Testing for structural stability in the whole sample

Hidalgo, Javier; Seo, Myung Hwan

doi:10.1016/j.jeconom.2013.02.008

Cited by 14 publications

(15 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…But, even in the case when t T = log T , the convergence is quite fast, and importantly the difference between the sample and theoretical quantiles at the 0.9, 0.95, and 0.99 levels was small for each value of T and DGP considered. where M T = 2 log log(T /(log T ) 3/2 ) −(1/2) log log log(T /(log T ) 3/2 ) + (1/2) log π, and to the Lagrange multiplier statistic LM t of equation (8) of Hidalgo and Seo (2013). The limiting distributions of A T and E T are reviewed in Aue and Horváth (2013).…”

Section: 2mentioning

confidence: 99%

A New Class of Change Point Test Statistics of Rényi Type

Horváth

Miller

Rice

2019

Journal of Business & Economic Statistics

View full text Add to dashboard Cite

A new class of change point test statistics is proposed that utilizes a weighting and trimming scheme for the cumulative sum (CUSUM) process inspired by Rényi (1953). A thorough asymptotic analysis and simulations both demonstrate that this new class of statistics possess superior power compared to traditional change point statistics based on the CUSUM process when the change point is near the beginning or end of the sample. Generalizations of these "Rényi" statistics are also developed to test for changes in the parameters in linear and non-linear regression models, and in generalized method of moments estimation. In these contexts we applied the proposed statistics, as well as several others, to test for changes in the coefficients of Fama-French factor models. We observed that the Rényi statistic was the most effective in terms of retrospectively detecting change points that occur near the endpoints of the sample.

show abstract

Section: 2mentioning

confidence: 99%

A New Class of Change Point Test Statistics of Rényi Type

Horváth

Miller

Rice

2019

Journal of Business & Economic Statistics

View full text Add to dashboard Cite

show abstract

“…In Theorem , we derive the joint limit distribution of

M_{T}^{*}, M_{T}^{(1)}

and

M_{T}^{(2)}

, where

M_{T}^{*} = \max_{M^{*}} \sum_{j = 2}^{m} M_{j} (k_{j - 1}, k_{j}) with M^{*} = {1 < k_{2} ⩽ \dots ⩽ k_{m} < T},

M_{T}^{(1)} = \max_{1 ⩽ k ⩽ T} M_{1} (k) and M_{T}^{(2)} = \max_{1 ⩽ k < T} M_{m + 1} (k) .

Owing to the standardization, the limit distributions of M 1 ( k 1 ) and

M_{frakturm + 1} (k_{frakturm})

are non‐standard, and they do not follow from weak convergence type results. For the application of the Lagrange multiplier type statistics using the whole sample, we refer to Hidalgo and Seo (). Jeng () surveys CUSUM and related procedures in financial applications.…”

Section: Introductionmentioning

confidence: 99%

“…Owing to the standardization, the limit distributions of M 1 .k 1 / and M mC1 .k m / are non-standard, and they do not follow from weak convergence type results. For the application of the Lagrange multiplier type statistics using the whole sample, we refer to Hidalgo and Seo (2013). Jeng (2015) surveys CUSUM and related procedures in financial applications.…”

Section: Introductionmentioning

confidence: 99%

Detecting at‐Most‐m Changes in Linear Regression Models

Horváth

Pouliot

Wang

2016

Journal Time Series Analysis

View full text Add to dashboard Cite

show abstract

“…Standard structural break tests (see e.g. Andrews, 1993;Hidalgo and Seo, 2013) may be employed to test this null hypothesis, which have power against general types of parameter instability in the linear regression. Furthermore, we expect our subsequent findings can be extended to the model with more than one break but we focus on the one break model for the clarity of our exposition.…”

Section: Structural Break Model Under Mis-specificationmentioning

confidence: 99%

Structural-break models under mis-specification: Implications for forecasting

Koo

Seo

2015

Journal of Econometrics

Self Cite

View full text Add to dashboard Cite

a b s t r a c tThis paper revisits the least squares estimator of the linear regression with a structural break. We view the model as an approximation to the true data generating process whose exact nature is unknown but perhaps changing over time either continuously or with some jumps. This view is widely held in the forecasting literature and under this view, the time series dependence property of all the observed variables is unstable as well. We establish that the rate of convergence of the estimator to a properly defined limit is at most the cube root of T , where T is the sample size, which is much slower than the standard super consistent rate. We also provide an asymptotic distribution of the estimator and that of the Gaussian quasi likelihood ratio statistic for a certain class of true data generating processes. We relate our finding to current forecast combination methods and propose a new averaging scheme. Our method compares favourably with various contemporary forecasting methods in forecasting a number of macroeconomic series.

show abstract

Testing for structural stability in the whole sample

Cited by 14 publications

References 31 publications

A New Class of Change Point Test Statistics of Rényi Type

A New Class of Change Point Test Statistics of Rényi Type

Detecting at‐Most‐m Changes in Linear Regression Models

Structural-break models under mis-specification: Implications for forecasting

Contact Info

Product

Resources

About