reverse_predict: Do a reverse prediction on a linear regression

In ricoderks/Rcpm: General functions for the Center of Proteomics and Metabolomics (LUMC)

Do a reverse prediction on a linear regression

Description

Predict x values from y values. As with calibration curves, determine the concentration (x) from the peak area (y).

Usage

reverse_predict(model, new_y, level = 0.95)

Arguments

model	regression model of class lm
new_y	the new y value or multiplicate of y as a vector
level	confidence interval, default = 0.95

Value

A list with :

x	the predict x value
confidence_interval	the confidence interval of the predict value

Author(s)

Rico Derks

Examples

set.seed(123)
# dummy data
my_data <- data.frame(x = 1:10,
                      y = 1:10 + rnorm(10))

# Create linear model
model <- lm(y ~ x, 
            data = my_data)
            
# Single y
reverse_predict(model = model,
                new_y = 5)
# $x
# [1] 4.874066
# $confidence_interval
# [1] 2.578921   

# Triplicate y's
reverse_predict(model = model,
                new_y = c(5.0, 4.9, 5.3))
# $x
# [1] 4.946685
# $confidence_interval
# [1] 1.622068             

ricoderks/Rcpm documentation built on May 18, 2022, 7:49 a.m.