- CFA Exams
- CFA Level I Exam
- Study Session 2. Quantitative Methods (1)
- Reading 4. Introduction to Linear Regression
- Subject 3. The standard error of estimate and the coefficient of determination

###
**CFA Practice Question**

Which of the following statements is true with respect to the Standard Error of the Estimate (SEE)?

II. SEE requires the summation of the squares of the differences between the predicted values of Y and the mean of Y.

III. SEE requires n-2 degrees of freedom.

IV. SEE will always decrease as more observations are added.

I. SEE measures the dispersion around the regression line.

II. SEE requires the summation of the squares of the differences between the predicted values of Y and the mean of Y.

III. SEE requires n-2 degrees of freedom.

IV. SEE will always decrease as more observations are added.

Correct Answer: I and III

Standard Error of Estimate (SEE) may be found as follows:

where Y-hat

_{i}is the regression for the Y value, given the X value.Therefore, II is false because SEE requires the summation of the squares of the differences between the observed value for Y and its value as predicted by the regression.

IV is also false because if these new observations have a greater dispersion from the regression line, then it will tend to enlarge the SEE.

###
**User Contributed Comments**
3

User |
Comment |
---|---|

Vonoko |
SEE for regression with 2 explanatory variables would have n-3 degrees of freedom. |

mazen1967 |
iv not alwayes but it tends to decrease see |

cfaajay |
If new addition of observations are outliers ,it will tend to increase the SEE..so its not always that increasing the number of observation will decrease the SEE. |