zbMATH — the first resource for mathematics

Simultaneous multiple change-point and factor analysis for high-dimensional time series. (English) Zbl 1398.62221
Summary: We propose the first comprehensive treatment of high-dimensional time series factor models with multiple change-points in their second-order structure. We operate under the most flexible definition of piecewise stationarity, and estimate the number and locations of change-points consistently as well as identifying whether they originate in the common or idiosyncratic components. Through the use of wavelets, we transform the problem of change-point detection in the second-order structure of a high-dimensional time series, into the (relatively easier) problem of change-point detection in the means of high-dimensional panel data. Also, our methodology circumvents the difficult issue of the accurate estimation of the true number of factors in the presence of multiple change-points by adopting a screening procedure. We further show that consistent factor analysis is achieved over each segment defined by the change-points estimated by the proposed methodology. In extensive simulation studies, we observe that factor analysis prior to change-point detection improves the detectability of change-points, and identify and describe an interesting ‘spillover’ effect in which substantial breaks in the idiosyncratic components get, naturally enough, identified as change-points in the common components, which prompts us to regard the corresponding change-points as also acting as a form of ‘factors’. Our methodology is implemented in the R package factorcpt, available from CRAN.

62M10 Time series, auto-correlation, regression, etc. in statistics (GARCH)
62H25 Factor analysis and principal components; correspondence analysis
62M07 Non-Markovian processes: hypothesis testing
Full Text: DOI
[1] Ahn, S. C.; Horenstein, A. R., Eigenvalue ratio test for the number of factors, Econometrica, 81, 1203-1227, (2013) · Zbl 1274.62403
[2] Aït-Sahalia, Y.; Xiu, D., Using principal component analysis to estimate a high dimensional factor model with high-frequency data, J. Econometrics, 201, 384-399, (2017) · Zbl 1377.62148
[3] Alessi, L.; Barigozzi, M.; Capasso, M., Improved penalization for determining the number of factors in approximate static factor models, Statist. Probab. Lett., 80, 1806-1813, (2010) · Zbl 1202.62081
[4] Bai, J., Inferential theory for factor models of large dimensions, Econometrica, 71, 135-171, (2003) · Zbl 1136.62354
[5] Bai, J.; Ng, S., Determining the number of factors in approximate factor models, Econometrica, 70, 191-221, (2002) · Zbl 1103.91399
[6] Bai, J., Han, X., Shi, Y., 2017. Estimation and Inference of Structural Changes in High Dimensional Factor Models. Tech. Rep. https://ssrn.com/abstract=2875193.
[7] Baltagi, B. H.; Kao, C.; Wang, F., Identification and estimation of a large factor model with structural instability, J. Econometrics, 197, 87-100, (2017) · Zbl 1443.62173
[8] Barigozzi, M.; Hallin, M., A network analysis of the volatility of high dimensional financial series, J. R. Stat. Soc. Ser. C. Appl. Stat., 66, 581-605, (2017)
[9] Barnett, I.; Onnela, J.-P., Change point detection in correlation networks, Sci. Rep., 6, (2016)
[10] Bates, B. J.; Plagborg-Møller, M.; Stock, J. H.; Watson, M. W., Consistent factor estimation in dynamic factor models with structural instability, J. Econometrics, 177, 289-304, (2013) · Zbl 1288.62125
[11] Bosq, D., Nonparametric statistics for stochastic process: estimation and prediction, (1998), Springer · Zbl 0902.62099
[12] Brault, V., Ouadah, S., Sansonnet, L., Lévy-Leduc, C., 2016. Nonparametric homogeneity tests and multiple change-point estimation for analyzing large hi-c data matrices, arXiv preprint arXiv:1605.03751. · Zbl 1397.62186
