• Graduate program
  • Research
  • News
  • Events
    • Summer School
      • Climate Change
      • Gender in Society
      • Inequalities in Health and Healthcare
      • Business Data Science Summer School Program
      • Receive updates
    • Events Calendar
    • Events Archive
    • Tinbergen Institute Lectures
    • Conference: Consumer Search and Markets
    • Annual Tinbergen Institute Conference
  • Summer School
    • Climate Change
    • Gender in Society
    • Inequalities in Health and Healthcare
    • Business Data Science Summer School Program
    • Receive updates
  • Alumni
  • Magazine
Home | Events Archive | A Dutch Agent Based Model calibrated with Microdata
Research Master Defense

A Dutch Agent Based Model calibrated with Microdata


  • Series
    Research Master Defense
  • Speaker(s)
    Steven Hoekstra , Steven Hoekstra
  • Location
    Tinbergen Institute Amsterdam, room 1.60 (Hybrid)
    Amsterdam
  • Date and time

    August 23, 2023
    13:30 - 15:00

We develop an extension of the stock flow consistent agent based model of Poledna et al. (2023). We calibrate the model for the Dutch economy by introducing the household optimization problem of Kaplan et al. (2018) which allows for varying marginal propensities to consume. We analyse the model by means of a forecasting exercise where we compare the model to the base version of the agent based model and to a benchmark VAR model. Furthermore, we analyze the internal validity of the model by means of comparing the auto- and cross-correlations of the model to the data. Finally, we run a robustness check of the model by means of a sensitivity analysis. We find that the model match the cross-correlations and auto-correlations of the data well for some variables but less well for other variables. The extended model has similar forecast performance to the base model and the benchmark model.