A toolbox of permutation tests for structural change

Zeileis, Achim; Hothorn, Torsten

doi:10.1007/s00362-013-0503-4

Cited by 23 publications

(26 citation statements)

References 44 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The parameter instability tests considered have first been suggested in the context of time series regressions but can also be applied to other contexts (e.g., Hjort and Koning, ; Zeileis and Hothorn, ). More specifically, the stability of the regression coefficients is tested, using the sup LM test of Andrews () for numerical partitioning variables:

sup L M = sup_{i = \underset{̲}{i}, \dots, \bar{ı}} {(}{, \frac{i}{n}, (1 - \frac{i}{n}))}^{- 1} {(||, |{\overset{false^}{V}}^{- 1 false/ 2} n^{- 1 false/ 2} \sum_{ℓ : z_{ℓ} \leq z_{false(i false)}} x_{ℓ ∙} {\overset{false^}{italicε}}_{ℓ}|)}_{2}^{2},

where z i denotes observation i of the considered partitioning variable, after ordering according to increasing size denoted by z ( i ) .…”

Section: Methodsmentioning

confidence: 99%

“…The parameter instability tests considered have first been suggested in the context of time series regressions but can also be applied to other contexts (e.g., Hjort and Koning, 2002;Zeileis and Hothorn, 2013). More specifically, the stability of the regression coefficients is tested, using the supLM test of Andrews (1993) for numerical partitioning variables:…”

Section: Estimation: Model-based Treesmentioning

confidence: 99%

See 1 more Smart Citation

Heterogeneity and Spatial Dependence of Regional Growth in the EU: A Recursive Partitioning Approach

Wagner

Zeileis

2019

German Economic Review

Self Cite

View full text Add to dashboard Cite

We use model‐based recursive partitioning to assess heterogeneity of growth and convergence processes based on economic growth regressions for 255 European Union NUTS2 regions from 1995 to 2005. Spatial dependencies are taken into account by augmenting the model‐based regression tree with a spatial lag. The starting point of the analysis is a human‐capital‐augmented Solow‐type growth equation similar in spirit to Mankiw et al. (1992, The Quarterly Journal of Economics, 107, 407–437). Initial GDP and the share of highly educated in the working age population are found to be important for explaining economic growth, whereas the investment share in physical capital is only significant for coastal regions in the PIIGS countries. For all considered spatial weight matrices recursive partitioning leads to a regression tree with four terminal nodes with partitioning according to (i) capital regions, (ii) non‐capital regions in or outside the so‐called PIIGS countries and (iii) inside the respective PIIGS regions furthermore between coastal and non‐coastal regions. The choice of the spatial weight matrix clearly influences the spatial lag parameter while the estimated slope parameters are very robust to it. This indicates that accounting for heterogeneity is an important aspect of modeling regional economic growth and convergence.

show abstract

sup L M = sup_{i = \underset{̲}{i}, \dots, \bar{ı}} {(}{, \frac{i}{n}, (1 - \frac{i}{n}))}^{- 1} {(||, |{\overset{false^}{V}}^{- 1 false/ 2} n^{- 1 false/ 2} \sum_{ℓ : z_{ℓ} \leq z_{false(i false)}} x_{ℓ ∙} {\overset{false^}{italicε}}_{ℓ}|)}_{2}^{2},

where z i denotes observation i of the considered partitioning variable, after ordering according to increasing size denoted by z ( i ) .…”

Section: Methodsmentioning

confidence: 99%

“…The parameter instability tests considered have first been suggested in the context of time series regressions but can also be applied to other contexts (e.g., Hjort and Koning, 2002;Zeileis and Hothorn, 2013). More specifically, the stability of the regression coefficients is tested, using the supLM test of Andrews (1993) for numerical partitioning variables:…”

Section: Estimation: Model-based Treesmentioning

confidence: 99%

Heterogeneity and Spatial Dependence of Regional Growth in the EU: A Recursive Partitioning Approach

Wagner

Zeileis

2019

German Economic Review

Self Cite

View full text Add to dashboard Cite

show abstract

“…According to [12], permutation tests for structural change from the framework of [13] cannot only be derived for the simple location model but for both the nonparametric and parametric (model-based) permutation tests. Literally, they found that exchangeability of the errors might be a too strong assumption in time series applications where the dependence structure of the observations cannot be fully captured within the model.…”

Section: Literature Reviewmentioning

confidence: 99%

“…Compute the sum of squares residual for the single model and the sub sample as RSST, RSS1 and RSS2.. Calculate the reference value of the F-statistic, F using(12).…”

mentioning

confidence: 99%

Permutation Methods for Chow Test Analysis an Alternative for Detecting Structural Break in Linear Models

Aronu¹,

Okechukwu²,

Nworuh³

et al. 2019

Adv. sci. technol. eng. syst. j.

View full text Add to dashboard Cite

This study examined the performance of two proposed permutation methods for Chow test analysis and the Milek permutation method for testing structural break in linear models. The proposed permutation methods are: (1) permute object of dependent variable and (2) permute object of the predicted dependent variable. Simulation from gamma distribution and standard normal distribution were used to evaluate the performance of the methods. Also, secondary data were used to illustrate a real-life application of the methods. The findings of the study showed that method 1(permute object of dependent variable) and Method2 (permute object of the predicted dependent variable) performed better than the traditional Chow test analysis while the Chow test analysis was found to perform better than the Milek permutation for structural break. The methods were used to test whether the introduction of Nigeria Electricity Regulatory Commission (NERC) in the year 2005 has significant impact on economic growth in Nigeria. The result revealed that all the methods were able to detect presence of structural break at break point 2005. Also, the methods were used to test for structural break at January, 2015 for monthly reported cases of appendicitis in Nigeria. Result revealed that all the methods were able to detect presence of structural break at break point January, 2015.

show abstract

“…[25], [22] and [8] and the references given therein. Motivated by these results, we propose the following distribution free procedure to test H 0 : Given the original sample pair x 1 , .…”

Section: Divergence Based Testsmentioning

confidence: 99%

Two-sample homogeneity tests based on divergence measures

Wornowizki

Fried

2016

Comput Stat

View full text Add to dashboard Cite

The concept of f -divergences introduced by [2] provides a rich set of distance like measures between pairs of distributions. Divergences do not focus on certain moments of random variables, but rather consider discrepancies between the corresponding probability density functions. Thus, two-sample tests based on these measures can detect arbitrary alternatives when testing the equality of the distributions. We treat the problem of divergence estimation as well as the subsequent testing for the homogeneity of two samples. In particular, we propose a nonparametric estimator for f -divergences in the case of continuous distributions, which is based on kernel density estimation and spline smoothing. As we show in extensive simulations, the new method performs stable and quite well in comparison to several existing non-and semiparametric divergence estimators. Furthermore, we tackle the two-sample homogeneity problem using permutation tests based on various divergence estimators. The methods are compared to an asymptotic divergence test as well as to several traditional parametric and nonparametric procedures under different distributional assumptions and alternatives in simulations. According to the results, divergence based methods detect discrepancies between distributions more often than traditional methods if the distributions do not differ in location only. The findings are illustrated on ion mobility spectrometry data.

show abstract

A toolbox of permutation tests for structural change

Cited by 23 publications

References 44 publications

Heterogeneity and Spatial Dependence of Regional Growth in the EU: A Recursive Partitioning Approach

Heterogeneity and Spatial Dependence of Regional Growth in the EU: A Recursive Partitioning Approach

Permutation Methods for Chow Test Analysis an Alternative for Detecting Structural Break in Linear Models

Two-sample homogeneity tests based on divergence measures

Contact Info

Product

Resources

About