Psych 271 Quiz 2

Variable

something that varies or changes, i.e. academic motivation or age

Measured Variable

a variable that is observed and recorded, i.e. your hair color and whether or not you take voice lessons

Manipulated Variables

a variable you can manipulate, i.e. access to technology

Not manipulated variables

things like your age, your gender identity, and religious identity

Frequency Claim

describes a particular rate or degree of one variable. I.e. 80% of UWEC students eat chocolate daily

Association Claim

argues that two variables are related. I.e. students who eat chocolate are more likely than those who eat breakfast to be overweight

Three rules of association claim

X and Y covary, X happens before Y, and addresses alternative explanations through experimental manipulation

Causal Claim

argues that one variable is responsible for changing the other variable. I.e. skipping breakfast leads to being overweight

Construct Validity

How well the researcher measured/manipulated the variable

Statistical Validity

What is the effect size? How strong is the difference? Is it statistically significant?

External Validity

To what population or setting can we generalize this causal/association claim?

self-report, observational, and physiological

How can a conceptual variable be operationalized?

Internal Validity

Did the researchers conduct an experiment and manipulate the variable they say is the cause? Did the researchers eliminate alternative explanations for the association by randomly assigning participants to different levels of the supposed causal variable?

Self-report Measures

operationalizes a variable by recording people's answer to questions about themselves in an questionnaire or interview. I.e. asking the partner how upset they were when someone was flirting with their partner

Observational Measures

operationalizes a variable by recording observable behaviors or physical traces of behaviors. I.e. watching someone through a hidden camera to see how they react to someone flirting with their partner.

Physiological Measures

operationalizes a variable by recording biological data, such as brain activity, hormone levels, or heart rate. I.e. we could track eye movements to see how long they were looking at the confederate

Categorical

numbers represent discrete categories. Levels of the variable are qualitatively distinct. The order of the levels does not matter.

Quantitative

numbers represent movement in a direction. The variable levels are coded with meaningful numbers. The order of the levels does matter.

Ordinal Variables

are quantitative, but numbers do NOT reflect equal distances. Rank order in a race is a classic example

Interval Variables

are quantitative, and numbers do reflect equal distances…but there is no true zero. Many Likert type rating scales are an example

Ratio Variables

are quantitative, and numbers do reflect equal distances…and there is a true zero. You can multiply and divide.

Reliability

multiple measurements of the same behavior, object, or event should be positively correlated.

Consistency

Another word for reliability

Test-retest Reliability

consistent response from the same person, on the same measure, at two or more points in time.

Interrater Reliability

consistent scores from two or more raters/observers/judges

Internal Reliability

a consistent pattern of responses from the same person to two or more items. Making sure they aren't clicking random buttons.

Correlation Coefficient r

evaluates reliability of two measurements. Direction and magnitude

Cronbach's Alpha

evaluate reliability of multiple measurements. Most common with internal reliability. Direction and Magnitude

Face Validity

it looks like what you want to measure

Content Validity

the measure contains all the parts that your theory says it should

Criterion Validity

does it correlate with key behaviors and outcomes

Convergent Validity

associations that can be positive or negative but have to be strong

Discriminant Validity

weak (or zero) association between measure and unrelated constructs

accuracy

Another word for validity