Class Notes (1,100,000)
CA (630,000)
U of G (30,000)
SOAN (900)
SOAN 2120 (400)
Lecture

Lecture Notes Feb 11.13.15.docx


Department
Sociology and Anthropology
Course Code
SOAN 2120
Professor
Scott Schau

This preview shows page 1. to view the full 4 pages of the document.
Lecture Notes Monday Feb. 11 2013
Bad index vs. bad validators
-if an internal item analysis shows inconsistent relationships between items
included in an index and the index itself something is wrong with the index
-if the index fails to predict strongly the external validation items conclusion is
ambiguous
-choose between 2 possibilities
1. index does not adequately measure the variable in question
2. validation items do not adequately measure the variable and thereby do
not provide a sufficient text of the index
Scale Construction
-not all indicators of a variable are really important or equally strong
-each item going into a composter measure may have a different intensity in
terms of the variable
-scales offer more assurance of ORDINALITY by tapping the intensity structures
among the indicators
-4 scaling procedures
1. bogardus social distance scale
-measures the wiliness of ppl to participate in social relations of
varying degrees of closeness with other kinds of people
-clear differences of intensity suggest a structure among the items
-ranges from “easy items” to “hard items”
-by knowing how many relationships a respondent will accept, we
know which relationships will be accepted
e.g. give me your first reaction, yes or no whether you personally
would feel comfortable having an exchange student from (country).
2. thurstone scales
-complicated and time consuming
-rarely ever used
3. likert scaling
-item format created by Likert is one of the most commonly used in
contemporary questionnaire design
-ordinality of response categories
-“strongly agree” “agree” “disagree” “strongly disagree”
-question format used to determine the relative intensity of different
items
-true Likert scale seldom used because of its complexity
4. guttman scaling
-based on the fat that some items may be more extreme indicators of
the variable than others
-steps for constructing a Guttman scale:
-1st examine the face validity of items available to analysis
You're Reading a Preview

Unlock to view full version