The treatment of multicollinearity in repeated trading model to construct the composite index:A solution based on parameter improvement

XIE Ruoqing, JIANG Guolin

Systems Engineering - Theory & Practice ›› 2022, Vol. 42 ›› Issue (6) : 1434-1447.

PDF(809 KB)
PDF(809 KB)
Systems Engineering - Theory & Practice ›› 2022, Vol. 42 ›› Issue (6) : 1434-1447. DOI: 10.12011/SETP2021-3007

The treatment of multicollinearity in repeated trading model to construct the composite index:A solution based on parameter improvement

  • XIE Ruoqing1,2, JIANG Guolin1
Author information +
History +

Abstract

Composite index construction is an important way and technical method to monitor the development of modern economy and society. Macro indicators of our country are characterized by 'small sample and short time', and the repeated trading model is widely used in the construction of comprehensive index. There are some methods to deal with multicollinearity:Eliminating the correlation of explanatory variables, enlarging the sample size to avoid selection bias, redefining the model form and improving the parameters' estimation. The first three are not applicable in the repeated trading model. In this paper, based on the least square estimation, a new method for multicollinearity treatment, which is different from ridge regression, is discussed. By designing the estimable model, we can find the available estimators of parameters. It provides a new perspective for dealing with multicollinearity problems in the repeated trading model. Finally, the empirical analysis on constructing national science and technology activity output index from 2010 to 2017 is carried out, and we construct the estimable model, using a very small k as a feasible value to estimate the composite index. Compared with the traditional ridge regression method and principal component regression method, we discuss the effectiveness and applicability of this new method to further reflect the practical applications of the new method in this paper.

Key words

repeated trading model / multicollinearity / ordinary least square estimation

Cite this article

Download Citations
XIE Ruoqing , JIANG Guolin. The treatment of multicollinearity in repeated trading model to construct the composite index:A solution based on parameter improvement. Systems Engineering - Theory & Practice, 2022, 42(6): 1434-1447 https://doi.org/10.12011/SETP2021-3007

