Class Notes (839,076)
Canada (511,183)
Sociology (2,104)
Lecture 13

# 2Z03 Lecture 13 "Scale Construction".docx

3 Pages
50 Views

Department
Sociology
Course Code
SOCIOL 2Z03
Professor
Gerald Bierling

This preview shows page 1. Sign up to view the full 3 pages of the document.
Description
Fox 1 Lecture 13 SOCIOL 2Z03 Monday March 3, 2014 Scale Construction rd Continued from last lecture – March 3 , 2014 ­ which items should be worth more? ­ Thurstone Scales: process used to identify the logical structure of indicators o ‘judges’ are given a large # of statements (80-100) o judges can be students in a large class, colleges in academic departments o asked to rate the degree to which each statement indicates favourability towards subject on a scale of 1 to 13 (eg. Immigrants work hard; immigrants do jobs we won’t, etc.) o statements are organized into 13 piles based on most agreement o one statement is selected from each pile and given value of 1 to 13 o assign numerical value to each one of these statements o these 13 statements are used in the survey ­ Benefit: helps identify ordering of statements ­ Limitation: very time consuming; who are the judges? Also a lot of potential statements Typologies ­ Typology – the classification of observations in terms of their attributes on two or more variables ­ Eg. Views social policies and economic policies Social Liberal Social Conservative Economic liberal Economic conservative ­ May be economically conservative but socially liberal, typologies help describe these situations and variation in sample ­ Help us identify different types of respondents/cases The Logic of Sampling (New Lecture) ­ Purpose of Sampling ­ Non-probability/Non-random Sampling ­ Sampling Terminology ­ Probability/Random Sampling ­ Sampling Error & Sampling Distribution Purpose of Sampling ­ Rarely are we able to gather information about the entire population ­ No time/money o Exception – census ­ So we need methods to gather a sample ­ Two types of sampling methods: o Non-random (non-probability) – least likely to be representative of population o Random (Probability) – most likely to be representative, and allow us to estimate population values Non-random sampling ­ Samples are selected in some way not suggested by probability theory ­ How we select people not based on probability o Accidental/Convenience – choose most convenient subject; self-selected subjects  Eg. Call-in polls, surveys on websites, select themselves to take part  Only certain people who self-select, people with extreme opinions, in favor of or opposition to – by definition not really representative of population, cant put a lot of faith in these respondents o Purposive sampling – selected on basis of their usefulness or representativeness  Eg. ArcelorMittal workers – working in steel industry, may not have a lot of research money or assistance which would allow to send researchers across country to interview, large amount at one company, those workers may represent a larger population of steel workers o Snowball sampling -- for population that are difficult to locate; through references,
More Less

Only page 1 are available for preview. Some parts have been intentionally blurred.

Unlock Document
###### You're Reading a Preview

Unlock to view full version

Unlock Document
Me

Log In

OR

Join OneClass

Access over 10 million pages of study
documents for 1.3 million courses.

Sign up

Join to view

OR

By registering, I agree to the Terms and Privacy Policies
Already have an account?
Just a few more details

So we can recommend you notes for your school.

Reset Password

Please enter below the email address you registered with and we will send you a link to reset your password.

Add your courses

Get notes from the top students in your class.

Request Course
Submit