ON THE ASYMPTOTICS OF ADF TESTS FOR UNIT ROOTS

By Yoosoon Chang, Joon Y. Park. 2002

164 citations recorded by the source corpus.

Subfields: Economics and Econometrics, Finance

View Paper: https://www.semanticscholar.org/paper/0d0e0169e6956d0ddfa03e235188e7eeabd0594a

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Economics and Econometrics

In Finance

Citations in the corpus

TESTING FOR A UNIT ROOT AGAINST TRANSITIONAL AUTOREGRESSIVE MODELS (2016, unknown): “The condition in Assumption 4.4 is very mild and the same as the one used in Chang and Park (2002) to derive the asymptotics for the ADF unit root t-test.”
BOOTSTRAP UNIT ROOT TESTS FOR TIME SERIES WITH NONSTATIONARY VOLATILITY (2007, methodology): “…op~1!+ It is also easy to verify that ck ' bk * is bounded; specifically, A1 implies that the coefficients of autoregressive representation ~A+1! satisfy i 1 ` 6 i 6bi,` * ` ~see Chang and Park, 2002, p+ 434, and references therein!+ This condition suffices for 6ck ' bk * 6 6 i 2 k 1 bi,` * ~i 1!”
The asymptotic size and power of the augmented Dickey–Fuller test for a unit root (2018, background): “It shows that this limiting distribution is identical to that obtained under the AR(∞) linearity or weak linearity assumption for {Ut}; cf. Dickey and Fuller (1981) and Chang and Park (2002).”
Nonstationarity in time series of state densities (2016, unknown): “, Chang and Park (2002), and |〈v, ut〉| ≤ ‖v‖‖ūt‖, from which it follows that E|〈v, ūt〉| p ≤ ‖v‖E‖ūt‖ p < ∞, for p > 2.”
The Performance of Panel Unit Root and Stationarity Tests: Results from a Large Scale Simulation Study (2006, result): “(2002) may be relaxed, given the results of Chang and Park (2002) brought to our attention by a referee, who derive ADF test asymptotics for p = o(T 1/2).”
HETEROSKEDASTIC TIME SERIES WITH A UNIT ROOT (2009, methodology): “10 Following the approach of Ferretti and Romo (1996), Park (2002b), and Chang and Park (2003), among others, this involves rebuilding stationary serial correlation into the bootstrap innovations.”
Bootstrap Unit‐Root Tests: Comparison and Extensions (2008, unknown): “…Cauchy–Schwartz inequality, ðn pÞ 1 Xn t¼pþ1 Xp j¼1 ð/̂j;n /jÞDyt j Xp j¼1 ð/̂j;n /jÞ2 " #1=2 ðn pÞ 1 Xn t¼pþ1 Xp j¼1 ðDyt jÞ2 " #1=2 : ð26Þ As /̂j;n /j ¼ Opððln n=nÞ1=2Þ þ oðp 1Þ (Chang and Park, 2002, Lem 3.5) and p(n) ¼ o((n/ln n)1/4), we have Xp j¼1 ð/̂j;n /jÞ2 " #1=2 ¼ Xp j¼1 fOpððln…”
Testing for unit roots in bounded time series (2014, methodology): “5 below, we can proceed as in Chang and Park (2002) to prove that”
A Sieve Bootstrap For The Test Of A Unit Root (2003, unknown): “2 in Chang and Park (2001), given the results in Lemmas A2 and A4.”
Testing for Unit Roots in Small Panels with Short-run and Long-run Cross-sectional Dependencies (2009, background): “This is well known in the unit root test literature, and can be readily shown along the lines of, e.g., Chang and Park (2002).4 However, the choice of covariates can be very important for the finite 4The proof for the asymptotic validity of our tests with Pi → ∞ is essentially identical to that of…”
LONG MEMORY TESTING IN THE TIME DOMAIN (2007, methodology): “For a given constant K, the truncation lag, p, is chosen as pK = K(T/100)1/4 ( 8 )”
Improving Size and Power in Unit Root Testing (2005, methodology): “…the stated assumptions regarding ut, the long-run variance ω2 equals 2πfu(0), where fu (·) is the spectral density of ut. 2As shown by Chang and Park (2002), the ARMA(p, q) assumption on ut can actually be replaced by the weaker assumption that ∑∞ j=0 ψjz j = 0 for every |z| ≤ 1 (and ∑∞j=0…”
Bootstrapping Unit Root Tests for Autoregressive Time Series (2005, unknown): “It is well known that under Assumptions (B1)(a) and (B2), and if pn → ∞ such that pn = o(n1/3) as n → ∞, then n(ρ̂DF − 1) ⇒ ( 1 − ∞∑ j=1 aj ) W2(1) − 1 2 ∫ 1 0 W 2(r)dr (9) (see Chang and Park 2002).”
Bootstrap Tests for Regression Models (2009, methodology): “The third and final example used in this chapter, like the first, is based upon a generalization of a test proposed in Chow (1960). The relevant procedure is Chow’s test of the null hypothesis that the regression coefficient vector is the same for all observations, with an untested auxiliary assumpt”
TESTING FOR A UNIT ROOT IN THE PRESENCE OF A POSSIBLE BREAK IN TREND (2009, background): “However, this assumption has attracted significant criticism (see, for example, Christiano, 1992) and, as a consequence, most recent approaches to this problem focus on the case where the possible break occurs at an unknown point in the sample which must be estimated in some way; see, inter alia, Zi”
UNIT ROOT TESTING IN PRACTICE: DEALING WITH UNCERTAINTY OVER THE TREND AND INITIAL CONDITION (2009, unknown): “tests of Dickey and Fuller (1979) and Said and Dickey (1984), together with the first difference demeaned/detrended von Neumann ratio tests of Bhargava (1986) and Schmidt and Phillips (1992). Taking the presence of a constant in the data generation process (DGP) as a given and working on the assumpt”