Skip to contents

Poisson Analysis - Site Residuals.

Source: R/Analyze_Poisson.R
Analyze_Poisson.Rd

[Stable]

Usage

Analyze_Poisson(dfTransformed)

Arguments

dfTransformed

data.frame Transformed data for analysis. Data should have one record per site with expected columns: GroupID, GroupLevel, Numerator, Denominator, and Metric. For more details see the Data Model vignette: vignette("DataModel", package = "gsm"). For this function, dfTransformed should typically be created using Transform_Rate().

Value

data.frame with one row per site with columns: GroupID, Numerator, Denominator, Metric, Score, and PredictedCount.

Details

Fits a Poisson model to site-level data and adds columns capturing Residual and Predicted Count for each site.

More information can be found in The Poisson Regression Method of the KRI Method vignette.

Statistical Methods

This function fits a Poisson model to site-level data and then calculates residuals for each site. The Poisson model is run using standard methods in the stats package by fitting a glm model with family set to poisson using a "log" link. Site-level residuals are calculated using stats::predict.glm via broom::augment.

Examples

dfTransformed <- Transform_Rate(analyticsInput)

dfAnalyzed <- Analyze_Poisson(dfTransformed)
#> ℹ Fitting log-linked Poisson generalized linear model of [ Numerator ] ~ [ log( Denominator ) ].