Chapter 6: Indexes, Scales, and Typologies Flashcards
A type of composite measure that summarizes and rank-orders several specific observations and represents some more-general dimension.
Index
A type of composite measure composed of several items that have a logical or empirical structure among them. Bogardus social distance, Guttman, Likert, and Thurstone are examples.
Scale
Which is superior–a scale or an index?
Scales because they take into consideration the intensity with which different items reflect the variable being measured.
What are the four main steps in constructing an index?
(1) Selecting possible items, (2) Examining their empirical relationships, (3) Scoring and validating an index, (4) Handling missing data
What is face validity?
A step in item selection for an index: Measures should appear on their face to indicate what you are trying to measure.
What is undimentionality?
A step in item selection for an index: A composite measure should represent only one dimension of a concept.
What is general or specific?
A step in item selection for an index: Are you trying to measure something generally or specifically and how does your measure line up with that?
What are the options to account for variance when creating an index?
(1) Select serveral items that generate responses that divide people equally in terms of the variable, (2) Select items differing in variance–needed for creating a scale
What establishes an empirical relationship?
When a respondents answers to one question help us predict how they will answer other questions.
What is a bivariate relationship?
A relationship between two variables
What are the two types of empirical relationships?
Bivariate and multivariate
What is a multivariate relationship?
A relationship between more than two variables
An assessment of whether each of the items included in a composite measure makes an independent contribution or merely duplicates the contribution of other items in the measure.
Item Analysis
The process of testing the validity of a measure, such as an index or scale, by examining its relationship to other presumed indicators of the same variable. If the index really measures prejudice, for example, it should correlate with other indicators of prejudice.
External Validation
A measurement technique for demtermining the willingness of people to participate in social relations–of varying degrees of closeness–with other kinds of people. It is an especially efficient technique in that one can summarize several discrete answers without losing any of the original details of the data.
Bogardus Social Distance Scale
A type of composit measure, constructed in accordance with the weights assigned by “judges” to various indicators of some variables.
Thurstone Scale
A type of composite measure developed by Rennis Likert in an attempt to improve the levels of measurement in social research through the use of standardized response categories in survey questionnaires to determine the relative intsnity of different times. Liker items are those using such response categories as “strongly agree,” “agree,” “disagree,” and “strongly disagree.” Such items may be used in the construction of true Likert scales as well as other types of composite measures.
Likert Scale
A questionnaire format in which the respondent is asked to rate something in terms of two, opposite adjectives (e.g. rate textbooks as “boring” or “exciting”), using qualifiers such as “very,” “somewhat,” “neither,” “somewhat” and “very” to bridge the distance between two opposites.
Semantic Differential
A type of composite measure used to summarize several discrete observations and to represent some more-general variable.
Guttman Scale
The classification (typically nominal) of observations in terms of their attributes on two or more variables. The classification of newspapers as liberal-urban, liberal, rural, conservative-urban, or conservative-rural would be an example.
Typology
What two desires will you hve to find a medium between when creating an index score?
(1) The range of measurement, and (2) an adequate number of cases at each point of the index
What are two decisions you need to make when creating an index score?
(1) The desirable range of the index score, and (2) whether to give each item in the index equal weight or different weights
What are some ways that you can deal with missing data when creating an index?
(1) If only a few cases have missing data, you can eliminate them from your results, (2) Decide to score the missing data based on the omission (for example, if someone didn’t check yes, score it as a no), (3) carefully analyze the missing data which may lead to an interpretation of its meaning, (4) if the item has several possible values, assign the middle valeu
In the Guttman Scale, what do you call the correct predictions or the percentage or original responses that toculd be reproduced by knowing the scale scores us to summarize them? = 1 - (number of errors/number of guesses)
Coefficient of Reproducibility
For the Guttman Scale, what are the commonly used standards for the coefficient of reproducibility
90-95%
