Scribd
Upload
5 views2 pages

Day 3 Problem Set

The document discusses the use of residual plots for verifying linear model assumptions, including linearity and constant variance, but notes their ineffectiveness for assessing independence. It provides specific statistical outputs for a regression analysis, including the slope (0.4674), intercept (1.3655), and standard error (1.39959), along with calculations for these values. Additionally, it explains the degrees of freedom for the regression standard error as n - 2, resulting in a value of 114 for a sample size of 116.

Uploaded by

michaelmafanire
Copyright
© All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
5 views2 pages

Day 3 Problem Set

The document discusses the use of residual plots for verifying linear model assumptions, including linearity and constant variance, but notes their ineffectiveness for assessing independence. It provides specific statistical outputs for a regression analysis, including the slope (0.4674), intercept (1.3655), and standard error (1.39959), along with calculations for these values. Additionally, it explains the degrees of freedom for the regression standard error as n - 2, resulting in a value of 114 for a sample size of 116.

Uploaded by

michaelmafanire
Copyright
© All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd

Day 3 Problem Set

1.2

A residual plot is a primary tool for verifying the assumptions of a linear model. It is specifically
used to check for linearity, constant variance (homoscedasticity), and a mean of zero. However,
it is not an effective method for evaluating the condition of independence (c), which usually
depends on how the data was collected rather than the plot itself.

1.3

The slope of the regression line is located in the statistical output under the Coef heading for the
predictor variable WingLength. The estimated slope (Beta-1) is 0.4674.

1.5

The y-intercept for the model is found in the Coef column next to the Constant label. The
estimated intercept (Beta-0) is 1.3655.

1.7

The slope represents the average change in the dependent variable. In this case, for every 1
mm increase in a sparrow’s wing length, the sparrow's weight is predicted to increase by an
average of 0.4674 grams.

1.9

The regression standard error (S) is reported as 1.39959. This value represents the typical
distance that the observed weights fall from the regression line.

You can calculate this by taking the square root of (SSE divided by n - 2). Using the numbers
from the ANOVA table:

●​ Square root of (223.31 / 114) = Square root of 1.959 = 1.39959.

In practical terms, the actual weight of a sparrow will typically deviate from the weight predicted
by its wing length by approximately 1.4 grams.

1.11

The degrees of freedom for the regression standard error are calculated as n - 2. With a sample
size of 116, the calculation is 116 - 2 = 114. This value also appears in the DF column of the
Error row in the Analysis of Variance section of the output.

You might also like