lm_resid function

Fit linear regressions, with the option of removing outliers using a interactive plot of residuals.

With this function it's possible to fit linear regressions by a grouping variable, and evaluate each equation via an interactive plot of residuals, and get a data frame. with each column as a coefficient and quality of fit variables, and other output options. Works with dplyr grouping functions.

lm_resid(
  df,
  model,
  output_mode = "table",
  est.name = "est",
  keep_model = FALSE,
  rmoutliers = FALSE,
  fct_to_filter = NA,
  rmlevels = NA,
  onlyfiteddata = FALSE,
  group_print = NA
)

Arguments

• df: A data frame.
• model: A linear regression model, with or without quotes. The variables mentioned in the model must exist in the provided data frame. X and Y sides of the model must be separated by "~".
• output_mode: Selects different output options. Can be either "table", "merge", "merge_est" and "nest". See details for explanations for each option. Default: "table".
• est.name: Name of the estimated y value. Used only if est.name = TRUE. Default: "est".
• keep_model: If TRUE, a column containing lm object(s) is kept in the output. Useful if the user desires to get more information on the regression. Default: FALSE.
• rmoutliers: If TRUE, outliers are filtered out using the IQR method. Default: FALSE.
• fct_to_filter: Name of a factor or character column to be used as a filter to remove levels. Default: NA.
• rmlevels: Levels of the fct_to_filter variable to be removed from the fit Default: NA.
• onlyfiteddata: If TRUE, the output data will be the same as the fitted (and possibly filtered) data. Default: FALSE.
• group_print: This argument is only used internally by another function. Please ignore.

Returns

A data frame. Different data frame options are available using the output argument.

Details

this function uses lm_table as a basis, but calls a plot of residuals for each fitted model, for the user to evaluate. If one decides to remove any of the points, one can click and drag, and then click on the 'remove points' button. After that, one must simply click 'done' and the coefficients will be printed out.

It's possible to use the output argument to get a merged table if output="merge", that binds the original data frame and the fitted coefficients. If output="merge_est" we get a merged table as well, but with y estimated using the coefficients. If the fit is made using groups, this is taken into account, i.e. the estimation is made by group.

If output="nest", a data frame with nested columns is provided. This can be used if the user desires to get a customized output.

Examples

if (interactive() ){
  library(forestmangr)
  library(dplyr)

  data("exfm19")

  # Fit SH model:
  lm_resid(exfm19, log(VWB) ~  log(DBH) + log(TH))

}

Author(s)

Sollano Rabelo Braga sollanorb@gmail.com