ADMS 2320 Study Guide - Final Guide: Type I And Type Ii Errors, Analysis Of Variance, Null Hypothesis

• School: York University
• Department: Administrative Studies
• Course: ADMS 2320
• Professor: Marwan Hassan

Document Summary

Contingency table: use to infer two nominal variables are related and differences exist btw two or more populations of nominal variables. H0: the two variables (responses and employee group) are independent (no relationship between 2 variables) H1: the two variables are dependent (2 variables are related) Conclusion: do not reject h0, there is not enough evidence to infer that responses. 2 differ among the three groups of employees. Single value p(x)=0, sample n , not reflect to parameter value. Desirable: unbiasedness ( ), consistency ( and relative efficiency (smaller variance is means more efficient) Larger confidence level produces a wider confidence interval. Larger sample size narrow confidence interval. produce wider confidence intervals. Zx a 2/ m=) ( xe n s. Chapter 11 hypothesis test: assume null h0 is true, find evident to infer alt. The smaller the p-value, the more evidence to support the alternative hypothesis. Type i error reject h0 (null hypothesis) when h0 is true.