Exam #3 Flashcards
4 levels of measurement
Nominal: categorizing data in exclusive (groups, ethnicity, city of birth)
Ordinal: data can be ranked in order but no order between categories
Interval: equal intervals between data point but NO TRUE ZERO POINT
Ratio: equal interval between data points but HAVE A TRUE ZERO POINT
Positive Relationship
dependent variable increases as the independent increases * both variables move in the same direction*
Negative relationship
two variables move in the opposite direction
Curvilinear relationship
two variables where as one variable increases, so does the other variable, but only up to a certain point
Mediating Variable
explains the process through which two variables are related
Moderating variable
affects the strength and direction of that relationship
Categorical variables such as ethnicity, race, religion, favorite colors, health status, or stimulus type,
Quantitative variables such as age, weight, height, income, or visual stimulus size.
Concept
An image in one’s mind that represents an idea, an item, an event, a behavior, or a person
Self-reports
are often used as a way of gaining participants’ responses in observational studies and experiments.
Direct Observation
physical characteristics-things we can observe of the person being interviewed
(sex, skin color)
Validity
measures the correct thing
Construct validity
how well a test measures the concept it was designed to evaluate.
Criterion related validity
when it has demonstrated its effectiveness in predicting criteria, or indicators, of a construct.
Reliability
which research method produces stable and consistent results.
Systematic error
is a consistent or proportional difference between the observed and true values of something
Test-retest reliability
administering the same test twice over a period of time to a group of individuals.
Internal consistency reliability
Consistency of items in a test or questionnaire, similar items should provide consistent information if they are measuring the same thing.
Interobserver Reliability
two observers independently observe. Can check the degree of the relationship, usually measured at the same time.
Inter-rater Reliability
a way to measure the level of agreement between multiple raters or judges.
Content Validity
evaluates how well an instrument (like a test) covers all relevant parts of the construct it aims to measure.
Face Validity
test appears to measure what it is intended to measure.
Parallel forms reliability
conducting assessment of the same phenomena with the same sample group
Random Error
Errors that arise from chance that lead to an incorrect estimate of association
Social desirability bias
Tendency for respondents to reply to questions in a manner than is viewed as socially acceptable.
Cultural Bias
Interpreting and judging other cultures by the standards of your own culture
4 alternative forms of Measurement
Broad categories for operationalizing variables
Written Self Reports
Interviews
Direct Behavioral Observation
Examining Available Records
How to Avoid measurement Error
Try to use neutral language and concepts that respondents will understand.
Ask for advice from colleagues to identify any biases you may have missed.
Test your questioniare.
Make sure the individuals you use to conduct interviews or rate behaviors are capable of performing their duties consistently.
interview schedule
interview list of questions
interview guide
list of topics to be asked
contingency questions
answered only if respondent gives certain answer
(have you ever been married? If yes …)
Open ended question
respondent provides their own answer
Exhaustive
includes all possible responses (“other”)
Close Ended
respondents asked to select answer from among a list provided
Double barreled questions
composed of more than two possible issues or topics but can only have one answer
(ex:do you believe campus parking and housing is a problem on campus)
Guidelines for asking Questions
Make Items Clear
Avoid double barreled questions( no “and” & agree and disagree)
Respondents must be competent to answer
Respondents must be willing to answer
Short Items are best
Questions should be relevant
Avoid NO or NOT
Questions should be culturally sensitive
Likert scaling
measurement technique that is based on the use of standardized response categories
(strongly agree, agree, disagree, strongly disagree)
Matrix questions
standardized set of close ended response categories are used in answering questionnaire items