AOAC Gluten Quantitative Validation Guidance-Round 1(Nov 2023)

1a or 2a 1a or 2a 1a or2a 1a or 2a 1a or 2a 1b or 2b 1b or 2b 1b or 2b 1b or 2b

2 2 2 4 4 2 2 2 4

2 2 2 4 4 2 2 2 4

1 2 4 2 4 1 2 6 6

No No Yes Yes Yes No No Yes Yes

Not Nested Not Nested

Nested Nested Nested

Not Nested Not Nested

Nested Nested

90 The idea here is if you just have 2 analysts and 2 days, you can only have enough separation for nested if 91 you have a different calibration for each day/lot combination. If you have 4 trained analysts in the lab 92 and you can spare them, then you can get separation that way. This is assuming calibration is the 93 significant source of variation, which is usually the case in ELISA methods. In fact, Day is usually always 94 confounded with calibration for a traditional ELISA. The case where there is a common calibration might 95 be if there is a pre-calibrated kit and the calibration is associated with the lot at the factory. If you can’t 96 get separation, it is not a problem. You just need to differentiate before the analysis happens so you get 97 the correct ANOVA estimates. 98 Model Statements in R 99 For the nested ANOVA analysis, we will be using R package VCA, which was developed by CLSI for doing 100 method validation on clinical analyses. Information can be found at https://cran.r- 101 project.org/web/packages/VCA/index.html and https://cran.r-project.org/web/packages/VCA/VCA.pdf 102 Model statements in R have the general form: 103 Response ~ terms 104 Where “Response” is the numeric response vector and “terms” is a series of terms indicating the 105 predictor variables in some correct syntax dependent on the command being used. 106 For VCA package in general, we will use the following two types of model statements: 107 If Analyst is nested: Result ~ Lot/Analyst/TP 108 If Analyst is not nested: Result ~ (Lot+Analyst)/TP 109 The names used here such as “Lot,” “Analyst,” “TP” and “Result” are objects defined when the data 110 table is read into the software, and may change depending on the data table. 111 Example Code for 3-level ANOVA (Designs 1a and 1b): 112 Library(VCA) 113 Data1<- read.csv("Test Data A1b.csv") 114 fit1<- fitVCA(form=Result~(Lot+Analyst), Data=Data1) # Analyst not nested within Lot 115 fit2<- fitVCA(form=Result~Lot/Analyst, Data=Data1) # Analyst nested within Lot

116 117 118 119

Example Code for 4-level ANOVA (Designs 2a and 2b):

library(VCA)

120

Data2<- read.csv("Test Data A2b.csv")