Dpananos

SET VARIABLE EXPERIMENT_START_DATE = TIMESTAMP '2024-10-01 00:00:00';
SET VARIABLE EXPERIMENT_END_DATE = TIMESTAMP '2024-10-31 00:00:00';


with prep_cleaned_exposures as (
  select distinct
    userid, 
    treatment,
    min(exposure_time) over (partition by userid) as exposure_time,
    (min(treatment) over (partition by userid)) <> (max(treatment) over (partition by userid)) as multiple_exposures

Dpananos

library(WeightIt)
library(tidyverse)
library(furrr)

plan(multisession, workers = 10)

sim <- function(n, l1, l2, l3, l4, ate, prop_br, ps_model_formula, simnum, ...) {
  

  withr::with_seed(simnum, {

Dpananos

library(tidyverse)

# Genuine confounding example.  Sex confounds relationship between drug and death

set.seed(0)
n <- 1000000
is_male <- rbinom(n, 1, 0.5)
drug <- rbinom(n, 1, 0.6 + 0.3*is_male)
y <- rbinom(n, 1, 0.4 - 0.1*drug + 0.4*is_male)
d <- tibble(drug, is_male, y)

Dpananos

# Licensed to the Apache Software Foundation (ASF) under one
# or more contributor license agreements.  See the NOTICE file
# distributed with this work for additional information
# regarding copyright ownership.  The ASF licenses this file
# to you under the Apache License, Version 2.0 (the
# "License"); you may not use this file except in compliance
# with the License.  You may obtain a copy of the License at
#
#   http://www.apache.org/licenses/LICENSE-2.0
#

Dpananos

import matplotlib.pyplot as plt
import numpy as np
from scipy.stats import multinomial
import cmdstanpy



def simulate(n_transitions):
    A = 1000
    B = 100

Dpananos

library(tidyverse)
library(marginaleffects)

g <- LETTERS[1:4]
N <- rpois(length(g), 100000)
theta <- c(0.1, 0.12, 0.14, 0.08)
y <- rbinom(length(g), N, theta)


d <- tibble(g, N, y)

Dpananos

library(survival)
library(tidyverse)
library(broom)
library(marginaleffects)


# Make a toy model
gr <- sample(letters[1:2], size = 10000, replace=T)
g <- as.numeric(gr=='a')
etime <- rexp(length(gr), rate = (5+1*g)/10)

Dpananos

import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
import pymc as pm
import arviz as az


N = 50_000
treatment_conversions = np.array([541, 557, 559, 556, 530, 532, 516, 532, 528, 544, 519, 552])
control_conversions = np.array([496, 524, 486, 500, 516, 475, 507, 475, 490, 506, 512, 489])

Dpananos

import numpy as np
from statsmodels.nonparametric.smoothers_lowess import lowess

from sklearn.datasets import load_breast_cancer
from sklearn.pipeline import Pipeline
from sklearn.preprocessing import StandardScaler
from sklearn.linear_model import LogisticRegression
from sklearn.model_selection import KFold, RepeatedKFold, GridSearchCV, cross_val_score
from sklearn.metrics import make_scorer, brier_score_loss
from sklearn.utils import resample

Dpananos

# LRT
data = c(27,24,3,14,9,14,4,6,7,8)
m = matrix(data, nrow = 2)

theta_null = colSums(m)/sum(m)
theta_1 = m[1,]/sum(m[1,])
theta_2 = m[2,]/sum(m[2,])

L0 = dmultinom(colSums(m), prob = theta_null, log=T)
L1 = dmultinom(m[1,], prob = theta_1, log=T) + dmultinom(m[2,], prob = theta_2, log=T)