Regression and Correlation

QUESTION (70 marks)
A company is analyzing the salary of its staff as compared to other companies in the same state. The variables below are given:
 Salary(RM)
 Ed= Employee’s years of education
 Ex = Employee’s years of working experience

Part I (16 marks)
(a) Based on the dataset given, obtain the descriptive statistics for the salary of the employees’ years of education. [4 marks]
(b) Create frequency distributions tables and draw appropriate diagrams for the salary of the employees’ years of education, separately. [12 marks]

Part II (16 marks)
It is known that the salary is influenced by the years of working experience. By using correlation and regression analysis in Excel, display the output for years of working experience by the salary of the employees. Your analysis should include a scatter plot of the data (complete with best fit line and explanation of the graph). Test the statistical significance of the correlation coefficient.

Part III (28 marks)
Write a report about your investigation. Give brief introduction of your data (including the variables). Interpret your results from part I and II. All the graphs given above should be interpreted as well. [Hint: include the best measure of location and spread]. Comment on the practical significance of your analysis from part II. Based on your analysis, do you think the assumed independent variable explain well your dependent variable? What are the other possible factors affecting your dependent variable? Discuss any limitations you have regarding using this technique for your study.

Part IV (10 marks)
Explain what regression and correlation means and how it can be used in real life. Include examples that will support your explanation.