Psyc012 Good Measurement And Surveys

Conceptual definition

The first step in measuring happiness, defining the concept in abstract terms.

Operational definition

The next step in measuring happiness, specifying how the concept will be measured.

Self-report measure

A method of measuring happiness through questionnaires.

Single item

A self-report measure asking, 'How happy are you?'

Multi-item scale

A self-report measure that includes multiple questions to assess happiness.

Satisfaction with Life Scale

A specific multi-item self-report measure developed by Diener.

Subjective Happiness Scale

A specific multi-item self-report measure developed by Lyubomirsky.

Observational measure

A method of measuring happiness by observing behavior.

Physiological assessment

A method of measuring happiness through biological indicators.

Nominal scale

A scale where values are just labels or categories, e.g., 'Are you happy? (1 = yes, 0 = no)'.

Ordinal scale

A scale that involves rank ordering, e.g., 'Rank order the happiness of your closest friends.'

Interval scale

A scale with equal differences between numbers but no true zero point, e.g., 'How happy are you? (1 = not at all...7 = very)'.

Ratio scale

An interval scale that includes a true zero, e.g., 'How many times did you feel happy today?'.

Validity

The degree to which a measure accurately represents the construct being measured.

Reliability

The degree to which a measure is consistent, stable, and dependable.

Correlation coefficient (r)

A measure of the strength and direction of association between two variables.

Test-retest reliability

Consistency of a measure over time, relevant when the construct should be stable.

Inter-rater reliability

Consistency of a measure across different observers.

Internal reliability

Consistency across scale items in self-report measures that assess the same construct.

Observed happiness

A measure of happiness assessed through observation.

Trait-level happiness

A stable measure of happiness assessed over time.

Cronbach's alpha

A statistic used to assess internal reliability, wanting it to be greater than .70.

Subjective happiness scale range

Ranges from .79 to .94.

Construct validity

How well did the researcher operationalize each variable?

Face validity

Does the measure seem plausible given the construct of interest, usually determined by experts.

Content validity

Does the measure capture all parts of the construct of interest, also determined by experts.

Criterion validity

Is the measure related to relevant objective outcomes, determined by correlations between scores on your measure and objective outcomes.

Known groups paradigm

A method where groups known to be different are given the measure to assess validity.

Convergent validity

Is the measure related to other measures that assess similar constructs, determined by correlations with other subjective, related measures.

Discriminant validity

Is the measure NOT related to other measures that assess different constructs, looking for weak correlations.

Categorical (nominal scale)

A type of measurement that classifies data into distinct categories.

Quantitative (interval, ordinal, ratio)

Types of measurements that involve numerical values and can be measured on a scale.

Objective measures

Data collected through observable and measurable methods.

Subjective measures

Data collected through personal opinions, interpretations, feelings, or beliefs.

Self-reports

Data collected from individuals about their own thoughts, feelings, or behaviors.

Observational measures

Data collected through observing subjects in their natural environment.

Physiological measures

Data collected through biological or physical assessments.

What is a key consideration when writing questions for self-report measures?

High construct validity involves many small decisions.

What are open-ended questions in self-report measures?

Questions that allow participants to respond in their own ways, such as 'Tell us about your views on legalizing marijuana.'

What is a primary advantage of open-ended questions?

They allow participants to express what is important to them.

What is a disadvantage of open-ended questions?

They may not cover the topics the researcher cares about and can be time-consuming.

What are closed-ended questions?

Questions that provide specific rating dimensions of interest, such as 'Are you in favor of legalization?'

What is a forced choice question?

A type of closed-ended question where participants choose between two options, e.g., 'Yes or No.'

What is a Likert scale?

A closed-ended question format that asks participants to rate their agreement on a scale, e.g., 'I favor legalizing marijuana.'

What is a semantic differential scale?

A closed-ended question format that asks participants to rate a concept on a scale between two opposing adjectives, e.g., 'Legalizing marijuana is... Foolish to Wise.'

What should be avoided when phrasing questions?

Leading questions, double-barreled questions, and negatively worded questions.

What is a leading question?

A question that makes one answer seem clearly better than another, e.g., 'Do you think it's about time for marijuana to finally be legalized?'

What is a double-barreled question?

A question that asks two questions at once, e.g., 'Do you think that legalizing marijuana will decrease the crime rate and lead to a happier, healthier population?'

Why should negatively worded questions be avoided?

They make questions more cognitively difficult, e.g., 'I do not believe that marijuana should not be legalized.'

How can question order affect self-report measures?

Responses on earlier questions can influence how later questions are interpreted.

What is acquiescence in self-report measures?

The tendency for participants to answer 'yes' or 'agree' to most questions without careful thought.

What is a solution to the acquiescence problem?

Include reverse-scored items in the questionnaire.

What is fence sitting in survey responses?

The tendency for participants to stay close to the middle of the scale.

How can fence sitting be mitigated?

Use an even number of scale points to eliminate a mid-point.

What is social desirability in self-report measures?

The concern over the impression one's responses might convey, leading to less accurate answers.

What are some solutions to address social desirability concerns?

Assure anonymity, include a social desirability scale, and use surreptitious measures.