Diagnosis
Francesc Carmona
29 de marzo de 2019
Los ejercicios con (∗) son opcionales, con (∗∗) además son difíciles.
Ejercicios del libro de Faraway
1. (Ejercicio 1 cap. 6 pág. 97)
Using the sat dataset, fit a model with the total SAT score as the response and expend, salary,
ratio and takers as predictors. Perform regression diagnostics on this model to answer the following
questions. Display any plots that are relevant. Do not provide any plots about which you have
nothing to say. Suggest possible improvements or corrections to the model where appropriate.
(a) Check the constant variance assumption for the errors.
(b) Check the normality assumption.
(c) Check for large leverage points.
(d) Check for outliers.
(e) Check for influential points.
(f) Check the structure of the relationship between the predictors and the response.
2. (Ejercicio 2 cap. 6 pág. 97)
Using the teengamb dataset, fit a model with gamble as the response and the other variables as
predictors. Answer the questions posed in the previous question.
3. (Ejercicio 3 cap. 6 pág. 97)
For the prostate data, fit a model with lpsa as the response and the other variables as predictors.
Answer the questions posed in the first question.
4. (Ejercicio 4 cap. 6 pág. 97)
For the swiss data, fit a model with Fertility as the response and the other variables as predictors.
Answer the questions posed in the first question.
5. (Ejercicio 5 cap. 6 pág. 97)
Using the cheddar data, fit a model with taste as the response and the other three variables as
predictors. Answer the questions posed in the first question.
6. (∗) (Ejercicio 6 cap. 6 pág. 98)
Using the happy data, fit a model with happy as the response and the other four variables as
predictors. Answer the questions posed in the first question.
7. (∗) (Ejercicio 7 cap. 6 pág. 98)
Using the tvdoctor data, fit a model with life as the response and the other two variables as
predictors. Answer the questions posed in the first question.
8. (∗) (Ejercicio 8 cap. 6 pág. 98)
For the divusa data, fit a model with divorce as the response and the other variables, except year
as predictors. Check for serial correlation.
9. (Ejercicio 3 cap. 7 pág. 110)
Using the divusa data:
(a) Fit a regression model with divorce as the response and unemployed, femlab, marriage,
birth and military as predictors. Compute the condition numbers and interpret their mean-
ings.
(b) For the same model, compute the VIFs. Is there evidence that collinearity causes some pre-
dictors not to be significant? Explain.
(c) Does the removal of insignificant predictors from the model reduce the collinearity? Investigate.
10. (Ejercicio 4 cap. 7 pág. 110)
For the longley data, fit a model with Employed as the response and the other variables as pre-
dictors.
(a) Compute and comment on the condition numbers.
(b) Compute and comment on the correlations between the predictors.
(c) Compute the variance inflation factors.
11. (Ejercicio 5 cap. 7 pág. 110)
For the prostate data, fit a model with lpsa as the response and the other variables as predictors.
(a) Compute and comment on the condition numbers.
(b) Compute and comment on the correlations between the predictors.
(c) Compute the variance inflation factors.
12. (∗) (Ejercicio 8 cap. 7 pág. 111)
Use the fat data, fitting the model described in Section 4.2.
(a) Compute the condition numbers and variance inflation factors. Comment on the degree of
collinearity observed in the data.
(b) Cases 39 and 42 are unusual. Refit the model without these two cases and recompute the
collinearity diagnostics. Comment on the differences observed from the full data fit.
(c) Fit a model with brozek as the response and just age, weight and height as predictors.
Compute the collinearity diagnostics and compare to the full data fit.
(d) Compute a 95% prediction interval for brozek for the median values of age, weight and
height.
(e) Compute a 95% prediction interval for brozek for age=40, weight=200 and height=73. How
does the interval compare to the previous prediction?
(f) Compute a 95% prediction interval for brozek for age=40, weight=130 and height=73. Are
the values of predictors unusual? Comment on how the interval compares to the previous two
answers.
Página 2 de 3
Ejercicios del libro de Carmona
1. (∗) (Ejercicio 9.1 del Capítulo 9 página 172)
Realizar el análisis completo de los residuos del modelo de regresión parabólico propuesto en la
sección 1.2 con los datos de tráfico.
2. (∗) (Ejercicio 9.2 del Capítulo 9 página 172)
Realizar el análisis completo de los residuos de los modelos de regresión simple y parabólico pro-
puestos en la sección 1.2 con los datos de tráfico, pero tomando como variable respuesta la velocidad
(sin raíz cuadrada). Este análisis debe justificar la utilización de la raíz cuadrada de la velocidad
como variable dependiente.
Página 3 de 3
