更新終了:空売り比率と日経平均株価
- 業種別空売り集計、時系列推移、単位根検定、共和分検定、最小二乗法、一般化最小二乗法、残差の自己相関 -
アセット･マネジメント･コンサルティング株式会社 https://am-consulting.co.jp
更新日時:2019-08-27 06:00:58
Contents
- Souece:日本取引所グループ、日本経済新聞社
空売り比率の時系列推移
- 2019-04-11 ~ 2019-08-26
日経平均株価と空売り比率
時系列推移
- 2019-04-11 ~ 2019-08-26
Date 日経平均株価:終値 空売り合計:比率
Min. :2019-04-11 Min. :20261 Min. :40.60
1st Qu.:2019-05-21 1st Qu.:20980 1st Qu.:43.73
Median :2019-06-20 Median :21274 Median :45.65
Mean :2019-06-20 Mean :21292 Mean :45.64
3rd Qu.:2019-07-23 3rd Qu.:21642 3rd Qu.:47.10
Max. :2019-08-26 Max. :22308 Max. :51.50
[1] 90単位根検定/共和分検定
- CADFtest {CADFtest}
- ca.po {urca}
- 各系列の“_change“は前営業日との差。
### 単位根検定 ###
Analysis period: 2019-04-11 ~ 2019-08-26,90days
$NIKKEI225.close
ADF test
data: x
ADF(0) = -1.7879, p-value = 0.7023
alternative hypothesis: true delta is less than 0
sample estimates:
delta
-0.07719964
$ShortSalerRatio
ADF test
data: x
ADF(1) = -4.7264, p-value = 0.001269
alternative hypothesis: true delta is less than 0
sample estimates:
delta
-0.6184679
$NIKKEI225.close_change
ADF test
data: x
ADF(0) = -8.9098, p-value = 0.0000000001568
alternative hypothesis: true delta is less than 0
sample estimates:
delta
-0.9877109
$ShortSalerRatio_change
ADF test
data: x
ADF(1) = -9.096, p-value = 0.0000000000811
alternative hypothesis: true delta is less than 0
sample estimates:
delta
-1.714739 ### 共和分検定 ###
Analysis period: 2019-04-11 ~ 2019-08-26,90days
########################################
# Phillips and Ouliaris Unit Root Test #
########################################
Test of type Pu
detrending of series none
Call:
lm(formula = z[, 1] ~ z[, -1] - 1)
Residuals:
Min 1Q Median 3Q Max
-3221.4 -1116.7 99.3 1171.4 3357.1
Coefficients:
Estimate Std. Error t value Pr(>|t|)
z[, -1] 464.887 3.348 138.8 <0.0000000000000002 ***
---
Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
Residual standard error: 1452 on 89 degrees of freedom
Multiple R-squared: 0.9954, Adjusted R-squared: 0.9954
F-statistic: 1.928e+04 on 1 and 89 DF, p-value: < 0.00000000000000022
Value of test-statistic is: 0.8644
Critical values of Pu are:
10pct 5pct 1pct
critical values 20.3933 25.9711 38.3413最小二乗法
- lm {stats}
- dwtest {lmtest}
- ks.test {stats}
- confint {stats}
- Box.test {stats}
- Ljung-Box 検定のラグは15としている。
### 切片項≠0 ###
Analysis period: 2019-04-11 ~ 2019-08-26,90days
Call:
lm(formula = NIKKEI225.close_change ~ ShortSalerRatio_change,
data = datadf)
Residuals:
Min 1Q Median 3Q Max
-355.27 -79.14 7.57 99.80 263.16
Coefficients:
Estimate Std. Error t value Pr(>|t|)
(Intercept) -13.579 14.511 -0.936 0.352
ShortSalerRatio_change -39.305 4.913 -7.999 0.00000000000465 ***
---
Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
Residual standard error: 137.6 on 88 degrees of freedom
Multiple R-squared: 0.421, Adjusted R-squared: 0.4144
F-statistic: 63.99 on 1 and 88 DF, p-value: 0.000000000004646
-----------------------------------------------------------------------------
Durbin-Watson test
data: OLS_Model
DW = 1.5632, p-value = 0.0201
alternative hypothesis: true autocorrelation is greater than 0
-----------------------------------------------------------------------------
One-sample Kolmogorov-Smirnov test
data: ResidualsOLS
D = 0.081661, p-value = 0.5579
alternative hypothesis: two-sided
-----------------------------------------------------------------------------
2.5 % 97.5 %
(Intercept) -42.41738 15.25861
ShortSalerRatio_change -49.06935 -29.54053
-----------------------------------------------------------------------------
Box-Ljung test
data: ResidualsOLS
X-squared = 21.235, df = 15, p-value = 0.1295### 切片項=0 ###
Analysis period: 2019-04-11 ~ 2019-08-26,90days
Call:
lm(formula = NIKKEI225.close_change ~ ShortSalerRatio_change -
1, data = datadf)
Residuals:
Min 1Q Median 3Q Max
