This preview shows pages 1–2. Sign up to view the full content.
Univariate Chisquare Test: Goodness of Fit test
One Qualitative Random Variable; several or more groups
Similar to Ztest for 2 sample proportions, but can extend to 3 or more group
Step One: State the Research Hypotheses
Null (Ho):
Pwa=.20; Pdunk=.40; Pstar=.20; P711=.20
Dunkin Donuts coffee is prefered two to one over competition
Model (1:2:1:1) is a good fit to the data; observed frequencies, and expecte
are not significantly different; any observed differences are due to chance
Alternate(Ha):
not Ho; dunkin donuts coffee is NOT prefered two to one over competition
Model (1:2:1:1) is NOT a good fit to the data; observed frequencies differed
from the expected frequencies
Step Two: State the Decision Rule: using Alpha = .05
DF= [K1] = 4 1 = 3; ChiSquare Critical = 7.81473
where K represents "# of groups" or "categories
Reject Null Hypothesis if ChiSquare Test exceeds ChiSquare Critical
(notice N has nothing to do with degrees of freedom for ChiSquare Tests)
Step Three: Collect the Data and Compute Test Statistic
This preview has intentionally blurred sections. Sign up to view the full version.
View Full Document
This is the end of the preview. Sign up
to
access the rest of the document.
This note was uploaded on 04/08/2008 for the course STAT 2102 taught by Professor Dr.pred during the Spring '07 term at Temple.
 Spring '07
 Dr.Pred

Click to edit the document details