A utility function for producing random regressors with a specified number of degrees of freedom.
rand(df = 1, rdist = rnorm, args = list(), nrow, seed = NULL)degrees of freedom, i.e., number of random regressors
random distribution function for sampling
arguments for rdist
number of rows in resulting matrix. This can often be omitted in
the context of functions like lm where it is inferred from the data frame,
if one is provided.
seed for random number generation
A matrix of random variates with df columns.
In its intended use, the number of rows will be selected to match the
size of the data frame supplied to lm
rand(2,nrow=4)
#> [,1] [,2]
#> [1,] -0.2578632 0.4079083
#> [2,] -0.4581839 0.5132579
#> [3,] 0.2708438 0.2311685
#> [4,] -2.8662993 -2.3355036
rand(2,rdist=rpois, args=list(lambda=3), nrow=4)
#> [,1] [,2]
#> [1,] 3 4
#> [2,] 4 1
#> [3,] 8 5
#> [4,] 1 0
summary(lm( waiting ~ eruptions + rand(1), faithful))
#>
#> Call:
#> lm(formula = waiting ~ eruptions + rand(1), data = faithful)
#>
#> Residuals:
#> Min 1Q Median 3Q Max
#> -12.0387 -4.4633 0.2022 3.9211 15.9570
#>
#> Coefficients:
#> Estimate Std. Error t value Pr(>|t|)
#> (Intercept) 33.49280 1.16340 28.789 <2e-16 ***
#> eruptions 10.72505 0.31680 33.855 <2e-16 ***
#> rand(1) -0.05678 0.37683 -0.151 0.88
#> ---
#> Signif. codes: 0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1
#>
#> Residual standard error: 5.925 on 269 degrees of freedom
#> Multiple R-squared: 0.8115, Adjusted R-squared: 0.8101
#> F-statistic: 578.9 on 2 and 269 DF, p-value: < 2.2e-16
#>