summary function variables

[tinafmills]

How do you set values from the summary function ie adjusted r squared to a variable?

[FJCC]

You can see the structure of the object returned by the summary function using the str function. If I store the output of a fit in an object called FIT, then I can run

str(summary(FIT))

To get the R-squared value

DF <- data.frame(Xval = 1:5, Yval = 11:15 +rnorm(5,0,2))
FIT <- lm(Yval ~ Xval, data = DF)
summary(FIT)
#> 
#> Call:
#> lm(formula = Yval ~ Xval, data = DF)
#> 
#> Residuals:
#>       1       2       3       4       5 
#>  1.0790 -0.1979 -2.5099  1.2974  0.3313 
#> 
#> Coefficients:
#>             Estimate Std. Error t value Pr(>|t|)  
#> (Intercept)   9.5388     1.8462   5.167   0.0141 *
#> Xval          1.3981     0.5566   2.512   0.0868 .
#> ---
#> Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
#> 
#> Residual standard error: 1.76 on 3 degrees of freedom
#> Multiple R-squared:  0.6777, Adjusted R-squared:  0.5703 
#> F-statistic: 6.308 on 1 and 3 DF,  p-value: 0.08682
Rsqr <- summary(FIT)$r.squared
Rsqr
#> [1] 0.6777015

^{Created on 2020-03-13 by the reprex package (v0.3.0)}

[dromano]

And if you need the information in a table, @tinafmills, you can also use the broom package to help you store model information:

DF <- data.frame(Xval = 1:5, Yval = 11:15 +rnorm(5,0,2))
FIT <- lm(Yval ~ Xval, data = DF)

library(broom)
tidy(FIT)
#> # A tibble: 2 x 5
#>   term        estimate std.error statistic p.value
#>   <chr>          <dbl>     <dbl>     <dbl>   <dbl>
#> 1 (Intercept)    8.13      0.631     12.9  0.00101
#> 2 Xval           0.999     0.190      5.25 0.0135
glance(FIT)
#> # A tibble: 1 x 11
#>   r.squared adj.r.squared sigma statistic p.value    df logLik   AIC   BIC
#>       <dbl>         <dbl> <dbl>     <dbl>   <dbl> <int>  <dbl> <dbl> <dbl>
#> 1     0.902         0.869 0.602      27.6  0.0135     2  -3.28  12.6  11.4
#> # … with 2 more variables: deviance <dbl>, df.residual <int>

^{Created on 2020-03-13 by the reprex package (v0.3.0)}