Scribd
Upload
29 views

W 1.42T - 1.11V According To This Model: Residuals Vs Fitted Normal Q-Q

The document analyzes a linear regression model predicting variable W based on variables T and V. Graphs of the residuals versus fitted values and a Q-Q plot show the residuals are not randomly distributed and do not fall along a linear path, indicating a linear model is not appropriate for this data. The regression output provides the coefficients, standard errors, and other model fit statistics.

Uploaded by

star6irl7
Copyright
© Attribution Non-Commercial (BY-NC)
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
29 views

W 1.42T - 1.11V According To This Model: Residuals Vs Fitted Normal Q-Q

The document analyzes a linear regression model predicting variable W based on variables T and V. Graphs of the residuals versus fitted values and a Q-Q plot show the residuals are not randomly distributed and do not fall along a linear path, indicating a linear model is not appropriate for this data. The regression output provides the coefficients, standard errors, and other model fit statistics.

Uploaded by

star6irl7
Copyright
© Attribution Non-Commercial (BY-NC)
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
You are on page 1/ 1

Cindy Wang Stat 224 Problem Set 5 1. The Residuals v.

Fitted values graph shows us that the distribution of residuals are not random. Residuals near the ends are more negative than the residuals near the middle of the fitted values. The QQ plot also shows us the standardized residuals do not all fall nicely on the linear path. Therefore, a linear model would not be appropriate.
Residuals vs Fitted
111

Normal Q-Q
4
111 101

30

101

91

Standardized residuals

91

Residuals

20

10

-10

-150

-100

-50 Fitted values lm(W ~ T + V)

50

-1

-2

-1

Theoretical Quantiles lm(W ~ T + V)

> summary(lin) Call: lm(formula = W ~ T + V) Residuals: Min 1Q -11.560 -6.106 Median -1.791 3Q 4.336 Max 33.704

Coefficients: Estimate Std. Error t value Pr(>|t|) (Intercept) -9.05664 1.71960 -5.267 6.4e-07 *** T 1.41867 0.02301 61.661 < 2e-16 *** V -1.10545 0.05530 -19.989 < 2e-16 *** --Signif. codes: 0 *** 0.001 ** 0.01 * 0.05 . 0.1 1 Residual standard error: 8.7 on 117 degrees of freedom Multiple R-squared: 0.9729, Adjusted R-squared: 0.9724 F-statistic: 2101 on 2 and 117 DF, p-value: < 2.2e-16

W = 1.42T -1.11V according to this model

You might also like