test?
    Post hoc analysis
  64. Which designs should use the one-way ANOVA for independent groups?
    • Multilevel independent groups design
    • Multilevel ex post facto design
  65. Which designs should use the one-way ANOVA for repeated measures?
    • Multilevel matched groups design
    • Multilevel repeated-measures design
  66. Which control groups are the most informative when used in the context of multilevel experimental designs?
    • Placebo Control Group Designs
    • Wait List Control Group Designs
    • Yoked Control Group Designs
  67. What kind of design would a study with a placebo control group use?
    • If subjects are randomly assigned to groups: Independent groups, single-factor, multilevel design
    • If subjects were first matched on some variable: Matched groups, single-factor, multilevel design
  68. What kind of design would a study with a waiting list control group use?
    Independent groups, single-factor, multilevel design
  69. What kind of design would a study with a yoked control group use?
    Matched groups, single-factor, multilevel design
  70. What is a yoked control group?
    Control group in which the treatment given a member of the control group is matched exactly with the treatment given a member of the experimental group
  71. What is a factorial design?
    Involves any study with more than one IV
  72. What are the two results that can occur in factorial studies?
    • Main effects
    • Interactions
  73. What are main effects?
    • The overall effect of a single IV
    • The difference between the means of the levels of any one IV
    • Involves combining all of the data for each of the levels of that factor
    • Can be seen using a factorial matrix
  74. What are interactions?
    • In a factorial design, occurs when the effect of one IV depends on the level of another IV
    • Can be seen using a line graph (parallel lines = no interaction; non parallel lines = interaction)
  75. What are the components of a mixed factorial design?
    • At least one variable must be tested between subjects and manipulated
    • At least one variable must be tested within subjects
  76. What are the components of a P x E design?
    • All between-subject IV
    • Some IV are manipulated variables and some are subject variables
  77. What are the components of a mixed P x E factorial design?
    • All between-subject IV
    • Some IV are manipulated variables and some are subject variables
    • Includes both between-subjects and within-subjects factor
    • The "E" (environment) is a within-subjects variable