Research Methods Social & Personality Study Guide

Validity vs Reliability

• validity: the best available approximation to the truth or falsity of propositions
• reliability: consistency of results
• *a measurement scale must be at least somewhat reliable in order to be valid

3 Categories of goals in empirical research

• demonstration
• causation
• explanation

Types of Validity

• internal validity: cause and effect, third variable effects
• construct validity: the extent to which a causal relationship could be generalized from the particular methods and operations of a specific study to the theoretical constructs and processes they were meant to represent
• external validity: the generalizability of findings to target populations of persons and setting
• content validity: the extent to which the elements within a measurement procedure are relevant and representative of the construct that they will be used to measure

Three Categories of Research Design

• Experimental- manipulation, random assignment, control + exp. groups
• Quasi-experimental- manipulation, no random assignment (groups cannot be randomly assigned such as gender, age, race, etc.)
• Non-experimental- no manipulation, no random assignment; often correlational

Types of Questions to Avoid

• leading questions: "lead" participants to a certain answer and discourage honest reporting (i.e. Most college students think that marijuana should be legalized everywhere... do you support legalizing marijuana?)
• double-barreled questions: ask participants two or more things at once thereby resulting in a muddled answer
• priming: setting up an individual to answer a certain way

Fixed Facto

• selected
• for its specific type in an experiment; will have an effect on participants and
• remains the same in replication of the study (i.e. meditation recording in
• meditation study)

Random Factor

• an
• outside factor that is not controlled for in an experiment; sample from a
• population of factors like it

Nominal Scale

• simplest
• form of measurement, involve assigning symbols or words to certain categories.
• Considered to be qualitative (or categorical) instead of quantitative because
• data are classified according to types, not amounts. Example of variables:
• gender, race, and personality

Ordinal Scale

• form
• of measurement that provides information about rank; however, intervals between
• each point on the scale are not equal and may be unknown. Therefore, ordinals
• scales allow you to say that one person scored higher than another, but do not
• tell you how much higher. Example: ranking students in order based on exam
• performance; would tell you the first person had the highest score, but doesn’t
• tell you what the difference between scores are

Interval Scale

• similar
• to ordinal scales, except that the intervals between points on the scale are
• equal. Example: IQ scores

Ratio Scale

• similar
• to interval scales, but they have a true
• zero (i.e. a point on the scale where zero means none, or the absence of
• the quality being assessed). Examples: income and weight