Class Notes (836,147)
Todd Alway (64)
Lecture

# October 16,2013-3N06 Lecture Notes.doc

2 Pages
88 Views

School
Department
Political Science
Course
POLSCI 3N06
Professor
Todd Alway
Semester
Fall

Description
Political Science 3N06 October 16, 2013 Political Science 3N06 2013 Lecture 6b A Sample of Sampling Sampling Strategy of some type is always necessary. - Why are you looking at THIS and not at THAT - Allows you to justify looking at a small piece of a whole - Do not need to look at the entire element; - Every sample take, will be slightly different from the population that the sample was taken from. PROBABILISTIC S AMPLING CONTINUED : - Sampling error will depend on: 1. The nature of the procedure followed - If it was not based on probabilistic means; cannot measure the kind of error. Even if done in a probabilistic way there will be some difference between the small and large; but can measure using probability theorem. 95% etc. - Probability samples have errors that can be estimated - Non-probability samples have errors that cannot be precisely estimated o They may introduce unknown systematic bias into the sample 2. The sample size - The larger the sample, the smaller the sampling error o PROVIDED that an appropriate probability sample has been gathered o IF you have a non-probability sample, then increasing the sample size might not make things better. o Literary Digest – In 1930s (excluded those people who would have gone towards the democratic party) o Bigger sample, the smaller the confidence interval;  Decrease sample size; the confidence interval increases N ON -PROBABILISTIC SAMPLES - Non-probabilistic techniques may be required or even desired, depending upon the purposes of your research - Do not use these techniques if your goal is to produce a sample that is representative of the population of interest o Particularly when producing data that will be subjected to statistical analysis - However, non-probabilistic sampling techniques do not always represent a methodological weakness - They are often used in qualitative research (particularly purposive sampling) - If you want a ‘representative’ sample ONLY use PROBABILISTIC TECHNIQUES; - Depending upon the research question, might not need to do a probabilistic approach. - A) Haphazard, convenience, or accidental sampling - The technique is not likely to produce very representative samples nor conclusions that are generalizable - You must be careful when generalizing your findings - Do not use this o For example CHCH interviewing at random; o Trying to generalize from th
More Less

Related notes for POLSCI 3N06
Me

OR

Join OneClass

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

Join to view

OR

By registering, I agree to the Terms and Privacy Policies
Just a few more details

So we can recommend you notes for your school.