In msperlin/afedR: Data and Functions for Book "Analyzing Financial and Economical Data with R"

set.seed(5)

# number of obs
n_row <- 1000

# set x as Normal (0, 1)
x <- rnorm(n_row)

# set coefficients
my_alpha <- 1.5
my_beta <- 0.5

# build y
y <- my_alpha + my_beta*x + rnorm(n_row)

library(tidyverse)

my_lm <- lm(formula = y ~ x, data = tibble(x, y))

summary(my_lm)

library(gvlma)

# global validation of model
gvmodel <- gvlma(my_lm) 

# print result
summary(gvmodel)

# none
#my_answers <- make_random_answers(my_sol)
my_answers <- rep(NA, 5)

Question

Use the gvlma package to test the OLS assumptions for the model previously estimated. Does the model pass all tests? If not, increase the value of n_row to 1000 and try again. Did the increase in the number of observations of the model impact the assumptions test? In what way?

Solution

The estimated model has not passed all the tests. In fact, not even the increase in the number of observations in the simulation resulted in the approval of the model in all aspects.

Meta-information

extype: string exsolution: r mchoice2string(c(TRUE, FALSE, FALSE, FALSE, FALSE), single = TRUE) exname: "function 01" exshuffle: TRUE

msperlin/afedR documentation built on Sept. 11, 2022, 9:49 a.m.