Stuart Grange skgrange
skgrange
/ linking_pmf_sources_to_op_with_multiple_linear_regression_models.R
Created
November 22, 2021 10:12
Example of training multiple linear regression (MLR) models to explain/predict oxidative potential (OP) by particulate matter (PM) sources as identified by positive matrix factorisation (PMF) using simulated observations
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| # Define the helper functions --------------------------- | |
| # https://stats.stackexchange.com/questions/83826/is-a-weighted-r2-in-robust-linear-model-meaningful-for-goodness-of-fit-analys/87085 | |
| r2w <- function(model, observed){ | |
| SSe <- sum(model$w * (model$resid) ^ 2) | |
| observed <- model$resid+model$fitted | |
| SSt <- sum((model$w * observed - mean(model$w * observed)) ^ 2) | |
| value <- 1 - SSe / SSt; | |
| return(value) | |
| } |
skgrange
/ multiple_linear_regression_modelling_of_op.R
Last active
November 19, 2021 09:24
Example of training multiple linear regression (MLR) models to predict oxidative potential (OP) with other particulate matter (PM) constituents with simulated observations
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| # Define the helper functions --------------------------- | |
| # https://stats.stackexchange.com/questions/83826/is-a-weighted-r2-in-robust-linear-model-meaningful-for-goodness-of-fit-analys/87085 | |
| r2w <- function(model, observed){ | |
| SSe <- sum(model$w * (model$resid) ^ 2) | |
| observed <- model$resid+model$fitted | |
| SSt <- sum((model$w * observed - mean(model$w * observed)) ^ 2) | |
| value <- 1 - SSe / SSt; | |
| return(value) | |
| } |
skgrange
/ calculate_ebc_components.R
Last active
November 4, 2020 12:28
R function to calculate equivalent black carbon (EBC) components with the aethalometer model.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| #' Function to calculate equivalent black carbon (EBC) components with the | |
| #' aethalometer model. | |
| #' | |
| #' @param df Data frame/tibble containing aethalometer absorption observations. | |
| #' See examples for details of format required. | |
| #' | |
| #' @param uv Name of variable/column in \code{df} to be used for the UV | |
| #' absorption. | |
| #' | |
| #' @param ir Name of variable/column in \code{df} to be used for the IR |