Research Methods: Chapter 5, 6, and 2

• Reliability of Measurement: are the scores consistent?
• Validity of Measurement: does it measure what it is supposed to measure
• 3 Types of Measures:

  1. Self-Report (Other-Report) Measure
  2. Observational Measure
  3. Physiological Measure
• Categorical Measures considers something grouped into categories
• Quantitative Measures have meaningful numbers
• Types of Quantitative Scales:

  • Ordinal Scale: rank order
  • Interval Scale: equal distances; no true zero
  • Ratio Scale: equal distances; true zero
• Ordering matters and is meaningful for ordinal scales
• There are 3 Types of Reliability:

  1. Test-Restest Reliability: is it the same when I give it to you again
  2. Interrater Reliability: applies to judgment on scores
  3. Internal Reliability: applies to measures with multiple items and if they agree with each other
• Correlation Coefficient (r) measures the strength of relationship between two variables
• r measures reliability

  • Test-Retest Reliability: uses r where r>.5 (Only relevant to measure things that do not change)
  • Interrater Reliability: may use r or other measures where r>.7
  • Internal Reliability: may use r
• Alpha summarizes r values in one number
• Temporal Interval is the time between measurements
• Types of Construct Validity

  • Face and Content Validity: is it a good measure
  • Criterion Validity: does it correlate with key behaviors
  • Convergent and Discriminant Validity: does the pattern make sense
• Convergent Validity refers to how closely a test is related to others with similar constructs
• Discriminant Validity has less strong relations between two measures
• Question Types for Surveys/Polls

  • open-ended
  • forced-choice
  • Likert scale
  • semantic differential format
• Poorly Worded Questions:

  • leading question: pushing people to answer in a particular way
  • double-barreled question: asking two questions at once
  • negatively worded questions: makes people confused/thrown off
• Surveys/Self-Reports are good for:

  • Demographics and Sample Descriptions
  • Subjective Experiences
• The method, structure, and wording of surveys matter
• Shortcuts People Take on Surveys:

  • Response Sets (patterns of response)
  • Acquiescence (yea-saying)
  • Fence-Sitting (middle option)
• To prevent fence-sitting, pick an even number of responses
• Faking Good is the socially desirable way of responding
• Faking Bad is a way of malingering
• A comparison group enables us to compare what would happen both with and without the thing we are interested in
• Confounds are alternative explanations
• A confederate is an actor playing a specific role for the experimenter
• Probabilistic means findings do not explain cases all the time
• 5 Examples of Biased Reasoning:

  1. being swayed by a good story
  2. being persuaded by what comes easily to mind
  3. failing to think about what we cannot see
  4. focusing on evidence we like best
  5. biased about being biased
• Availability Heuristics are things that pop up easily in our mind and tend to guide our thinking
• Present/Present Bias reflects our failure to consider appropriate comparison groups
• Confirmation Bias is the tendency to look only for information that agrees with our believe
• A bias blind spot is where we are unlikely to fall prey to other biases
• Empirical Journal Articles report the results of an empirical research study which contains details about the study's method, statistical tests used, and study results
• Review Journal Articles summarize and integrate all the published studies that have been done in one research area
• Meta-Analysis combines the results of many studies and gives a number that summarizes the magnitude or effect size of a relationship
• Abstract: a concise summary of the article that briefly describes the study's hypotheses, method, and major results
• Introduction: the first section of regular text that explains the topic of study
• Method: explains in detail how researchers construct their study
• Results: describes the quantitative end or results of the study including statistical tests used which provide tables and figures that summarize key results
• Discussion: summarizes the study's research question and methods indicates how well the results of the study supported the hypotheses and includes the importance of the study