Research Methods -- CRJU 3601 – Study Guide

Validity and Reliability in Research (95% Confidence Interval)

Validity -- Reliability

Validity: An instrument is valid if it measures what it is supposed to measure / – what it says it measures

The ACT is valid because it measures what a student learned in high school.

Reliability: the stability or consistency of the instrument / it can be replicated over and over

The ACT is reliable because it measures knowledge across all students

Validity -- Reliability Examples

Validity -- 3 ways to express it to get accurateness of Measurement

a) Research design -- is your dependent variable actually impacted by the independent variable (or some other factor)

b) Measurement -- Does your survey instrument measure what you intend it to measure

c) Representativeness -- Does your sample accurately represent the population

Reliability: Replication of results

a) Ask the same person at a different time, and get the same answer.

b) To test, in a survey, ask the same question in different ways.

Types of validity: subjective or objective (Opinion or Facts)

a) Face Validity-logical, common sense -- Subjective Varies by opinion

b) Content Validity-full breadth, depth, and completeness -- Subjective Varies by person

c) Criterion Validity-correlated with existing measures -- Objective backed by facts

d) Construct Validity-backed up by existing research -- Objective backed by facts

Increase validity

Shorten the time-frame from which you are asking questions to increase memory, and avoid embarrassing questions

Increase reliability: Use Scales and Indexes

Scales (10 questions sequentially ordered indicating agreement with all that precede it)

Indexes -- Summed over multiple Scales provide a composite score.

The statistic used to calculate reliability is called "Cronbach’s Alpha"