Interlude II (simulations) [RSABE / ABEL]

posted by PharmCat  – Russia, 2020-08-20 00:26 (1285 d 20:16 ago) – Posting: # 21890
Views: 5,364

Hi Helmut!

using DataFrames, CSV, ReplicateBE, LinearAlgebra

path      = dirname(@__FILE__)
dfa       = CSV.File(path*"/sim500-2x3x3.csv") |> DataFrame
dfa.logpk = log.(dfa.PK)

res = Vector{Any}(undef, 500)
pd  = Vector{Any}(undef, 500)
os  = Vector{Any}(undef, 500)
for i in 1:500
    df = filter(r -> i == r.set , dfa)
    res[i] = ReplicateBE.rbe!(df, dvar = :logpk, subject = :subject, formulation = :treatment, period = :period, sequence = :sequence, g_tol = 1e-10, singlim = 1e-12)
    pd[i]  = isposdef(Symmetric(res[i].result.H))
    os[i]  = ReplicateBE.optstat(res[i])
    println(i)
end
println("Positive definite: ", sum(pd), "(",sum(pd)/500*100,"%)")
println("Converged: ", sum(os), "(",sum(os)/500*100,"%)")


Positive definite: 332(66.4%)
Converged: 500(100.0%)

I can make table with results if necessary.

Complete thread:

UA Flag
Activity
 Admin contact
22,912 posts in 4,806 threads, 1,635 registered users;
28 visitors (0 registered, 28 guests [including 5 identified bots]).
Forum time: 19:43 CET (Europe/Vienna)

[…] an inappropriate study design is incapable of answering
a research question, no matter how careful the subsequent
methodology, conduct, analysis, and interpretation:
Flawless execution of a flawed design achieves nothing worthwhile.    J. Rick Turner

The Bioequivalence and Bioavailability Forum is hosted by
BEBAC Ing. Helmut Schütz
HTML5