[Paper Review] Quantifying the `end of history' through a Bayesian Markov-chain approach

Florian Klimm|arXiv (Cornell University)|Jan 1, 2022

Opinion Dynamics and Social Influence1 citations

TL;DR

This study applies a Bayesian Markov-chain model to historical regime data (1800–2018) to quantify the 'end of history' (EoH) as a steady-state distribution of political regimes. It estimates that 46% of countries will be full democracies in the long-term equilibrium, with autocracies expected to rise before declining, and finds characteristic lifetimes of 244 years for democracies and 69 years for autocracies—challenging the notion of a fixed, universal democratic dominance.

ABSTRACT

Political regimes have been changing throughout human history. After the apparent triumph of liberal democracies at the end of the twentieth century, Francis Fukuyama and others have been arguing that humankind is approaching an ‘end of history’ (EoH) in the form of a universality of liberal democracies. This view has been challenged by recent developments that seem to indicate the rise of defective democracies across the globe. There has been no attempt to quantify the expected EoH with a statistical approach. In this study, we model the transition between political regimes as a Markov process and—using a Bayesian inference approach—we estimate the transition probabilities between political regimes from time-series data describing the evolution of political regimes from 1800 to 2018. We then compute the steady state for this Markov process which represents a mathematical abstraction of the EoH and predicts that approximately 46% of countries will be full democracies. Furthermore, we find that, under our model, the fraction of autocracies in the world is expected to increase for the next half-century before it declines. Using random-walk theory, we then estimate survival curves of different types of regimes and estimate characteristic lifetimes of democracies and autocracies of 244 years and 69 years, respectively. Quantifying the expected EoH allows us to challenge common beliefs about the nature of political equilibria. Specifically, we find no statistical evidence that the EoH constitutes a fixed, complete omnipresence of democratic regimes.

Motivation & Objective

• To empirically quantify the 'end of history' (EoH) as a long-term equilibrium in political regime transitions.
• To test whether liberal democracy represents a stable, universal endpoint using statistical modeling.
• To assess the robustness of the EoH prediction under counterfactual historical scenarios.
• To estimate characteristic lifetimes of democracies and autocracies using random-walk theory.
• To challenge the assumption that EoH implies a fixed, complete dominance of liberal democracies.

Proposed method

• Models political regime transitions as a first-order Markov process using a 21-point ordinal scale for regime types.
• Applies Bayesian inference to estimate transition probabilities from sparse time-series data on POLITY2 scores (1800–2018).
• Uses information criteria (AIC, BIC) to select the optimal Markov chain order, confirming a first-order model is best.
• Computes the steady-state distribution of the Markov chain as a mathematical abstraction of the EoH.
• Employs random-walk theory to estimate survival curves and characteristic lifetimes of regime types.
• Conducts counterfactual analyses by modifying key historical events (USSR collapse, Arab Spring) to test model robustness.

Experimental results

Research questions

• RQ1 What is the predicted long-term distribution of political regimes under the assumption that historical transition patterns are representative of future behavior?
• RQ2 Does the data support the idea that liberal democracy constitutes a stable, universal endpoint (EoH) or is it merely a transient state?
• RQ3 How do characteristic lifetimes of democracies and autocracies compare, and what do they imply about regime stability?
• RQ4 How robust is the EoH prediction to major historical counterfactuals such as the non-collapse of the USSR or stronger Arab Spring democratisation?
• RQ5 Is there statistical evidence that the EoH represents a fixed, complete dominance of democratic regimes?

Key findings

• The steady-state distribution of political regimes predicts that approximately 46% of countries will be full democracies in the long-term equilibrium.
• The fraction of autocracies is expected to increase over the next 50 years before declining, indicating a non-monotonic transition path.
• Democracies have a characteristic lifetime of 244 years, while autocracies last on average 69 years, suggesting democracies are significantly more stable.
• Counterfactual analyses show that even major historical changes—such as the non-collapse of the USSR or stronger Arab Spring democratisation—only moderately alter the EoH prediction, with full democracies remaining the most frequent regime type.
• The model finds no statistical evidence that the EoH constitutes a fixed, complete omnipresence of democratic regimes, challenging the conventional interpretation of Fukuyama’s thesis.