Research Methods in Psychology Chapter 3

variable

something that varies, must have at least two levels (values)

constant

something that does not vary (within our study) it only has one level

conceptual variable

an abstract entity that we know exists, but is nontangible, often talked about in an abstract way

conceptual definition

theoretical definition that we give to the conceptual variable

operational definition

a particular way a conceptual variable is defined that allows it to be measured or manipulated with a tangible metric

measured variable

something that we are measuring as it naturally occurs, a variable whose levels are simply observed, and then recorded

manipulated variables

a variable a researcher controls or influences, usually by assigning participants to a particular level of a variable

claim

an argument someone is trying to make

frequency claims

describes a particular rate or degree of a single variable, always measured

association claims

argue that one level of a variable is likely to be associated with a particular level of another variable

positive association

as one increases the other increases, or as one decreases, the other decreases

negative association

as one increases the other decreases, or, as one decreases the other increases

zero association

no relationship between variables (or an insignificant relationship)

causal claims

argues that one variable is responsible for changes in another variable

validity

the appropriateness of a conclusion or a decision; reasonable, accurate, justifiable

internal validity

a study’s ability to rule out alternative explanations for a causal relationship between two variables

covariance

the measured variable (outcome variable) must change as the causal variable changes

temporal precedence

the causal variable must come first, and the outcome variable after

internal validity

alternative causal explanations must be ruled out

construct validity

how well a variable is measured or manipulated

external validity

how well we can generalize the results of this study to other people or contexts

statistical validity

the extent of a study’s statistical conclusions are precise, reasonable, and replicable

point estimate

an estimate of a value in the population

confidence interval

a range designed to include the true population value a high proportion of the time

observational measures

record observable behaviors or physical traces of behavior

self-report measures

operationalize behavior by recording people’s answers to questions about themselves

physiological measures

record biological data

nominal scale

numbers serve only as labels, no numerical meaning, describes categories

ordinal scale

ranking the order of data, differences between values are not equal

interval scale

ordered scale with equal intervals throughout, no meaningful zero

ratio scale

ordered scale with equal intervals throughout, contains a meaningful zero

reliability

the consistency of the measuring technique, how consistent a measurement is, or whether the results can be reproduced under the same conditions

test-retest reliability

consistency of responses on the same measure over time

internal reliability

the degree that all items (or questions) in a scale asses the same construct

Cronbach’s alpha coefficient

correlation based on statistic that measures a scale’s internal reliability

interrater reliability

the degree to which two or more observers give consistent ratings of a set of targets

criterion-related validity

does the measure allow you to distinguish people based on a particular behavioral outcome?

concurrent validity

your measure and the behavioral outcome measure are administered at the same time

predictive validity

your measure is administered before the behavioral outcome measure is taken

convergent validity

comparing our new measures to another measure. Does our measure positively correlate with other measures that are assessing similar constructs?

discriminant validity

does our measure only weakly relate (or have no relationship) to other measures that have little/nothing to do with our construct?