weighted_line function

Weighted Robust Line Fitting

weighted_line fits a robust line and allows weights.

weighted_line(x, y = NULL, w, na.rm = FALSE, iter = 1)

## S3 method for class 'medline'
print(x, ...)
## S3 method for class 'medline'
coef(object, ...)
## S3 method for class 'medline'
residuals(object, ...)
## S3 method for class 'medline'
fitted(object, ...)

Arguments

• x: [numeric vector] explanatory variable.
• y: [numeric vector] response variable (default: NULL).
• w: [numeric vector] weights (same length as x).
• na.rm: [logical] indicating whether NA values should be removed before the computation proceeds (default: FALSE).
• iter: [integer] number of iterations to use (default: 1).
• object: object of class medline.
• ...: additional arguments passed to the method.

Details

weighted_line uses different quantiles for splitting the sample than stats::line().

Returns

intercept and slope of the fitted line

See Also

Overview (of all implemented functions)

line

Examples

head(cars)

# compute weighted line
weighted_line(cars$speed, cars$dist, w = rep(1, length(cars$speed)))
m <- weighted_line(cars$speed, cars$dist, w = rep(1:10, each = 5))
m
coef(m)
residuals(m)
fitted(m)