Lecture 4.docx

4 Pages
84 Views
Unlock Document

Department
Sociology
Course
SOCB05H3
Professor
Katherine( Katy) De Celles
Semester
Summer

Description
Lecture 4: Compensate measure of variables; 1. Scale  Process of measuring or ordering entities in respect to quantitative attributes  Give those attributes a list, and group them to stronger or weaker variables  Cluster of questions, which tap into a unitary dimension of behaviour, attitude or feeling  Exp. Attribute to masculinity; Cars, sports, etc…  Measuring one concept in a scale, everything is related 2. Index  Constructed by accumulating scores assign to individual attributes  exp. Index contribute to scores in a dimension, not as specific as a scale  Combination of several empirical indicators into a single measure  Inadequacy of a single indicator  when we have multiple indicators each indicator reflects a distinct aspect of the dimensions  Compensate measurement has a better range of variation  Increases the reliability of our experiment  Similarities  Both are ordinal measures of variables  They rank order attributes  Both are compensate, measure one variable  Difference  Index: accumulate scores assigned to individual attributes  weighted on the same  Scale: Assign scores to patterns of responses  has an intensity structure among the attributes  Indexes are easier to create, scale is better  Scales are predictive of outcomes, an ordinal list  Index, everything is weighted the same, they measure all the dimensions of a topic rather than focus on one aspect.  Exp. Multiple but distinctive attribute of behaviour (exp)  Index should have high face validity 5 things to keep in mind; Index 1. Select your items carefully  Face validity (logical), related to your construct  They are unidimensional; tapping into multiple dimension but based on and measuring only one concept  Depending on your topic, it will determine the broadness of your index  Conceptualize your term 2. Examine whether there is an empirical relation  Empirical relation is established when answer to one question will predict the next question  If two items are empirically related, we can argue that each reflects the same variable, so both can be included in the same index 3. Assign scores for responses  Two basic decisions  Decide the desirable range of the index scores  Decide whether to give each item in the index equal weight or different weights  Ranking for each items 4. Handle missing data  How representative will your research be?  Exclude cases with missing data from the construction of the index and the analysis  Treat missing data as one of the available responses  Assumptions, using their non – response as a “no”  Analysis missing data to interpret the meaning  All of these methods  enters bias into one’s paper 5. Validate the index  Item analysis: internal validation  to what extent does the index as a whole to the items that formulate it?  does each item make an independent contribution to the overall measurement of one’s concept  having internal validity does not mean the items are not empirically related  External validation: ranking of groups on the index should predict the ranking of groups in answering similar or related questions  Sampling  Question: who do I want to question?  Not being confine to only the individuals they study, generalize to the population  The population is who we sample from  Studying a population as a whole is impossible, need small groups to function the research Sampling process: stages 1. Defining the population of concern; who you want to caterer to for your research 2. Specifying a sampling frame 3. Specifying a sampling method for selecting items or events
More Less

Related notes for SOCB05H3

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.


Submit