Research Methods Midterm

Start Studying!

Terms

undefined, object

copy deck

Deception in Research: - May not be told complete details of study or misled about procedures
- Must forewarn
- Must be justified - No possible alternatives would be effective
PROS: Naturalistic Behavior
CONS: Cause Mistrust
-Have to debrief
IRB: Institutional Review Board
Effective safeguard for participants, researchers, and universities
-Determines degree of risk
-Expedited or Formal Reviews
Effective Literature Searches: - Compose narrative of search questions
- Identify seperate concepts in your question
- Use APA thesaurus
- Combine concept words in manner that best suits question
Independent Variable: -Predictor Variable
-Manipulated
-"X"
Dependent Variable: -Outcome Variable
-Observale behavior we're measuring in response to the IV
-"Y"
Confounding Variables: -Any variable that changes systematically with the IV
-Any uncontrolled extraneous variable that covaries with the IV and could provide an alternative explanation for the results
-Causes poor internal validity
Constructs vs. Variables: Construct - Not directly measurable concepts

Variables - Something we can measure
Subject Variables: -Existing characteristics serve as variables
-Subject already possesses the thing you want to measure
-Equivlalent groups is not gauranteed & could influence outcome
-Cannot draw causation
Types of Variables: Control-We do not allow to fluctuate
Random-Allow to fluctuate
Confounding-Changes systematically with the IV
Extraneous-Uncontrolled factors that are not of interest but may influence the DV
Hypothesis: -Statement contain 2 or more variables that are measurable and specify how the variables are related
-Prediction about specific events that is derived from deduction
-Educated guess about what should happen under certain circumstances
Empirical Questions: -Those that can be answered through systematic observations & experiences that characterize scientific methodology
-Precise enough to allow specific predictions to be made
MUST:
-Answerable
-Specific
-Operational Definition
-Leads to clear hypothesis
-Asks ?'s we don't know answer
-Theory Driven
Type I Error: Rejecting the Null Hypothesis when it is in fact true - Found a significant difference in your study but there really isn't one
Type II Error: Failure to reject the Null when it is in fact false - You fail to find a significant difference in your study but there really was one
Reliability: How consistent is a measure over repeated applications
-Spread of scores cluster tight
-How much error of measurement is associated with a measure
Measuring Reliability: Single Administrations
-Split-Half
-Internal Consistency
-Interrater
Multiple Administrations
-Alternate Forms
-Test-Retest
Measurement Validity: Are we measuring what we intend to measure
-Constructs must be operationalized
4 Types:
(1)Face Validity
(2)Content
(3) Criterion
(4)Construct
Face Validity (1): Does it look like its measuring what it says its measuring
Content Validity (2): Related to Face - Items reflect the area
-The more the items cover the relevant areas the more content validity
Criterion Validity (3): The degree to which a test is related to a criterion
How well does the measure predict outcomes based on info from other variables
(1)Predictive
(2)Concurrent
Construct Validity (4): Does the measure assess the construct it claims to assess
The degree to which a test is an accurate measure of the construct
(1)Convergent - how is it similar to other measures
(2)Discriminant - divergent
(3)Nomological -
Experimenter Validity: Approximation that a conclusion is true
-A set of standards by which research can be judged
(1)Statistical Conclusion Valdity
(2)Internal Valdity
(3)Construct Validity
(4)External Validity
Statistical Conclusion Validity (1): The extent to which the researcher uses statistics properly and draws the appropriate conclusions from the statistical analyses
Internal Validity (2): The degree to which an experiment is methodologically sound and confound free
Construct Validity (3): The adequacy of the definitions for the IV and DV
External Validity (4): Generalizable
Can we generalize to:
(1)Other persons/populations
(2)Other environments
(3)Other times
Experimental Validity is Best When: -There is a relationship between the cause and effect
-The relationship is causal
-You can generalize to the constructs
-You can generalize to other persons, places, & times
Threats to Internal Validity Pre-Post Tests: -History
-Maturation
-Regression to the mean
-Testing Effects
-Instrumentation Effects
Threats to Internal Validity Participants: -Sample Selection
-Attrition
-Compare Groups
Operational Definition: A definition of a concept or variable in terms of precisely described operations, measures, or procedures
