Statistics for health, life, and social sciences
Statistics for health, life, and social sciences Math 14500-02
Popular in Statistics for health, life, and social sciences
Popular in Math
verified elite notetaker
This 2 page Class Notes was uploaded by kyle dunham on Thursday March 3, 2016. The Class Notes belongs to Math 14500-02 at Ithaca College taught by James E Conklin in Spring 2016. Since its upload, it has received 8 views. For similar materials see Statistics for health, life, and social sciences in Math at Ithaca College.
Reviews for Statistics for health, life, and social sciences
Report this Material
What is Karma?
Karma is the currency of StudySoup.
Date Created: 03/03/16
Statistics First we did a warmup in class: A 90% confidence interval is an interval estimate for a ________ using a procedure which will capture the parameter 95% of the time. HYPOTHESIS TEST -We are seeing if our data is strong enough to rule out chance -To first setup a hypothesis test you should have a: Null Hypothesis: Ho =Both are about the population Alternative Hypothesis: Ha *Logic: We give Ho the benefit of the doubt to see if our results could have happened by chance. (This is like in a court case: INNOCENT UNTIL PROVEN GUILTY) example: We are going to test if more than 15% of Ithaca College students drank coffee today. So…… Ho: p=0.15 Ha: p>0.15 We used a sample in the class and our data showed that 4/25 of the students in our class drank coffee today p-hat=4/25=.16 next you would obtain a p-value…. P-VALUE A p-value is the probability that we would have obtained data as extreme or more extreme as we did if Ho (Null Hypothesis) was true. ***A p-value close to 0 means that your null hypothesis is usually false*** p-value for coffee drinkers was .539 which means that you can’t reject ho. The usual cutoff whether to reject or accept the null is less than .05 HYPOTHESIS TESTS -Tests for parameters -tests for means -tests for proportions -tests for difference in means -tests for difference in proportions LEVEL OF SIGNIFICANCE: IT is the cutoff for the p-value -If the significance level is .01 and the p-value is .02 than we can’t reject Ho (Null Hypothesis) TYPE 1 ERROR: Reject the null hypothesis, but the null hypothesis is actually true TYPE 2 ERROR: Fail to reject the Null hypothesis, but the null hypothesis is actually false.