{[ promptMessage ]}

Bookmark it

{[ promptMessage ]}

Comm291_Final_Exam_2004

# Comm291_Final_Exam_2004 - The University of British...

This preview shows pages 1–3. Sign up to view the full content.

This preview has intentionally blurred sections. Sign up to view the full version.

View Full Document
Question 1 (Total 10 marks) – “True or False” (to get you started) For each of the following statements, indicate whether the statements are True or False. Parts a) through f) refer to simple linear regression; parts g) through j) are about hypothesis testing in general. Each statement is worth one mark; there is no penalty for a wrong answer. Circle True or False. No explanation is needed. a) A value of r = 0.7 means that 70% of the variation True False in Y is explained by the independent variable. b) If r 2 = 1, then it must be the case that r = 1. True False c) (1-r 2 )SST = SSE True False d) For a given level of confidence the narrowest confidence True False interval for the mean Y will occur at x . e) Let b 1 be the slope of the regression line of Y on X, and b 2 True False the slope of the regression line of X on Y, and r the sample correlation coefficient between X and Y. Then b 1 x b 2 = r 2 . f) The least squares regression line passes through ( y x , ) True False and through (0, x b y 1 - ). g) If the null hypothesis is rejected in a test, then this True False proves that the null hypothesis is false. h) A Type I error cannot be made if the null hypothesis True False is accepted. i) A good way to increase the chance of detecting a true True False difference between two means is to increase the sample size. j) A confidence interval for the population mean based
This is the end of the preview. Sign up to access the rest of the document.

{[ snackBarMessage ]}

### Page1 / 14

Comm291_Final_Exam_2004 - The University of British...

This preview shows document pages 1 - 3. Sign up to view the full document.

View Full Document
Ask a homework question - tutors are online