In santikka/Sima: Simulation Framework for Large-scale Individual Level Data Generation

knitr::opts_chunk$set(
    collapse = TRUE,
    comment = "#>"
)

In this example we consider a simulator for the incidence of type-2 diabetes and stroke with various risk factors as well as mortality from stroke and other causes. Interventions that aim to reduce systolic blood pressure in the population are also considered

Data files

To run the example, the following data files are needed

• The Finnish WHO MONICA data: http://www.thl.fi/publications/monica/monograph_cd/data/form04_3.zip
• Finnish mortality statistics from Statistics Finland for the year 2017. The material was downloaded from Statistics Finland's interface service on 10 May 2020 with the license CC BY 4.0: http://users.jyu.fi/~santikka/Sima/data/kuol_007_201700.csv
• Finnish age structure statistics from Statistics Finland for the year 2017. The material was downloaded from Statistics Finland's interface service on 11 May 2020 with the license CC BY 4.0: http://users.jyu.fi/~santikka/Sima/data/vaesto_3112_2017.csv

The data files (with MONICA data unzipped) should be placed to directory called data in relation to the working directory for the purposes of this example.

R scripts

The R script files required to run the example can be downloaded at http://users.jyu.fi/~santikka/Sima/diabetes_and_stroke.zip

The zip file contains the following

• diabetes_and_stroke.R is the primary script that contains the all the simulator definition and simulation runs.
• events.R contains all the event definitions.
• data.R contains the function to generate the initial population.
• functions.R contains utility function definitions that are used throughout.

The contents of these scripts are also listed in the following sections for direct viewing

Main script

The file diabetes_and_stroke.R provides the code to run the entire example

Events

The file events.R includes the event definitions

Initial population

The file data.R contains the following function for generating the initial population (of size n)

Utility functions

The file functions.R provides a set of useful functions used in defining events and the initial data

santikka/Sima documentation built on Dec. 22, 2021, 10:15 p.m.