Study with the several resources on Docsity
Earn points by helping other students or get them with a premium plan
Prepare for your exams
Study with the several resources on Docsity
Earn points to download
Earn points by helping other students or get them with a premium plan
Community
Ask the community for help and clear up your study doubts
Discover the best universities in your country according to Docsity users
Free resources
Download our free guides on studying techniques, anxiety management strategies, and thesis advice from Docsity tutors
An introduction to indexes and scales, their importance in modern society and personal success, and the process of constructing and evaluating them. It covers the concept of measurement levels, reliability, and validity, as well as methods for evaluating reliability and validity. The document also touches upon the importance of indexes in social research and their role in statistics and data analysis.
Typology: Lecture notes
1 / 22
This page cannot be seen from the preview
Don't miss anything!
Summarize several indicators into a single index score.
With an index we can assume we have achieved a higher level of measurement (e.g., add up a series of nominal responses to form an ordinal or interval index). This allows us to use more powerful statistics in analysis.
Indexes & scales almost always provide a more reliable and valid measure of a phenomenon than a single indicator or question.
With scales we are more concerned about
reliability & validity with indexes.
Most scales assume unidimensionality ….the
scale is measuring only one concept.
Sociology is concerned with developing
interesting & useful indexes to test research hypotheses. Ad hoc indexes are common in social research.
Parallel Forms Reliability (two similar versions of an index should produce similar index scores).
Test-Retest Reliablity (same index administered to same group at 2 different times should produce similar index scores).
Split-Half Reliability (Randomly split questions that form index into 2 sub- indexes…scores on the 2 sub-indexes should be similar for a given respondent).
Cronbach’s Alpha (A statistical measure of reliablity…the closer the alpha coefficient is to 0 the lower your reliability, the closer it is to 1 the higher the reliability of your index.
“Jury opinion validity” ….a variant of
content validity.
“Known groups validity”… a variant of
criterion validity.
Indexes do not require the level of
validity (or reliability) scales require.
Avoid chatting, dozing off, text messaging, net surfing, etc., during lectures & labs…this can be tough given the subject matter but try to remain quiet, attentive and awake!
Study statistics regularly! Massed or crammed studying of stats is a recipe for disaster.
Do not fall behind…schedule a weekly review!
Work out problems using a calculator to build intuitive understanding & confidence.
Use computer labs wisely…plan ahead so you can complete as much of the Assignment during our labs as possible!!!
TABLE 1.1: RESPONSES OF REMOVAL OF A TOY BY SEX OF CHILD. RESPONSE OF CHILD SEX OF CHILD MALE FEMALE
Cry 25 28 Express Anger 15 3
Withdraw from Play 5 4 Play with Alternative Toy 5 15
N= 50 50
We can facilitate comparisons of groups of different sizes by using proportions or percentages.
We convert a frequency into a proportion by dividing the number of cases in a category by the total number of cases.
p = f / N where f is the number of cases in a category and N is the total number of cases. (e.g., 15 girls out of 50 girls found an alternative toy so the proportion is 15 / 50 = .30; the proportion of boys who found an alternative toy was 5 / 15 = .10)
SEX OF STUDENTS MAJORING IN ENGINEERING AT UNIVERSITIES “A” AND “B”.
ENGINEERING MAJORS SEX UNIVERSITY “A” UNIVERSITY “B” f f Male 1,082 146
Female 270 37
Total 1,352 183
SEX OF STUDENTS MAJORING IN ENGINEERING AT UNIVERSITIES “A” AND “B”.
ENGINEERING MAJORS SEX UNIVERSITY “A” UNIVERSITY “B” f f Male 1, 80%
146 80% Female 270 20%
37 20% Total 1,352 183