-368.92 -93.01 -6.38 85.64 249.79
Coefficients:
Estimate Std. Error t value Pr(>|t|)
ShortSalerRatio_change -39.395 4.909 -8.025 0.00000000000386 ***
---
Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
Residual standard error: 137.5 on 89 degrees of freedom
Multiple R-squared: 0.4198, Adjusted R-squared: 0.4133
F-statistic: 64.4 on 1 and 89 DF, p-value: 0.000000000003862
-----------------------------------------------------------------------------
Durbin-Watson test
data: OLS_Model_no_intercept
DW = 1.5488, p-value = 0.02197
alternative hypothesis: true autocorrelation is greater than 0
-----------------------------------------------------------------------------
One-sample Kolmogorov-Smirnov test
data: ResidualsOLS_no_intercept
D = 0.080482, p-value = 0.5764
alternative hypothesis: two-sided
-----------------------------------------------------------------------------
2.5 % 97.5 %
ShortSalerRatio_change -49.14908 -29.6407
-----------------------------------------------------------------------------
Box-Ljung test
data: ResidualsOLS_no_intercept
X-squared = 21.209, df = 15, p-value = 0.1303一般化最小二乗法
- gls {nlme}
- corARMA {nlme}
- ks.test {stats}
- confint {stats}
- Box.test {stats}
- 残差の系列相関の有無に拘わらず一般化最小二乗法による回帰係数を求めています。
- 最小二乗法の残差に系列相関が見られない場合、ここではAR(p=0,q=0)の結果(AIC最小)が表示されます。
- http://user.keio.ac.jp/~nagakura/zemi/GLS.pdf
- http://tokyox.matrix.jp/wiki/index.php?%E4%B8%80%E8%88%AC%E5%8C%96%E6%9C%80%E5%B0%8F%E4%BA%8C%E4%B9%97%E6%B3%95
- Ljung-Box 検定のラグは15としている。
### 切片項≠0 ###
Analysis period: 2019-04-11 ~ 2019-08-26,90days
Generalized least squares fit by REML
Model: NIKKEI225.close_change ~ ShortSalerRatio_change
Data: datadf
AIC BIC logLik
1131.438 1141.348 -561.7191
Correlation Structure: AR(1)
Formula: ~1
Parameter estimate(s):
Phi
0.2240136
Coefficients:
Value Std.Error t-value p-value
(Intercept) -14.42960 18.223033 -0.791833 0.4306
ShortSalerRatio_change -37.31784 4.276135 -8.727002 0.0000
Correlation:
(Intr)
ShortSalerRatio_change -0.017
Standardized residuals:
Min Q1 Med Q3 Max
-2.55689142 -0.53769718 0.09024844 0.71774041 1.87903597
Residual standard error: 138.0711
Degrees of freedom: 90 total; 88 residual
-----------------------------------------------------------------------------
One-sample Kolmogorov-Smirnov test
data: ResidualsGLS
D = 0.062736, p-value = 0.8485
alternative hypothesis: two-sided
-----------------------------------------------------------------------------
2.5 % 97.5 %
(Intercept) -50.14608 21.28689
ShortSalerRatio_change -45.69891 -28.93677
-----------------------------------------------------------------------------
Box-Ljung test
data: ResidualsGLS
X-squared = 21.732, df = 15, p-value = 0.115### 切片項=0 ###
Analysis period: 2019-04-11 ~ 2019-08-26,90days
Generalized least squares fit by REML
Model: NIKKEI225.close_change ~ ShortSalerRatio_change - 1
Data: datadf
AIC BIC logLik
1137.703 1145.168 -565.8513
Correlation Structure: AR(1)
Formula: ~1
Parameter estimate(s):
Phi
0.2163432
Coefficients:
Value Std.Error t-value p-value
ShortSalerRatio_change -37.42968 4.284702 -8.735656 0
Standardized residuals:
Min Q1 Med Q3 Max
-2.67220008 -0.64615843 -0.01585983 0.61591467 1.78321954
Residual standard error: 137.5424
Degrees of freedom: 90 total; 89 residual
-----------------------------------------------------------------------------
One-sample Kolmogorov-Smirnov test
data: ResidualsGLS_no_intercept
D = 0.073594, p-value = 0.6864
alternative hypothesis: two-sided
-----------------------------------------------------------------------------
2.5 % 97.5 %
ShortSalerRatio_change -45.82755 -29.03182
-----------------------------------------------------------------------------
Box-Ljung test
data: ResidualsGLS_no_intercept
X-squared = 21.708, df = 15, p-value = 0.1157
残差
- 残差の自己相関
業種別空売り集計