Norris Test

test_norris.jl

using LinearRegressionKit, StatsModels, DataFrames, CSV

y = [0.1, 338.8, 118.1, 888.0, 9.2, 228.1, 668.5, 998.5, 449.1, 778.9, 559.2, 0.3, 0.1, 778.1, 668.8, 339.3, 448.9, 10.8, 557.7, 228.3, 998.0, 888.8, 119.6, 0.3, 0.6, 557.6, 339.3, 888.0, 998.5, 778.9, 10.2, 117.6, 228.9, 668.4, 449.2, 0.2]
x = [0.2, 337.4, 118.2, 884.6, 10.1, 226.5, 666.3, 996.3, 448.6, 777.0, 558.2, 0.4, 0.6, 775.5, 666.9, 338.0, 447.5, 11.6, 556.0, 228.1, 995.8, 887.6, 120.2, 0.3, 0.3, 556.8, 339.1, 887.2, 999.0, 779.0, 11.1, 118.3, 229.2, 669.1, 448.9, 0.5]

df = DataFrame(x= x, y= y)

f = @formula(y ~ x)
lrk = regress(f, df, req_stats=["default"])
lrk

delta(a,b) = abs(a-b) ≈ 0. ?  0. : abs(a-b)

println("Norris - LRK")
println(string("delta B0 ", delta(-0.262323073774029, lrk.coefs[1])))
println(string("delta B1 ", delta(1.00211681802045, lrk.coefs[2])))
println(string("delta std err B0 ", delta(0.232818234301152, lrk.stderrors[1])))
println(string("delta std err B1 ", delta(0.429796848199937E-03, lrk.stderrors[2])))
println(string("delta resid std dev ", delta(0.884796396144373, lrk.RMSE)))
println(string("delta R2 ", delta(0.999993745883712, lrk.R2)))

using GLM
lr = GLM.lm(f, df)
println("Norris - GLM")
println(string("delta B0 ", delta(-0.262323073774029, coef(lr)[1])))
println(string("delta B1 ", delta(1.00211681802045, coef(lr)[2])))
println(string("delta std err B0 ", delta(0.232818234301152, stderror(lr)[1])))
println(string("delta std err B1 ", delta(0.429796848199937E-03, stderror(lr)[2])))
println(string("delta resid std dev ", delta(0.884796396144373, deviance(lr)/dof_residual(lr))))
println(string("delta R2 ", delta(0.999993745883712, r2(lr))))