Study Guides (248,151)
Geography (224)
GGR270H1 (28)
Midterm

# hypothesis testing

2 Pages
95 Views

Department
Geography
Course
GGR270H1
Professor
Damian Dupuy
Semester
Fall

Description
Statistics Lecture November 30, 2011 Hypothesis Testing- Non-Parametric • Most common assumption is a normal population distribution • We are assuming it’s a normal distribution o Population mean miu and variance s2 • But what happens when: o Using nominal/ordinal or categorical data; are we using some sort of ranking system o Normality of the population discribution is unknown • So then we use a non-parametric test o We want to know something about the goodness of fit: is our sample drawn from the particular population o Contingency table or cross-tabulated data; use a chi squared test; if its in a table and its counts are frequencies, you use a pi squared test- you compare the actual cell frequencies with the observed cell frequencies and if they are quite large, then you can say there is some variation going on • Many parametric test have non-parametric equivalents Non-Parametric- Chi Square or X2 • Using observed frequency counts of a variable or variables • We are looking for a significant difference between actual frequencies and an expected frequencies • Null hypothesis assumes no significant difference between actual and expected frequency counts • If the difference between actual and expected is small, the fact that there is a difference is random and there is nothing significant going on; no significant difference • If the difference between actual and expected is large, there is something else we need to be concerned about; is a significant difference • Us
More Less

Related notes for GGR270H1
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.