olr (version 1.1)

olr: olr: Optimal Linear Regression

Description

The main olr() runs all of the possible linear regression equation combinations, which are all of the combinations of dependent variables respect to the independent variable. In essence, the olr() returns the best fit linear regression model. The user can prompt the olr() to return either the best fit statistical summary of either the greatest adjusted R-squared, or the greatest R-squared term. R-squared increases with the addition of an explanatory variable whether it is 'significant' or not, thus this was developed to eliminate that conundrum. Adjusted R-squared is preferred to overcome this phenomenon, but each combination will still produce different results and this will return the best one.

Usage

olr(dataset, responseName = NULL, predictorNames = NULL,
  adjr2 = TRUE)
olrmodels(dataset, responseName = NULL, predictorNames = NULL)
olrformulas(dataset, responseName = NULL, predictorNames = NULL)
olrformulaorder(dataset, responseName = NULL, predictorNames = NULL)
adjr2list(dataset, responseName = NULL, predictorNames = NULL)
r2list(dataset, responseName = NULL, predictorNames = NULL)

Arguments

dataset

is defined by the user and points to the name of the dataset that is being used.

responseName

the response variable name defined as a string. For example, it represents a header in the data table.

predictorNames

the predictor variable or variables that are the terms that are to be regressed against the responseName. Place desired headers from the dataset in here as a character vector.

adjr2

adjr2 = TRUE returns the regression summary for the maximum adjusted R-squared term. adjr2 = FALSE returns the regression summary for the maximum R-squared term.

Value

The regression summary for the adjusted R-squared or the R-squared, specified with TRUE or FALSE in the olr().

Details

Complimentary functions below follow the format: function(dataset, responseName = NULL, predictorNames = NULL) olrmodels: returns the list of models accompanied by the coefficients. After typing in olrmodels(dataset, responseName, predictorNames) type the desired summary number to the right of the comma in the brackets: [,x] where x equals the desired summary number. For example, olrmodels(dataset, responseName, predictorNames)[,8] olrformulas: returns the list of olr() formulas olrformulasorder: returns the formulas with the predictors (dependent variables) in ascending order adjr2list: list of the adjusted R-squared terms r2list: list of the R-squared terms

When responseName and predictorNames are NULL, then the first column in the dataset is set as the responseName and the remaining columns are the predictorNames.

A 'Python' version is available at <https://pypi.org/project/olr>.

Examples

# NOT RUN {
file <- system.file("extdata", "oildata.csv", package = "olr", mustWork = TRUE)
oildata <- read.csv(file, header = TRUE)

dataset <- oildata
responseName <- 'OilPrices'
predictorNames <- c('SP500', 'RigCount', 'API', 'Field_Production', 'OperableCapacity', 'Imports')

olr(dataset, responseName, predictorNames, adjr2 = TRUE)

# }