[13] Breitung, J.; Eickmeier, S., Testing for structural breaks in dynamic factor models, J. Econometrics, 163, 71-84, (2011) · Zbl 1441.62615
[14] Brodsky, B. E.; Darkhovsky, B. S., Nonparametric methods in change-point problems, (1993), Springer
[15] Chamberlain, G.; Rothschild, M., Arbitrage, factor structure, and mean-variance analysis on large asset markets, Econometrica, 51, 1281-1304, (1983) · Zbl 0523.90017
[16] Chen, L.; Dolado, J. J.; Gonzalo, J., Detecting big structural breaks in large factor models, J. Econometrics, 180, 30-48, (2014) · Zbl 1298.62145
[17] Cheng, X.; Liao, Z.; Schorfheide, F., Shrinkage estimation of high-dimensional factor models with structural instabilities, Rev. Econom. Stud., 83, 1511-1543, (2016) · Zbl 1409.62143
[18] Cho, H., Change-point detection in panel data via double CUSUM statistic, Electron. J. Stat., 10, 2000-2038, (2016) · Zbl 1397.62301
[19] Cho, H., Barigozzi, M., Fryzlewicz, P., 2016. : Simultaneous change-point and factor analysis, R package version 0.1.2. · Zbl 1398.62221
[20] Cho, H.; Fryzlewicz, P., Multiscale interpretation of taut string estimation and its connection to unbalanced Haar wavelets, Stat. Comput., 21, 671-681, (2011) · Zbl 1221.62056
[21] Cho, H.; Fryzlewicz, P., Multiscale and multilevel technique for consistent segmentation of nonstationary time series, Statist. Sinica, 22, 207-229, (2012) · Zbl 1417.62240
[22] Cho, H.; Fryzlewicz, P., Multiple change-point detection for high-dimensional time series via sparsified binary segmentation, J. R. Stat. Soc. Ser. B Stat. Methodol., 77, 475-507, (2015) · Zbl 1414.62356
[23] Corradi, V.; Swanson, N. R., Testing for structural stability of factor augmented forecasting models, J. Econometrics, 182, 100-118, (2014) · Zbl 1311.62130
[24] Davis, C.; Kahan, W. M., The rotation of eigenvectors by a perturbation. III, SIAM J. Numer. Anal., 7, 1-46, (1970) · Zbl 0198.47201
[25] Enikeeva, F., Harchaoui, Z., 2015. High-dimensional change-point detection with sparse alternatives, arXiv preprint, arXiv:1312.1900.
[26] Fan, J.; Liao, Y.; Mincheva, M., High dimensional covariance matrix estimation in approximate factor models, Ann. Statist., 39, 3320-3356, (2011) · Zbl 1246.62151
[27] Fan, J.; Liao, Y.; Mincheva, M., Large covariance estimation by thresholding principal orthogonal complements, J. R. Stat. Soc. Ser. B Stat. Methodol., 75, 603-680, (2013) · Zbl 1411.62138
[28] Fan, J.; Lv, J.; Qi, L., Sparse high dimensional models in economics, Annu. Rev. Econ., 3, 291-317, (2011)
[29] Forni, M.; Giannone, D.; Lippi, M.; Reichlin, L., Opening the black box: structural factor models versus structural vars, Econometric Theory, 25, 1319-1347, (2009) · Zbl 1284.91446
[30] Forni, M.; Hallin, M.; Lippi, M.; Reichlin, L., The generalized dynamic factor model: identification and estimation, Rev. Econ. Stat., 82, 540-554, (2000)
[31] Forni, M.; Lippi, M., The generalized dynamic factor model: representation theory, Econometric Theory, 17, 1113-1141, (2001) · Zbl 1181.62189
[32] Fryzlewicz, P., Wild binary segmentation for multiple change-point detection, Ann. Statist., 42, 2243-2281, (2014) · Zbl 1302.62075
[33] Fryzlewicz, P.; Nason, G. P., Haar-fisz estimation of evolutionary wavelet spectra, J. R. Stat. Soc. Ser. B Stat. Methodol., 68, 611-634, (2006) · Zbl 1110.62121
[34] Fryzlewicz, P.; Subba Rao, S., Multiple-change-point detection for auto-regressive conditional heteroscedastic processes, J. R. Stat. Soc. Ser. B Stat. Methodol., 76, 903-924, (2014) · Zbl 1411.62248
[35] Gonçalves, S.; Perron, B., Bootstrapping factor-augmented regression models, J. Econometrics, 182, 156-173, (2014) · Zbl 1311.62040
[36] Gonçalves, S., Perron, B., 2016. Bootstrapping factor models with cross sectional dependence, Preprint.
