Class Notes (839,242)
Canada (511,223)
Sociology (2,434)
SOCB05H3 (99)
Lecture

SOCB05; LEC04.docx

3 Pages
122 Views

Department
Sociology
Course Code
SOCB05H3
Professor
Rania Salem

This preview shows page 1. Sign up to view the full 3 pages of the document.
Description
LEC04 - sampling - the logic of causation - units of analysis and the ecological fallacy - types of survey designs - formulating a research question and hypotheses SAMPLING IN QUALITATIVE AND QUANTITATIVE RESEACH - in quantitative research (surveys), probability sampling is favoured. This is because most statistical analysis assumes that the sample elements have an equal probability of selection - in qualitative research (field observation, qualitative interviewing, oral histories) probability sampling methods are possible, but rarely used. Instead non probability sampling is used IDIOGRAPHIC AND NOMOTHEIC MODELS OF EXPLANATION - idiographic explanations- what are all the factors that may have caused the phenomenon of interest? o The bigger the number identified, the better o List different types of causes that may underlie a given phenomenon  The more the numbers are, the more holistic the graphic will be - Nomothetic explanations- what are the most important factors that caused the phenomenon of interest? o Identify the causal factors that most effectively predict most or all of the cases is best o Noma; law o Try to arrive to a general rule that would apply to the greatest number of cases possible o Probabilistic  Deal with probability of something happening o Causal factors presence does not necessarily guarantee the outcome of the interest  Effect that we are interested in may not always be present  Raises the chances that the outcome would be observed o There are always exceptions to rules  They are not disproven if there are exceptions  Generally, …………. o They do not have to apply to the majority of cases  Less than 50% of all university degree holders in Canada earn less than 6 figures  Doesn’t change the fact that the higher proportion of graduates have 6 figure jobs than non graduates  Pattern still holds ESTABLISHING CAUSAL RELATIONSHIPS - correlation o an empirical relationship between two variables where:  changes in one variable are associated with changes in the other   ex. Grades and studying  particular attributes of one variable are associated with particular attributes of the other - temporal ordering o the cause most precede the effect in time, not vice versa  some attributes are fixed at birth, so the cause-effect sequence is easy to establish  with other variables, it is difficult to determine temporal ordering - non-spuriousness o spuriousness relationship= a correlation between two variables that is actually caused by a third variable o you can control for a third variable and if the correlation between independent and dependent disappears, then you know there’s a spurious relation between them  aka confounder or antecedent NECESSARY AND S
More Less
Unlock Document

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

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