ADM 2304 Lecture Notes - Lecture 10: Null Hypothesis, Confidence Interval, Type I And Type Ii Errors

• School: University of Ottawa
• Department: Administration
• Course: ADM 2304
• Professor: Tony Quon

Document Summary

Variable n n* mean se mean stdev minimum q1 median q3 maximum. City_1 16 0 133. 99 2. 75 11. 01 117. 49 122. 76 135. 47 142. 47 153. 43. City_2 13 0 143. 52 3. 51 12. 66 119. 55 131. 86 144. 69 153. 99 161. 55 a. Calculation: t (stat) =(x1-bar)-(x2-bar)/ (s1^2/n1) + (s2^2/n2) In conclusion, since /tstat/ is larger than t-crit, we can reject the null hypothesis, and there is sufficient evidence that there is a difference in the mean value: p-value=0. 043. Since p-value=0. 043<0. 05, we can reject the null hypothesis that there is sufficient evidence that the means are different: confidence interval: (x1-bar-x2-bar)+/-t(0. 05/2)se. Since ci(-18. 7385,-0. 3214) doesn"t include 0, so we can reject null hypothesis, there is sufficient evidence that means are different. Point estimate for 1 - 2 is -9. 50. 95. 4 percent ci for 1 - 2 is (-19. 21,-0. 67) Test of 1 = 2 vs 1 2 is significant at 0. 0373. The test is significant at 0. 0372 (adjusted for ties) a. One or both of the samples is not normally distributed.