[37] Groen, J. J.; Kapetanios, G.; Price, S., Multivariate methods for monitoring structural change, J. Appl. Econometrics, 28, 250-274, (2013)
[38] Hallin, M.; Lippi, M., Factor models in high-dimensional time series: a time-domain approach, Stochastic Process. Appl., 123, 2678-2695, (2013) · Zbl 1285.62106
[39] Han, X.; Inoue, A., Tests for parameter instability in dynamic factor models, Econometric Theory, 31, 1-36, (2014)
[40] Horváth, L.; Hušková, M., Change-point detection in panel data, J. Time Series Anal., 33, 631-648, (2012) · Zbl 1282.62181
[41] Jentsch, C.; Politis, D. N., Covariance matrix estimation and linear process bootstrap for multivariate time series of possibly increasing dimension, Ann. Statist., 43, 1117-1140, (2015) · Zbl 1320.62099
[42] Jirak, M., Uniform change point tests in high dimension, Ann. Statist., 43, 2451-2483, (2015) · Zbl 1327.62467
[43] Korostelev, A., On minimax estimation of a discontinuous signal, Theory Probab. Appl., 32, 727-730, (1987) · Zbl 0659.62103
[44] Li, J.; Todorov, V.; Tauchen, G.; Lin, H., Rank tests at jump events, J. Bus. Econom. Statist., (2018), (in press)
[45] Ma, S., Su, L., 2016. Estimation of large dimensional factor models with an unknown number of breaks, Preprint. · Zbl 1452.62414
[46] Massacci, D., Least squares estimation of large dimensional threshold factor models, J. Econometrics, 197, 101-129, (2017) · Zbl 1443.62175
[47] Merlevède, F.; Peligrad, M.; Rio, E., A Bernstein type inequality and moderate deviations for weakly dependent sequences, Probab. Theory Related Fields, 151, 435-474, (2011) · Zbl 1242.60020
[48] Nason, G. P.; von Sachs, R.; Kroisandt, G., Wavelet processes and adaptive estimation of the evolutionary wavelet spectrum, J. R. Stat. Soc. Ser. B Stat. Methodol., 62, 271-292, (2000)
[49] Omranian, N.; Mueller-Roeber, B.; Nikoloski, Z., Segmentation of biological multivariate time-series data, Sci. Rep., 5, (2015)
[50] Onatski, A., Determining the number of factors from empirical distribution of eigenvalues, Rev. Econ. Stat., 92, 1004-1016, (2010)
[51] Onatski, A., Asymptotic analysis of the squared estimation error in misspecified factor models, J. Econometrics, 186, 388-406, (2015) · Zbl 1331.62480
[52] Patton, A.; Politis, D. N.; White, H., Correction to “automatic block-length selection for the dependent bootstrap” by D. politis and H. white, Econometric Rev., 28, 372-375, (2009) · Zbl 1400.62193
[53] Pelger, M., Large-dimensional factor modeling based on high-frequency observations, tech. rep., (2015), Stanford University
[54] Politis, D. N.; Romano, J. P., The stationary bootstrap, J. Amer. Statist. Assoc., 89, 1303-1313, (1994) · Zbl 0814.62023
[55] Politis, D. N.; White, H., Automatic block-length selection for the dependent bootstrap, Econometric Rev., 23, 53-70, (2004) · Zbl 1082.62076
[56] Schröder, A.L., Ombao, H., 2016. FreSpeD: Frequency-specific change-point detection in epileptic seizure multi-channel EEG data, Preprint.
[57] Stock, J. H.; Watson, M., Forecasting in dynamic factor models subject to structural instability, (J, C.; N, S., The Methodology and Practice of Econometrics. A Festschrift in Honour of David F. Hendry, (2009), Oxford University Press), 173-205 · Zbl 1456.62219
[58] Stock, J. H.; Watson, M. W., Forecasting using principal components from a large number of predictors, J. Amer. Statist. Assoc., 97, 1167-1179, (2002) · Zbl 1041.62081
[59] Stock, J. H.; Watson, M. W., Has the business cycle changed and why?, (NBER Macroeconomics Annual 2002, vol. 17, (2003), MIT press), 159-230
[60] Sun, Z.; Liu, X.; Wang, L., A hybrid segmentation method for multivariate time series based on the dynamic factor model, Stoch. Environ. Res. Risk Assess., 31, 1-14, (2016)
[61] Trapani, L., On bootstrapping panel factor series, J. Econometrics, 172, 127-141, (2013) · Zbl 1443.62289
[62] Van Bellegem, S.; von Sachs, R., Locally adaptive estimation of evolutionary wavelet spectra, Ann. Statist., 36, 1879-1924, (2008) · Zbl 1142.62067
[63] Wang, T.; Samworth, R. J., High dimensional change point estimation via sparse projection, J. R. Stat. Soc. Ser. B Stat. Methodol., 80, 57-83, (2018) · Zbl 1439.62199
[64] Yamamoto, Y.; Tanaka, S., Testing for factor loading structural change under common breaks, J. Econometrics, 189, 187-206, (2015) · Zbl 1337.62125
[65] Yu, Y.; Wang, T.; Samworth, R. J., A useful variant of the Davis-Kahan theorem for statisticians, Biometrika, 102, 315-323, (2015) · Zbl 1452.15010
This reference list is based on information provided by the publisher or from digital mathematics libraries. Its items are heuristically matched to zbMATH identifiers and may contain data conversion errors. It attempts to reflect the references listed in the original paper as accurately as possible without claiming the completeness or perfect precision of the matching.