References

[1] Chen R, Ji Y Y, Jiang G L, et al. Composite index construction with expert opinion[J]. Journal of Business&Economic Statistics, 2021. doi:10.1080/07350015.2021.2000418.
[2] 刘超,郑莹,刘宸琦,等.股市是经济的晴雨表吗?-基于2005-2017年沪深300指数和采购经理人指数数据[J].系统工程理论与实践, 2020, 40(1):55-68. Liu C, Zheng Y, Liu C Q, et al. Is the stock market a barometer of the economy?Based on 2005-2017 years'CSI 300 index and PMI data[J]. Systems Engineering-Theory&Practice, 2020, 40(1):55-68.
[3] Stock J, Watson M W. New indexes of coincident and leading economic indicators[J]. NBER Macroeconomics Annual, 1989, 4:351-409.
[4] 李晓芳,高铁梅.应用HP滤波方法构造我国增长循环的合成指数[J].数量经济技术经济研究, 2001(9):100-103.Li X F, Gao T M. Using HP filtering method to construct the composite index of growth cycle in China[J]. The Journal of Quantitative&Technical Economics, 2001(9):100-103.
[5] 韩艾,郑桂环,汪寿阳.广义动态因子模型在景气指数构建中的应用-中国金融周期景气分析[J].系统工程理论与实践, 2010, 30(5):803-811.Han A, Zheng G H, Wang S Y. Generalized dynamic-factor model with an application to coincident index-A prosperity analysis of the financial cycle in China[J]. Systems Engineering-Theory&Practice, 2010, 30(5):803-811.
[6] 李绍芳,刘晓星.金融系统压力:指数化测度及其溢出效应研究[J].系统工程理论与实践, 2020, 40(5):1089-1112.Li S F, Liu X X. Financial systemic stress:Index construction and spillover effect measurement[J]. Systems Engineering-Theory&Practice, 2020, 40(5):1089-1112.
[7] Bailey M J, Muth R F, Nourse H O. A regression method for real estate price index construction[J]. Journal of the American Statistical Association, 1963, 58(304):933-942.
[8] Goodman A C. Andrew court and the invention of hedonic price analysis[J]. Journal of Urban Economics, 1998, 44(2):291-298.
[9] Case K E, Shiller R J. Prices of single-family homes since 1970:New indexes for four cities[R]. National Bureau of Economic Research Working Paper Series, No. 2393, 1987.
[10] Case K E, Shiller R J. The efficiency of the market for single-family homes[J]. The American Economic Review, 1989, 79(1):125-137.
[11] 石薇,李强,王洪卫.城市住房价格指数编制方法的拓展设计及实证检验[J].数量经济技术经济研究, 2014(12):127-141.Shi W, Li Q, Wang H W. An extension in the construction of urban housing price indexes and its application[J]. The Journal of Quantitative&Technical Economics, 2014(12):127-141.
[12] 周自明,潘晶,张蒙.重复交易模型在土地价格指数编制中的应用研究[J].中国土地科学, 2010(2):45-50.Zhou Z M, Pan J, Zhang M. The application of repeat sales model in compilation of land price index[J]. China Land Science, 2010(2):45-50.
[13] 石阳,李曜.中国艺术品投资收益-整体特征与杰作效应[J].金融研究, 2013(12):194-206.Shi Y, Li Y. Income of art investment in China:Overall features and masterpiece effect[J]. Journal of Financial Research, 2013(12):194-206.
[14] 董倩.重复特征"R-H "交易法-二手房价格指数编制方法研究[J].统计研究, 2017(3):118-128.Dong Q." Repeat-Hedonic"sales method-Research on compiling the second-hand housing price index[J]. Statistical Research, 2017(3):118-128.
[15] 郑思齐,孔鹏,郭晓#
[28].类重复交易房价指数编制方法与应用[J].统计研究, 2013(12):41-47.Zheng S Q, Kong P, Guo X Y. Method and application of pseudo repeat sale housing price index[J]. Statistical Research, 2013(12):41-47.
[16] Frisch R. Statistical confluence analysis by means of complete regression systems[M]. Oslo:University Institute of Economics, 1934:5-8.
[17] Tibshirani R. Regression shrinkage and selection via the lasso[J]. Journal of the Royal Statistical Society:Series B (Methodological), 1996, 58(1):267-288.
[18] Massy W F. Principal components regression in exploratory statistical research[J]. Journal of the American Statistical Association, 1965, 60(309):234-256.
[19] Haitovsky Y. Multicollinearity in regression analysis:Comment[J]. The Review of Economics and Statistics, 1969, 51(4):486-489.
[20] 白雪梅,赵松山.对主成分分析综合评价方法若干问题的探讨[J].统计研究, 1995(6):47-51.Bai X M, Zhao S S. Discussion on some problems of comprehensive evaluation using principal component analysis[J]. Statistical Research, 1995(6):47-51.
[21] Hoerl A E. Application of ridge analysis to regression problems[J]. Chemical Engineering Progress, 1962, 58:54-59.
[22] Hoerl A E, Kennard R W. Ridge regression[M]//Encyclopedia of Statistical Sciences. New Jersey:John Wiley&Sons, 2006.
[23] 中华人民共和国科学技术部.中国科学技术指标[M].北京:科学技术文献出版社, 2007.Ministry of Science and Technology of the People's Republic of China. China science and technology indicators[M]. Beijing:Scientific and Technical Documentation Press, 2007.
[24] Seber G A. A matrix handbook for statisticians[M]. New Jersey:John Wiley&Sons, 2008.

Funding

National Natural Science Foundation of China (71773078);Youth Program of National Natural Science Foundation of China (71803134);Youth Program of Shanghai Philosophy and Social Science Foundation (2020EJB003);Shanghai Soft Science Research Base——Research Center of Shanghai Science and Technology Statistics and Analysis Project Supported by the Shanghai Foundation for Development of Science and Technology
PDF(809 KB)

847

Accesses

0

Citation

Detail

Sections
Recommended

/