NONPARAMETRIC STATISTICS EDRM 712
Popular in Course
Popular in OTHER
Mrs. Dangelo Fahey
verified elite notetaker
This 2 page Class Notes was uploaded by Edwin Considine on Monday October 26, 2015. The Class Notes belongs to EDRM 712 at University of South Carolina - Columbia taught by M. Seaman in Fall. Since its upload, it has received 28 views. For similar materials see /class/229492/edrm-712-university-of-south-carolina-columbia in OTHER at University of South Carolina - Columbia.
Reviews for NONPARAMETRIC STATISTICS
Report this Material
What is Karma?
Karma is the currency of StudySoup.
Date Created: 10/26/15
NONPARAMETRIC STATISTICS EDRM 712 Report S20 Model In this report I will analyze the annual performance review scores and the accompanying merit pay raises for junior faculty members in one department at a university The purpose is to determine if merit raises are associated with annual review outcomes The performance review scores obtained are on a 10point scale with high scores indicating strong performance Merit raises were obtained as a percentage increase in salary This is a very small sample situation There are only four junior faculty members The performance review scores and merit raises are as follows APR Score Merit Raise 3 2 6 22 7 24 9 25 The following scatterplot illustrates that there is a strong association among the variables The association appears to be strong and linear at least in this sample Percent Merit Raise 3 4 Annual Performance Review Score 5 6 Pearson s correlation coefficient for these data is 098 Correlations Percent Merit Raise 977 Annual Performance Pearson Correlation Review Score The small sample size led me to choose Pitman s exact test of the hypothesis that there is no association among the variables With this test there are 4 24 possible correlation coefficients Thus with my chosen 5 error rate there are 0524 12 values in the rejection region for this test In other words the only condition under which I can reject the null hypothesis of no association is when I obtain the largest possible correlation from all possible orderings of the observed values In fact that is exactly what happened with these data The correlation of 0977 is the maximum correlation that can be obtained with any arrangement of these data Itherefore can reject the null hypothesis of no association I do not have enough information to know whether my data come from a bivariate normal distribution I can however conclude that merit raises are positively and monotonically associated with annual performance review scores It is reasonable to argue that this is how it should be in a performancebased merit system Summav A study of the annual performance review scores and the accompanying merit pay raises for junior faculty members in one department at a university revealed that the department is operating with a performancebased reward system The correlation of annual performance review scores with pay raises is 098 This is a strong positive correlation that provides enough evidence to conclude that there is a nonchance positive association among annual performance review scores and pay raises in this department