Selecting the tuning parameter of the l1 trend filter

被引：1
|
作者：
Yamada, Hiroshi [1 ]
Yoon, Gawon [2 ]
机构：
[1] Hiroshima Univ, Dept Econ, 1-2-1 Kagamiyama, Higashihiroshima 7398525, Japan
[2] Kookmin Univ, Dept Econ, Seoul 136702, South Korea
来源：
STUDIES IN NONLINEAR DYNAMICS AND ECONOMETRICS | 2016年 / 20卷 / 01期
关键词：
Hodrick-Prescott filter; lasso; l(1) trend filter; sparsity; tuning parameter; ECONOMIC TIME-SERIES; BUSINESS CYCLES; REGRESSION; LASSO;
D O I：
10.1515/snde-2014-0089
中图分类号：
F [经济];
学科分类号：
02 ;
摘要：
The l(1) trend filter, which is similar to the popular Hodrick-Prescott (HP) filter, seems to be very promising because it enables us to estimate a piecewise linear trend without specifying the location and number of kink points a priori. Such a trend may be regarded as a result of occasional permanent shocks to the growth rate. Similarly to the HP filter, the value of the tuning parameter needs to be selected in applying this filter. This paper proposes a method for selecting the tuning parameter of the l(1) trend filter and its generalization.
引用
收藏
页码：97 / 105
页数：9
相关论文
共 50 条
  • [41] L1 regularization for detecting offsets and trend change points in GNSS time series
    Wu, Dingcheng
    Yan, Haoming
    Yuan, Shenglin
    GPS SOLUTIONS, 2018, 22 (03)
  • [42] Application of L1 Trend Filtering Technology on the Current Time Domain Spectroscopy of Dielectrics
    Suo, Changyou
    Li, Zhonghua
    Sun, Yunlong
    Han, Yongsen
    ELECTRONICS, 2019, 8 (09)
  • [43] L1 regularization for detecting offsets and trend change points in GNSS time series
    Dingcheng Wu
    Haoming Yan
    Shenglin Yuan
    GPS Solutions, 2018, 22
  • [44] FITTING A GROUNDWATER CONTAMINANT TRANSPORT MODEL BY L1 AND L2 PARAMETER ESTIMATORS
    XIANG, YY
    THOMSON, NR
    SYKES, JF
    ADVANCES IN WATER RESOURCES, 1992, 15 (05) : 303 - 310
  • [45] Tuning parameter calibration for l1-regularized logistic regression
    Li, Wei
    Lederer, Johannes
    JOURNAL OF STATISTICAL PLANNING AND INFERENCE, 2019, 202 : 80 - 98
  • [46] On the implementation of ADMM with dynamically configurable parameter for the separable l1/l2 minimization
    Wang, Jun
    Ma, Qiang
    OPTIMIZATION LETTERS, 2025, 19 (01) : 85 - 102
  • [47] Hellinger Distance-Based Parameter Tuning for ε-Filter
    Suetake, Noriaki
    Tanaka, Go
    Hashii, Hayato
    Uchino, Eiji
    IEICE TRANSACTIONS ON INFORMATION AND SYSTEMS, 2010, E93D (09) : 2647 - 2650
  • [48] A comparative analysis of L1 retrotransposition activities in human genomes suggests an ongoing increase in L1 number despite an evolutionary trend towards lower activity
    Sawsan Sami Wehbi
    Heinrich zu Dohna
    Mobile DNA, 12
  • [49] Adaptively Tuning the Scaling Parameter of the Unscented Kalman Filter
    Scardua, Leonardo Azevedo
    da Cruz, Jose Jaime
    CONTROLO'2014 - PROCEEDINGS OF THE 11TH PORTUGUESE CONFERENCE ON AUTOMATIC CONTROL, 2015, 321 : 429 - 438
  • [50] A comparative analysis of L1 retrotransposition activities in human genomes suggests an ongoing increase in L1 number despite an evolutionary trend towards lower activity
    Wehbi, Sawsan Sami
    Dohna, Heinrich Zu
    MOBILE DNA, 2021, 12 (01)
12345