SCALES AND MEASURES

Overview

The progress of science, including social science, depends heavily on building on the past. This is particularly so when it comes to the measurement of constructs. Coming to a disciplinary consensus on how to operationalize a construct (ex., "trust in goverment") is itself an exercise which illuminates surrounding issues. Conversely, if each social scientist operationalizes the same construct differently, confusion and "talking past one another" abounds and the state of the art progresses more slowly. While often there is no one perfect way to operationalize a construct, by using the same operationalization, social scientists achieve a far greater level of comparability across varied research than would otherwise be the case. Searching out existing standard scales and measures for constructs is therefore often an important early step in the research process, even if in the end the researcher opts for an original approach.

This volume of the Statistical Associates "Blue Book" series focuses on explanation of the common types of scales, measures of internal consistency and agreement, and standard scales and measures found in the literature. It is not intended to cover multidimensional scaling (subject of a different "Blue Book" volume) or item analysis. Likewise, other statistical methods of measuring constructs are also found in separate "Blue Book" volumes, such as those on factor analysis, structural equation modeling, partial least squares regression, canonical correlation, and latent class analysis.

The full content is now available from Statistical Associates Publishers. Click here.

Below is the unformatted table of contents.

Table of Contents

Overview	7
Key Concepts and Terms	7
Constructs vs. categories and benchmarks	7
Data-gathering techniques	8
Types of techniques	8
Likert survey items	9
Ranking scales	9
Social distance scales	9
Paired comparisons	9
Q-Sorts	10
Fixed resources allocations	10
Other methods	10
Methods of combining items in a scale	10
Overview	10
Indexes	10
Ordinal scales	11
Ordered scales	11
Composite scores	12
Factors and latent variables	12
Multidimensional scales	12
Tau Equivalence	13
Congeneric v. tau-equivalent v. parallel indicators	13
Tau-equivalence in SEM	13
Likert scales	13
Likert items and likert scales	13
"Likert scales" as Likert items in ordinal scales	14
Data level of Likert scales	14
Index of discriminative power (DP)	14
Guttman scales	15
Overview	15
How Guttman scaling works	15
Counting scale errors in Guttman scaling	15
Goodness of fit measures for Guttman scales	17
Minimum marginal reproducibility (MMR)	17
Marginal error (ME)	17
The coefficient of scalability	17
The coefficient of reproducibility	18
Stouffer's H technique	18
Chi-square significance of Guttman scales	18
Proximity scales	19
Overview	19
Example	19
Proximity scales vs. Guttman scales	20
Mokken scales	20
Overview	20
Loevinger's H	21
Measures of Internal Consistency	22
Overview	22
Cronbach's alpha	22
Overview	22
Characteristics of Cronbach's alpha	23
Alpha cut-off criteria	23
Negative alphas	23
Alpha vs. reliability	24
Alpha in SPSS	24
Standardized item alpha	24
Factor analysis	24
Rasch scales	25
Other internal consistency measures	25
Tarkkonen's measure of scale reliability	25
Loevinger's H	25
Kuder-Richardson Formula 20	25
Spearman's rho	25
Intraclass correlation	26
Measures of Agreement	26
Example	27
Measures of Reliability	27
Measures of Item Discrimination	27
Biserial correlation	27
Point-biserial correlation	28
Assumptions	28
Unidimensionality	28
Equality of Means and Standard Deviations	28
Frequently Asked Questions	29
Should I use existing items or create my own?	29
How can I find standard scales and instruments?	29
When may ordinal scale data be used in regression and other interval techniques?	29
Should I standardize my variables before testing for reliability of scale items with Cronbach's alpha?	30
I want to add item scores together to form a scale. How can I test if the items are additive?	30
How can I get my SPSS worksheet into Guttman scaling format?	30
What software programs compute Guttman scaling coefficients of scalability and reliability?	31
What is the 'cluster bloc technique'?	31
Selecting the criteria	32
Computing indices of agreement	32
Establishing non-arbitrary cutoff points	32
Forming the cluster block matrix	32
What are Thurstone equal-appearing interval scales?	33
Q-dispersion	33
Bibliography	34
References	34
Methodology	36
General	38
Business	39
Crime	39
Economic/Financial/Work	39
Education	40
Medical	40
Politics	40
Psychology	41
Public Administration/Organizations	43
Social and Sociology	44