Persistency of price patterns in the international oil industry, 2001-2016

This paper is aimed at studying price patterns and their persistency in selected international oil companies (Exxon Mobil, British Petroleum, Royal Dutch Shell, and China Petroleum Sinopec). The proposal uses a one-step counting of price patterns and a two-step counting derived from transition probabilities of price patterns both procedures based on Japanese candlesticks. An extension of Kolmogorov–Smirnov test for discrete variables, provided by Taylor and Emerson (2011), is used to measure the statistical significance of the obtained results. Furthermore, the persistence of patterns is examined via the correlation in two-step conditional probabilities by using Blomqvist’s beta test. This method is useful to identify patterns even under market booms and busts, and in high and low volatility environments.