-Defines a variable in terms of the techniques used to measure it
Between-Subject Design What is It: -Participants only receive 1 level of the IV
-Subject variables are almost always between-subjects
-Cross-Sectional
Between-Subject Design Advantage: Subjects enter study fresh and naive
Between-Subjects Design Disadvantages & Error: -Large # of people needed
-Time and energy
-Individual Differences: Error-whenever there is a large difference between people there will be a large amount of error
Between-Subjects Design Threats: -Differential Attrition
-Diffusion
-Compensatory Equalization
-Compensatory Rivalry
-Resentful Demoralization
Within-Subjects Design What is it: Every participant receives every condition or level of the IV
-Each group is assigned to each condition
-longitudinal studies
-repeated measures
Within-Subjects Design Advantages: -Smaller sample size
-Convenient
-Use to study limited population
-Avoids Error Variance
Within-Subjects Design Disadvantages: -Order/Sequence Effects
-Equivalent Groups
-Time related factors
-Attrition
Within-Subjects Design Error: Differences can be due to:
-IV
-Systematic Error
-Nonsystematic Error
-Random Error
Experimenter Bias: Experimenter Expectancy Effects
-experimenters may inadvertently do something that leads participants to behave in ways that confirm the hypothesis
(a)Bio-Social Effects
(b)Psycho-Social Effects
(c)Situational Effects
Participant Bias: Participants unconsciously modify their behavior to match expected results of the research
Participant Bias Hawthorne Effect: Change behavior when they know they're being studied/observed
Participant Bias Demand Characteristics: Any potential cues or features of a study that make the hypothesis obvious & influence participants to respond or behave in certain ways
(1)Good Subject
(2)Negativistic Subject
(3)Faithful Subject
(4)Apprehensive Subject
Controlling Participant Bias: -Deception
-Manipulation Check
-Use small sample
-Field Research
Single Blind Study: Only experimenter knows which condition participant is in -
Double Blind Study: Neither the experimenter nor participant know who is getting which condition
Single Factor Designs: -1 IV with 2 or more levels
-Simplest experimental design
-Between or Within Subjects
Weaknesses:
-Not impressive
Strengths:
-Simplistic
Single Factor Designs 4 Types: Between Subjects
(1)Independent Groups - randomly assigned
(2)Matched Groups - matched
(3)Nonequivalent Groups - assignment is not random
Within Subjects
(1)Repeated Measures - uses counterbalancing
Single Factor Designs Statistics: T Test - analyze mean difference
For Two Levels:
(1)t test for independent groups
(2)t test for dependent groups
More Than Two Levels:
(1)1-way ANOVA
(2)Post-Hoc Analysis
Factorial Designs: -At least 2 IV's with 2 or more levels each
-Numerical System indicates # of IV's and levels in each
-Factorial Matrix
Factorial Designs Advantages: -Main Effects
-Interactions
How do factors operate independently & together to affect behavior
Factorial Designs 4 Types: (1)Between Subject
(2)Within Subject
(3)Mixed Factorial Design - 1 factor within, 1 between
(4)SxM (SubjectxManipulated)- 1 subject variable, 1 manipulated variable
Factorial Designs Statistics: -N-way ANOVA
-N = # of IV's
-F score for each main effect and each possible interaction
-Post-Hoc Analysis
Main Effects: Mean Effect
-Comparing overall means
-The overall effect of a single IV
-How do factors influence behavior simultaneously
Interactions: -One factor modifies the effect of a second factor
-Factors are interdependent
-Occurs when the effect of 1 IV depends on the level of another IV
-When effects of a factor vary depending on the level of another factor, unique effects occur
Interactions Not/Is: Not an Interaction if:
-Main effects are additive
-You can predict cell means
Is an Interaction if:
-Main effects are not additive
-Extra means differences not explained by main effects
-Below .05 is significant
Correlations: -A numerical relationship between 2 variables
-When the goal of descriptive research is to test a hypothesis about the relationship between variables
-No manipulation of variables
-Implies Prediction
-Predictor Variable
-Criterion Variable
Correlations 3 Things To Consider: (1)Directionality
-Positive
-Negative
-Curvilinear
-No Relationship
(2)Form
-Linear
-Monotonic
(3)Strength
Small = .10-.29
Moderate = .30-.49
Large = .50-1.00
Correlations Strength: -Study what exists
-Variables that cannot be tested
-Study many variables
-High external validity
Correlations Weaknesses: -Directionality Problem- Does A cause B or does B cause A

-Third Variable-Another variable may be contributing to effect

Start Studying!

Deck Info

Number of cards 58