Session Details

PM04: Microsimulation Modeling in R

(Event: SMDM 42nd Annual Meeting: Virtual Meeting)

Oct 13, 2020 1:00PM - Oct 13, 2020 4:00PM

Session Type: Short Course- PM 1/2 Day

Description

Background

Many economic evaluations are conducted using Markov cohort models. However, there are many instances where an individual-level model is necessary to capture the clinical realism required for the question of interest. Microsimulation models involve the stochastic simulation of individuals and allow for much greater flexibility over cohort models. Microsimulation models can capture individual clinical pathways, can incorporate complex relationships between clinical history and future events, and more easily capture the impact of heterogeneity in patient demographics, genetics, and other baseline characteristics. Because of their increased complexity, microsimulation models are often implemented in a programming language. The freely available programming environment R can be used to implement, simulate, and analyze the results of a microsimulation model and has parallel processing capabilities, which can improve computational efficiency. In addition, R can facilitate most parts of an evaluation including data analysis to estimate input parameters values as well as documenting model results.

Course Type

Half Day

Course Level

Intermediate

Format Requirements

This course will focus on how to implement discrete-time microsimulation models in R and will involve hands-on programming exercises using code templates. This course is intended for an audience familiar with the theory of discrete-time microsimulation models who wish to learn how to implement these models in R. All participants will be expected to have a basic understanding of decision analytic modeling, including decision trees, state-transition models, probabilistic sensitivity analysis and the general premise of economic evaluation. In addition, they are assumed to have a working knowledge of base R (including data types, iteration routines (loops), functions and plots). This course requires participants to bring their own laptops with the latest versions of R and Rstudio installed. Installation instructions will be provided in advance.

Description & Objectives

This course will teach participants how to implement microsimulation models in R. We will first provide a conceptual overview of a microsimulation model and the general structure for its implementation. This will be followed by a brief review of relevant R commands and concepts, including data structures, creating variables and functions, sampling random numbers, and basic numerical manipulations. We will then engage in hands-on programming exercises to implement a simple microsimulation, followed by models of incrementally increasing complexity. By the end of the course, participants will have implemented microsimulation models with baseline patient heterogeneity, probabilities dependent on the time since the start (time-dependent) of the model as well as probabilities depending on state-residency (history-dependent). We will also cover the necessary methods to implement probabilistic sensitivity analysis (PSA) of a microsimulation model and shortly cover methods for visualizing and analyzing the output of microsimulation models. Throughout the course, we will highlight good programming principles.

At the end of the course, participants will be able to:

Construct discrete-time microsimulation models in R with any of the following elements:
- Population heterogeneity
- Time-dependent probabilities
- History-dependent probabilities, costs, and/or utilities
Visualize and analyze microsimulation outputs in R
Perform a probabilistic sensitivity analysis (PSA)
Understand computational efficiency considerations in implementing a microsimulation
Appreciate the advantages and challenges of using R in decision modeling

All the material of this short course will be provided to participants after the course for future use.

Course Director

Eline Krijkamp, MSc
- Erasmus MC, department of Epidemiology, Rotterdam, Netherlands

Course Faculty

Petros Pechlivanoglou, PhD
- Child Health Evaluative Sciences, The Hospital for Sick Children, Toronto, ON, Canada
- Fernando Alarid-Escudero, PhD
- Health Policy and Management, Division of Public Administration, Center for Research and Teaching in Economics (CIDE), Aguascalientes, AG, Mexico

Session Fees

	Fee Type	Member Fee	Non-Member Fee
This session is free
	Early:	$40.00	$40.00
	Regular:	$40.00	$40.00
	Late:	$40.00	$40.00
This session is free
	Early:	$20.00	$20.00
	Regular:	$20.00	$20.00
	Late:	$20.00	$20.00