are106-quiz3-key

are106-quiz3-key - by $762. In the second model: if height...

Info iconThis preview shows pages 1–2. Sign up to view the full content.

View Full Document Right Arrow Icon
University of California, Davis ARE 106 - Winter 2011 Quiz 3 Name: Student Number: 1. To derive the R 2 statistic, we decomposed the sum of squares about y i into three parts, giving a name and acronym for each. The formulas for these parts are given below. Identify each part and state which one must always be larger than the other two. (8 points) n X i =1 ( y i - ˆ y ) 2 SSE n X i =1 ( y i - ¯ y ) 2 SST. It is always greatest; recall SST = SSE + SSR n X i =1 y i - ¯ y ) 2 SSR 2. We are interested in the effect of height, H i on earnings, E i . Our dataset contains E i , a person’s average annual income in dollars and H i , his or her height in inches. We estimate the regression model: (1) E i = β 1 + β 2 H i + e i We find b 1 = 10 , 000, b 2 = 762. We convert height in inches, H i , to height in centimeters, H cm i by multiplying by a conversion factor. We estimate the model: (2) E i = β 1 + β 2 H cm i + e i We find that b 1 = 10 , 000 and b 2 = 300. (a) Interpret the b 2 estimates for each model in words. (i.e. If (blank) increases by (blank), we estimate that (blank).) (3 points) In the first model: if height increases by one inch, we expect that income increases
Background image of page 1

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

View Full DocumentRight Arrow Icon
Background image of page 2
This is the end of the preview. Sign up to access the rest of the document.

Unformatted text preview: by $762. In the second model: if height increases by one centimeter, we expect that income increases by $300. (b) Which model (1 or 2) provides better goodness-of-t to the data? Why? (4 points) Both models t the data equally well. Scaling the data does not change the R 2 which measures the goodness of t. In other words, we can measure our variables in which ever units we prefer and the conclusions drawn from our regression model remain the same. University of California, Davis ARE 106 - Winter 2011 (c) How could you solve for the conversion factor between inches and centimeters? (2 bonus points) You could divide b inches 2 by b cm 2 to get the conversion factor. The conversion factor is the constant c in the algebraic representation of scaling the data presented in class....
View Full Document

Page1 / 2

are106-quiz3-key - by $762. In the second model: if height...

This preview shows document pages 1 - 2. Sign up to view the full document.

View Full Document Right Arrow Icon
Ask a homework question - tutors are online