- CFA Exams
- CFA Level I Exam
- Topic 1. Quantitative Methods
- Learning Module 10. Simple Linear Regression
- Subject 5. Prediction Using Simple Linear Regression and Prediction Intervals
CFA Practice Question
Reg Reshin, a CFA candidate, has recently concluded that weekend beverage sales are linearly related to average
hourly wages. The regression has an intercept of 10 liters, a correlation coefficient of 0.55, and an R(squared)of 0.30. If the average hourly wage is predicted to be $20, what would be the associated prediction of weekend beverage sales in liters?
A. 11 liters.
B. 16 liters.
C. Cannot be calculated from the information provided.
Explanation: What is needed to answer the question is the slope, which is not provided.
User Contributed Comments 11
| User | Comment |
|---|---|
| sohappy | Isn't correlation coefficient the slope? |
| humphrey | slope = Cov(X,Y)/sx square correlation coefficient (ro) = Cov(X,Y)/sx * sy |
| lwang014 | "Correlation" is the slope (ie. Beta) |
| vivi2005 | is humphrey right? I just cannot find such equation in notes... |
| Mutizwa | not too sure about the divisor in humphrey's formula above. the divisor should the variance of X i.e Var X, but this is not vailable in this question. |
| lwang014 | The divisor should be the "variance of market" in order to calculate the beta |
| armanaziz | humphrey right as he says sx square which means variance of x. lwang014 wrong, correlation is r not beta. |
| Carol1 | Slope is Coefficient, and the corelation coeeficient is the relationship between coefficient. |
| Dinosaur | the correlation coefficient is r^2 |
| steved333 | coefficient of determination is r^2. correlation coefficient is r. correlation coefficient can be negative, but determination cannot. you square the r to see what percentage of the variance in y is explained by x. but percentages cannot be negative in this context. see? |
| dimitris13 | slope coefficient (b1) = Cov(X,Y)/s^2x |