This preview shows pages 1–8. Sign up to view the full content.
This preview has intentionally blurred sections. Sign up to view the full version.
View Full DocumentThis preview has intentionally blurred sections. Sign up to view the full version.
View Full DocumentThis preview has intentionally blurred sections. Sign up to view the full version.
View Full DocumentThis preview has intentionally blurred sections. Sign up to view the full version.
View Full Document
Unformatted text preview: Statistical Significance levels Alpha level: The selected maximum risk of Type I Error that is acceptable Probability value (pvalue): The smallest probability of a Type I Error you could have adopted and still rejected the null hypothesis. Wednesday, June 1, 2011 OneSample Statistics N Mean Std. Deviation Std. Error Mean bloodsugar 102.0000 8.21922 2.59915 OneSample Test.769 9 .4612.000007.8797 3.8797 bloodsugar t df Sig. (2tailed) Mean Difference Lower Upper 95% Confidence Interval of the Difference Test Value = 0 Wednesday, June 1, 2011 Suppose df=9, and observed t = .769, and you have a more thorough table of critical values for the ttest. df .50 .40 .30 .20 .10 .05 1 2 9 .70ish .80ish 1.0ish 1.383 1.833 2.262 An observed ttest statistic: .769 If you had adopted alpha = ~.47, you would have rejected your null hypothesis, but with a .47 risk of a false alarm/Type I error. Alpha levels Wednesday, June 1, 2011...
View
Full
Document
 Spring '10
 DAMARE

Click to edit the document details