﻿ 银行业股票收益率的分析 Analysis of Banking Stock Returns

Statistics and Application
Vol.07 No.04(2018), Article ID:26647,13 pages
10.12677/SA.2018.74054

Analysis of Banking Stock Returns

Zixuan Wang, Yehui Huang

School of Mathematics and Physics, North China Electric Power University, Beijing

Received: Aug. 9th, 2018; accepted: Aug. 22nd, 2018; published: Aug. 29th, 2018

ABSTRACT

In this paper, we choose 21 banking stocks from all the A shares in Shanghai and Shenzhen securities markets as the background and count the rate of return of these stocks during a period of time. Then we carry out a stability test using the time series data of the rate of return of these stocks. Next, we obtain the regression equation between the rates of return of these stocks based on the method of multiple regression analysis. Finally, we try to determine which of these stocks have more obvious correlation between the rates of return and analyze the factors which can influence the rate of return of the stocks. The result shows that Huaxia Bank has the strongest correlation with other stocks on the rate of return. Also, factors, such as the business and service projects of the banks, the businesses between banks, the city and area where the banks belong and the industry development prospects, can have influence on the banking stock returns.

Keywords:The Rate of Return on Stocks, Stability Test, Time Series, Regression Equation

1. 研究背景及意义

2. 数据的来源与整理

3. 数据的描述性统计及其分析

Table 1. Display of the original data of banking stock returns (part)

Table 2. The descriptive statistics of the rate of return data of each stock

Table 3. Pearson correlation coefficients and their average values between the rate of return of each stock (part)

Table 4. Pearson correlation coefficients and their average values between the rate of return of each stock (continues Table 3)

4. 数据的平稳性检验

Figure 1. Timing diagram of the rate of return of Huaxia Bank stock

Figure 2. Autocorrelation diagram of the rate of return of Huaxia Bank stock

Figure 3. Autocorrelation diagram of the rate of return of Huaxia Bank stock

5. 多元线性回归模型的求解

Figure 4. The coefficients of each independent variable in the regression equation (using forward method)

R平方的值是0.863。R平方的值反映了回归的效果，它是一个介于0和1之间的数，R平方的值越大，即意味着模型的拟合效果越好。同样，我们采取后退法，得到的回归方程中各自变量的系数如图5所示(这里因该方法进行的步骤较多，图中未能列出前面若干步得到的回归方程，只保留了最后部分的结果)。

6. 结论

Figure 5. The coefficients of each independent variable in the regression equation (using backward method)

Figure 6. The coefficients of each independent variable in the regression equation (using stepwise regression method)

Analysis of Banking Stock Returns[J]. 统计学与应用, 2018, 07(04): 463-475. https://doi.org/10.12677/SA.2018.74054

1. 1. 张培源. 中国股票市场与宏观经济相关性研究[D]: [博士学位论文]. 北京: 中共中央党校, 2013.

2. 2. 俞庆进, 张兵. 投资者有限关注与股票收益——以百度指数作为关注度的一项实证研究[J]. 金融研究, 2012(8): 152-165.

3. 3. 罗大为. 股票收益率影响因素的实证分析[J]. 人民论坛, 2011(2): 152-153.

4. 4. 傅能普. 股票收益率影响因素的实证研究[D]: [硕士学位论文]. 重庆: 重庆大学, 2013.

5. 5. 刘珍. 通货膨胀对我国股票收益率影响研究[D]: [硕士学位论文]. 济南: 山东财经大学, 2012.

6. 6. 顾鹏. 宏观经济冲击、信息传导与中国股票市场[D]: [博士学位论文]. 南京: 南京大学, 2015.

7. 7. 杨刚齐. 股票收益率影响因素研究[J]. 中国乡镇企业会计, 2016(3): 33-35.

8. 8. 刘罗曼. 时间序列平稳性检验[J]. 沈阳师范大学学报(自然科学版), 2010, 28(3): 357-359.

9. 9. 罗芳琼, 吴春梅. 时间序列分析的理论与应用综述[J]. 柳州师专学报, 2009, 24(3): 113-117.

10. 10. 吴建春, 张子英. 评议多元线性回归分析方法[J]. 水电能源科学, 1992(2): 120-125.

11. 11. Wang, H.W., Shangguan, L.Y., Wu, J.J. and Guan, R. (2013) Multiple Linear Regression Modeling for Compositional Data. Neurocomputing, 122, 490-500. https://doi.org/10.1016/j.neucom.2013.05.025

12. 12. 王振友, 陈莉娥. 多元线性回归统计预测模型的应用[J]. 统计与决策, 2008(5): 46-47.

13. 13. 周勇. 首届应用统计专业硕士优秀案例选[M]. 北京: 中国统计出版社, 2016.

14. 14. 李丹. 华夏银行成立25周年: 不忘初心 续写华章[J]. 中国金融家, 2017(12): 98-99.

15. 15. 黄鹤, 郭城. 我国股票收益率影响因素的理论分析[J]. 全国商情, 2016(20): 80-81.

import numpy as np

import pandas as pd

data

data.max()

data.min()

data.mean()

data.var()

data.skew()

data.kurt()

JBvalue = (119/6) * (data.skew() * data.skew() + (data.kurt() - 3) * (data.kurt() - 3) * 0.25)

JBvalue