Testing for Structural Breaks in Small Samples

What Makes Growth Sustained?

“…At the ten percent significance level and h = 5, our algorithm identifies a total of 290 breaks-139 "upbreaks" and 151 "downbreaks", that is, a little more than one upbreak and one downbreak per country on average. This is dramatically higher than the total number of breaks (74) that the standard Bai-Perron algorithm identifies using the same data, p-value and interstitiary period, and is consistent with the findings reported in Antoshin, Berg, and Souto (2008). Upbreaks tend to be most common in the 1950s and 60s, driven by Europe and Latin America, and in the 1990s, driven by Africa (see figure and Table 1).…”

“…Our approach differs from the Bai-Perron approach in that it uses sample-specific critical values that take into account heteroskedasticity and small sample size as opposed to asymptotic critical values; and in that it extends Bai-Perron's algorithm for sequential testing of structural breaks, as described below. Antoshin, Berg, and Souto (2008) describes these extensions in more detail and shows that they improve both the power and size properties of the test in applications such as ours.…”

Application of a breakpoint model to population growth in Türkiye

“…The size and power of tests for structural change, the coverage rates of the confidence intervals for the break periods, as well as the advantages and disadvantages of model selection procedures were studied by Bai and Perron (2003). Hence, Bai and Perron developed a methodology for finding multiple structural breaks in time series and testing their statistical significance (Antoshin, Berg, and Souto, 2008). In the opinion of Antoshin, Berg, and Souto (2008), the simulation analysis handled in Bai and Perron shows that the size and power of their tests may be significantly distorted by several factors, such as small sample sizes, small break size, breaks clustering and apply of heteroskedasticity, and autocorrelation corrections.…”

“…Hence, Bai and Perron developed a methodology for finding multiple structural breaks in time series and testing their statistical significance (Antoshin, Berg, and Souto, 2008). In the opinion of Antoshin, Berg, and Souto (2008), the simulation analysis handled in Bai and Perron shows that the size and power of their tests may be significantly distorted by several factors, such as small sample sizes, small break size, breaks clustering and apply of heteroskedasticity, and autocorrelation corrections. The sequential Bai-Perron test is considered a more advanced and compounded way to detect structural breaks.…”

Robust Correlates of Growth Spells: Do Inequality and Redistribution Matter?

“…First, following Antoshin, Berg, and Souto (2008) we employ a variant of the Bai and Perron (1998) procedure to test for multiple structural breaks in time series when both the total number and the location of breaks are unknown. Second, we employ an economic filter to the identified structural breaks as proposed by Berg, Ostry, and Zettelmeyer (2012) to identify spells in economic growth in 153 countries for which internationally comparable output data are available using version 7.1 of the Penn World Tables.…”