Testing for Multiple Bubbles in Asset Prices


  • Nikolaus Landgraf




Bubbles, Test Statistics, Monte Carlo


Detecting the presence of bubbles in asset prices has become a major interest for policy makers and central banks. By an early identification of a bubble it might be possible for them to intervene and prevent the asset price from collapsing. For this purpose, several econometric tests were invented and some of which summarized by Homm and Breitung (2011). The power of one of the statistics, the sup augmented Dickey- Fuller (SADF) statistic, was improved by Phillips, Shi and Yu (2012). They developed a new recursive strategy and proposed the general SADF statistic.The present thesis approaches the sup Bhargava and the sup DFC statistic similarly and computes the power of all statistics on five different bubble generating processes using Monte Carlo Simulations. It turned out that the modified DFC statistic and the general SADF statistic have highest rejection frequencies on processes that generate multiple bubbles, while the simple sup DFC statistic performed best on processes that do not burst. Application was conducted to the internet currency Bitcoin and the Japanese stock Index Nikkei 225. In both instances, the findings of the power investigation were confirmed. Since both series include bursting bubbles, the simple sup Bhargava and sup DFC statistics were not able to detect a bubble. On the other hand, the modified sup DFC and the general SADF statistics showed clear evidence in favor of the presence of a bubble in both series.


Banerjee, A. N., Chevillon, G., and Kratz, M. (2013). Detecting and forecasting large deviations

and bubbles in a near-explosive randomcoe fficientmodel. Available at SSRN 2337438.

Colombo, J. (2012). Japan’s bubble economy of the 1980s.

Dash, M. (2001). Tulipomania. Broadway Books.

Diba, B. T. and Grossman, H. I. (1988). Explosive rational bubbles in stock prices? The American

Economic Review, pages 520–530.

Evans, G. W. (1991). Pitfalls in testing for explosive bubbles in asset prices. The American Economic

Review, pages 922–930.

Gouriéroux, C., Zakoian, J.-M., et al. (2013). Explosive bubble modelling by noncausal process.

Technical report.

Greenspan, A. (2002). Economic volatility.

Holt, J. (2009). A summary of the primary causes of the housing bubble and the resulting credit

crisis: A non-technical paper. The Journal of Business Inquiry, 8(1):120–129.

Homm, U. and Breitung, J. (2012). Testing for speculative bubbles in stock markets: a comparison

of alternative methods. Journal of Financial Econometrics, 10(1):198–231.

Impoco, J. (2008). Life after the bubble: How japan lost a decade. The New York Times.

Nakamoto, S. (2008). Bitcoin: A peer-to-peer electronic cash system. Consulted, 1(2012):28.

Phillips, P. C., Shi, S.-P., and Yu, J. (2012). Testing formultiple bubbles.

Phillips, P. C., Wu, Y., and Yu, J. (2011). Explosive behavior in the 1990s nasdaq: When did exuberance

escalate asset values?*. International economic review, 52(1):201–226.

Williams, M. (2014). Virtual currencies - bitcoin risk. In World Bank Conference Washington,