Docsity
Docsity

Prepare for your exams
Prepare for your exams

Study with the several resources on Docsity


Earn points to download
Earn points to download

Earn points by helping other students or get them with a premium plan


Guidelines and tips
Guidelines and tips

Indices and Scales - Introduction to Social Research Methods - Lecture Slides, Slides of Research Methodology

This lecture is from Introduction to Social Research Methods course. Some points of these lecture slides are: Indices and Scales, Underlying Constructs, Individual Indicator, Index Validation, Item Validation, Numerical Score, Opinion Measures, Liking or Disliking, True Zero, Likert Scales

Typology: Slides

2011/2012

Uploaded on 12/24/2012

asgari
asgari 🇮🇳

4.7

(7)

114 documents

1 / 7

Toggle sidebar

Related documents


Partial preview of the text

Download Indices and Scales - Introduction to Social Research Methods - Lecture Slides and more Slides Research Methodology in PDF only on Docsity!

Indices and Scales

Indices

  • Use sets of responses to questions to provide

measures of underlying constructs

  • Each question that makes up an index

constitutes an individual indicator for that

construct

  • One analogy for an index is a test , and

approaches to index validation work for test-

item validation as well.

Scales

  • SCALING creates a measure of a variable

expressed as a numerical score. This measure can be any of the following:

  • ordinal (ranked, as with opinion measures),
  • interval (ranked with known distances between

rankings, as with “degrees” of liking or disliking something), or

  • ratio (interval with known proportions among

scores due to existence of a “true zero,” as with age and income).

Likert Scales

  • Likert scales provide ordinal-level measures of attitudes.
  • Likert scales always run from one extreme evaluative response to another.
  • Likert scales are generally combined to formulate a composite index of some underlying construct. This is why “additive scaling” is typically Likert scaling.
  • Likert scales are simple to produce and answer and aid in comprehensive indicator measurement.
  • The greatest problem with Likert scales is a form of bias known as response set****.
  • Another problem is that equivalent scores don’t necessarily mean equivalent responses.

Bogardus Social Distance Scales

  • Bogardus scales measure liking or antipathy between social groups. Groups that dislike one another have greater “social distance” separating them.
  • The scale proposes a number of hypothetical situations of social interaction.
  • Social distance scales are used to measure overt and symbolic racism and various anti-outgroup sentiments, although their findings are always questionable if not presented comparatively and in context.

Semantic Differential Scales

  • These are indirect measure of how a person feels about a concept, object or other person.
  • Adjectives express opposite forms of evaluation ( good vs bad), potency (strong vs weak) and activity (active vs passive).
  • On response forms, the adjectives are spaced with seven to eleven choices between them, and respondents select one “feeling” per pair.
  • Results expose a more complicated set of attitudes than can be acquired asking straightforward questions.

Guttman, or Cumulative, Scales

  • Guttman scales describe underlying dimensions in survey data. Guttman scales measure the intensity of a concept.
  • Process begins with surveys that ask simple yes-no or present-absent questions about the topic of interest.
  • The researcher determines how many people answered the questions in every possible order, and has a hypothesised order based on question “seriousness.”
  • If the questions all (or predominately) follow the hypothesised logical order, the question set is considered a “true Guttman scale” and can subsequently be used to measure the intensity of underlying constructs in other studies.