Application of VAR Model to Determine Sustainability of Short-Term Rental Accommodation

Abstract

Platforms like Airbnb have fundamentally reshaped the hospitality sector as we have known it. With its distinctive model, short-term rentals (STR) have gained significant popularity among tourists and property owners alike. As the popularity of STR continues to grow, questions arise regarding its implications for sustainable tourism. In this paper, we investigate the impact of short-term rental accommodation on residential housing prices in the centre of Prague by employing an econometric analysis of time series. For this purpose, we apply the vector autoregressive (VAR) model. In the modelling, we use data on the numbers and locations of Airbnb listings alongside data on the average housing price per square meter. Other variables did not prove to be statistically significant in the equations. Firstly, the variables need to be tested for stationarity. Based on the detection of non-stationarity in the time series, the data are then transformed using the first differences. Finally, the variables are suitable for the estimation of their parameters. Subsequently, we present an impulse response analysis and plot a forecast. The prediction is then subject to the ex-post comparison, which visualises how the prognosis of the VAR model correlates with the real values.