Case Study: Severance Pay When one company buys another company, it is not unusu
ID: 3396073 • Letter: C
Question
Case Study: Severance Pay When one company buys another company, it is not unusual that some workers are terminated. The severance benefits offered to the laid-off workers are often the subject of dispute. Suppose that the Laurier Company recently bought the Western Company and subsequently terminated 20 of Western’s employees. As part of the buyout agreement, it was promised that the severance package offered to the former Western employees would be equivalent to those offered to Laurier employees who had been terminated in the past year. Thirty-six-year-old Bill Smith, a Western employee for the past 10 years, was one of those let go. His severance package included an offer of 5 weeks’ severance pay. Bill complained that this offer was less than that offered to Laurier’s employees when they were laid off, in contravention of the buyout agreement. A statistician was called in to settle the dispute. The statistician was told that severance is determined by length of service with the company. To determine how generous the severance package had been, a random sample of 50 Laurier ex-employees was taken. For each, the following variables were recorded: Number of weeks of severance pay Number of years with the company The statistician would like to use the above sample information and the appropriate statistical method to determine whether Bill is correct in his assessment of the severance package.
Question: What is the final conclusion base on the data by using both versions of 95% confidence intervals.
Weeks SP Years 13 16 13 19 11 8 14 16 3 4 10 9 4 3 7 2 12 15 7 15 8 13 11 10 9 5 10 13 18 19 17 20 13 11 14 19 5 2 11 15 10 14 8 6 15 16 7 6 9 8 11 12 10 13 8 14 5 7 6 4 14 12 12 17 10 11 14 14 12 17 12 17 8 8 12 16 10 10 11 13 15 19 5 6 8 9 11 11 15 15 11 13 6 5 6 7 13 14 9 10Explanation / Answer
Statistician want to estimate the severance based on the length of the service.
The linear model he used in this case is No.of weeks SP = a+b* ( length of the service)
The regression output for the data of given 50 observations is
The regression equation is
Weeks SP = 3.62 + 0.574 Years
Predictor Coef SE Coef T P
Constant 3.6214 0.6967 5.20 0.000
Years 0.57428 0.05552 10.34 0.000
S = 1.91704 R-Sq = 69.0% R-Sq(adj) = 68.4%
The regression equation is
Weeks SP = 3.62 + 0.574 Years
By substituting the value of X =10 , the predicted severance is SP=9.364
Computation for 95% confidence interval
The 95% confidence interval is = 8.79, 9.94
For Bill smith, he used the 95% confidence interval of the Laurier ex-employees irrespective of the length of the service.
The 95% confidence of interval of Laurier ex-employees (sample of 50)
The 95% confidence interval is 9.29 to 11.23
The statistician estimate is in between 8 to 10 weeks where as Bill estimate is somewhare between 9 to 11.5 weeks.
Bill was paid only for 5 weeks of pay
So Bill argument is valid
Intermediate Calculations Sample Size 50 Degrees of Freedom 48 t Value 2.010635 XBar, Sample Mean of X 11.56 Sum of Squared Differences from XBar 1192.32 Standard Error of the Estimate 1.917041 h Statistic 0.022041 Predicted Y (YHat) 9.36413 For Average Y Interval Half Width 0.572243 Confidence Interval Lower Limit 8.791887 Confidence Interval Upper Limit 9.936374