Q4_W2 PR 2 Reviewer
3: Measurement in Research
A measure can refer to things that can be counted unambiguously such as:
Personal income
Household income
Age
Number of children
Number of years spent at school (Bryman, 2008, p. 145).
Page 4: Indicators in Research
An indicator is less directly quantifiable and is employed as though it were a measure of a concept (Bryman, 2008, p. 145).
Page 5: Concepts and Indicators
Concepts: Income, Poverty, Social Class
Variables: Annual earnings, Family income, Education, Occupational prestige
Indicators:
What was your total income from all sources in 2010?
Subjective poverty: Would you say you are poor?
Absolute poverty: Family income + poverty threshold.
Education + income + prestige.
Page 7: Types of Variables
Nominal Variables: Categories cannot be ranked and have name value only.
Examples: School attended, country of residence, race, religion, gender.
Page 8: Ordinal Variables
Ordinal Variables: Categories can be rank-ordered but distances between them are not equal.
Examples: Social class, opinions on a questionnaire, job position in a hierarchy.
Page 9: Interval Variables
Interval Variables: Identical distance between categories, but no true zero point.
Example: IQ scores with no meaningful zero.
Page 10: Ratio Variables
Ratio Variables: Identical distance between categories with an absolute zero.
Example: Scores on an achievement test indicating a lack of skills/knowledge.
Page 12: Rating Scales
Rating scales capture respondents' reactions or responses to a given item.
Page 17: Likert Scale
Designed by Rensis Likert to measure ordinal data in research.
Page 18: Semantic Differential Scale
A composite scale where respondents indicate opinions using pairs of adjectives as polar opposites.
Page 20: Guttman Scale
A composite scale designed by Louis Guttman with items arranged in increasing intensity.
Page 22-23: Sample Question Formats
Sample 1: Closed question in vertical format:
How do you rate the president’s performance?
Very Good - 5 / Good - 4 / Fair - 3 / Poor - 2 / Very Poor - 1.
Sample 2: Closed question in horizontal format with same ratings.
Page 24-25: Likert Scale Format
Format where participants indicate agreement/disagreement with statements on a scale.
Page 26: Survey Layout Example
Example layout for a Television News Broadcasting Survey with demographic questions.