Running linear model (lm) across multiple grouping variables.

Source: R/grouped_lm.R

Running linear model (lm) across multiple grouping variables.

grouped_lm(
  data,
  grouping.vars,
  ...,
  output = "tidy",
  tidy.args = list(conf.int = TRUE, conf.level = 0.95),
  augment.args = list()
)

Arguments

data

Dataframe (or tibble) from which variables are to be taken.
grouping.vars

Grouping variables.
...

Additional arguments to broom::tidy, broom::glance, or broom::augment S3 method.
output

A character describing what output is expected. Two possible options: "tidy" (default), which will return the results, or "glance", which will return model summaries.
tidy.args

A list of arguments to be used in the relevant S3 method.
augment.args

A list of arguments to be used in the relevant S3 method.

Value

A tibble dataframe with tidy results from linear model.

See also

grouped_slr, grouped_tidy

Examples


# loading needed libraries
library(ggplot2)

# getting tidy output of results
grouped_lm(
  data = mtcars,
  grouping.vars = cyl,
  formula = mpg ~ am * wt,
  output = "tidy"
)

#> # A tibble: 12 x 9
#>      cyl term        estimate std.error statistic   p.value conf.low conf.high
#>    <dbl> <chr>          <dbl>     <dbl>     <dbl>     <dbl>    <dbl>     <dbl>
#>  1     4 (Intercept)   13.9      16.1      0.865  0.416       -24.1     51.9  
#>  2     4 am            30.3      17.2      1.77   0.121       -10.3     70.9  
#>  3     4 wt             3.07      5.44     0.564  0.590        -9.79    15.9  
#>  4     4 am:wt        -11.0       6.16    -1.78   0.118       -25.5      3.61 
#>  5     6 (Intercept)   63.6      14.1      4.51   0.0204       18.7    109.   
#>  6     6 am           -41.4      19.0     -2.18   0.117      -102.      19.1  
#>  7     6 wt           -13.1       4.16    -3.16   0.0511      -26.4      0.113
#>  8     6 am:wt         12.5       6.22     2.02   0.137        -7.26    32.4  
#>  9     8 (Intercept)   25.1       3.51     7.14   0.0000315    17.2     32.9  
#> 10     8 am            -2.92     25.9     -0.113  0.912       -60.5     54.7  
#> 11     8 wt            -2.44      0.842   -2.90   0.0159       -4.32    -0.563
#> 12     8 am:wt          0.439     7.63     0.0575 0.955       -16.6     17.4  
#> # … with 1 more variable: significance <chr>

# getting model summaries
# diamonds dataset from ggplot2
grouped_lm(
  data = diamonds,
  grouping.vars = c(cut, color),
  formula = price ~ carat * clarity,
  output = "glance"
)

#> # A tibble: 35 x 14
#>    cut   color r.squared adj.r.squared sigma statistic   p.value    df logLik
#>    <ord> <ord>     <dbl>         <dbl> <dbl>     <dbl>     <dbl> <dbl>  <dbl>
#>  1 Fair  D         0.915         0.906 1005.      106. 1.03e- 70    15 -1350.
#>  2 Fair  E         0.917         0.912  883.      179. 8.70e-106    13 -1830.
#>  3 Fair  F         0.917         0.912  954.      217. 9.37e-150    15 -2575.
#>  4 Fair  G         0.932         0.929  964.      273. 5.03e-164    15 -2595.
#>  5 Fair  H         0.932         0.929 1033.      332. 1.76e-161    12 -2526.
#>  6 Fair  I         0.958         0.955  794.      307. 1.14e-104    12 -1410.
#>  7 Fair  J         0.955         0.950  907.      204. 1.82e- 66    11  -973.
#>  8 Good  D         0.933         0.931  831.      600. 0            15 -5382.
#>  9 Good  E         0.927         0.926  905.      781. 0            15 -7667.
#> 10 Good  F         0.915         0.914  939.      644. 0            15 -7504.
#> # … with 25 more rows, and 5 more variables: AIC <dbl>, BIC <dbl>,
#> #   deviance <dbl>, df.residual <int>, nobs <int>