vankesteren

# Packages for this script
library(tidyverse)
library(lavaan)
library(dagitty)
library(glue)
library(rstanarm)


## SIMULATION ##
# here is a true data-generating process in lavaan (SEM) syntax

vankesteren

virtual_grid <- function(...) {
  pars <- list(...)
  lens <- vapply(pars, length, 1L)
  return(structure(list(pars = pars, lens = lens), class = c("vgrid", "tbl_lazy")))
}

dim.vgrid <- function(x) {
  as.integer(c(prod(x$lens), length(x$lens)))
}

vankesteren

# panel data factor model simulation
# See hollingsworth & wing (2022) tactics for design..
# paragraph 2.3, assumption 2
n_timepoints <- 100
n_unobserved <- 1
n_units <- 200
n_covar <- 5

ru <- 0.6
mean_ly <- 1

vankesteren

# Comparing lintsampler to basic uniform importance sampling
from scipy.stats import norm, uniform
import numpy as np
import matplotlib.pyplot as plt
from lintsampler import LintSampler

NSAMPLES = 1000000

# GMM example
def gmm_pdf(x):

vankesteren

# Simple probabilistic simulation script

# Causal graph: 
# NetIncome -> + CulturalActivities
# NetIncome -> + SportsActivities
# NetIncome -> - Debts
# NetIncome -> + SocialComparison
# SportsActivities -> + Health
# SportsActivities -> + Partnership
# CulturalActivities -> + SocialComparison

vankesteren

using StatsBase: sample, mean, cor
using LinearAlgebra: norm
using Plots, Random

"""
    permutefun!(x::Vector, y::Vector, rule::Function, score::Real; tol::Number = 1e-3, max_iter::Int = 10_000, max_search::Number = 100, verbose::Bool = true)

Permute y values to approximate a functional constraint (rule) between x and y.

# Arguments

vankesteren

using Turing
using LogExpFunctions: logsumexp
using DataFrames

# The rank ordered logit model in Turing
# The rank-ordered logit likelihood
function rank_ordered_logit(ordered_skills::Vector{<:Real})
    ll = 0.0
    for m in 1:(length(ordered_skills) - 1)
        ll += ordered_skills[m] - logsumexp(ordered_skills[m:end])

vankesteren

# Ideal point model in stan / R
# example taken & simplified from https://medewitt.github.io/resources/stan_ideal_point.html
library(tidyverse)
library(cmdstanr)

# simulate data: 100 legislators, 150 votes
set.seed(1834)
N_legislators <- 50
N_bills <- 150

vankesteren

# Let's figure out this ELBO thing
using Distributions, StatsPlots, Optim, Random
Random.seed!(45)

# The target distribution. Assume we don't know it but
# we can compute the (unnormalized) logpdf and sample
# from it. For illustration, let's make it a weird mixture
comps = [Normal(2, 3), Normal(-3, 1.5), LogNormal(3, 0.4)]
probs = [.1, .1, .8]
p = MixtureModel(comps, probs)

vankesteren

#' Marginal density ratio plot
#' 
#' A plot to compare two (continuous) distributions in the
#' relative number of occurrences on a particular variable.
#' The transparency of the background histogram indicates
#' how much data is available at that location.
#' 
#' @param dr_fit fitted model from the densityratio package
#' @param var <[`data-masked`][dplyr::dplyr_data_masking]> variable from the data
#'