Analysis
[1] "景気動向指数個別系列:先行系列:最終需要財在庫率指数(逆サイクル)(平成27年=100):内閣府"
Jan Feb Mar Apr May Jun Jul Aug Sep Oct Nov Dec
1999 99.0
2000 101.6 97.0 100.3 101.0 99.6 98.6 101.6 97.8 98.1 100.1 99.0 98.0
2001 100.6 99.4 100.3 102.2 103.3 103.8 105.7 105.8 108.7 105.2 106.2 106.3
2002 104.4 104.4 106.3 101.2 99.0 100.0 97.2 96.7 98.1 97.9 95.8 97.8
2003 100.0 95.7 97.4 95.4 94.1 94.9 95.5 95.1 92.0 91.0 96.6 89.5
2004 87.2 91.2 91.0 94.1 95.3 92.9 89.4 95.1 94.5 93.3 92.3 86.4
2005 91.5 94.6 94.0 88.9 94.1 92.4 92.8 92.5 94.1 91.3 92.6 92.8
2006 93.3 94.0 93.4 93.7 90.8 91.1 93.3 91.2 90.8 93.9 92.9 92.4
2007 91.3 90.7 90.9 91.5 91.8 93.5 92.4 92.3 95.8 94.1 95.9 95.8
2008 92.9 92.9 98.3 88.9 90.7 95.8 95.6 101.2 100.2 102.5 110.6 115.3
2009 135.9 138.4 131.9 130.1 128.1 120.6 117.0 113.1 108.2 107.1 103.9 99.4
2010 98.0 98.6 93.6 92.2 93.9 92.3 91.3 90.4 91.1 96.6 94.1 97.6
2011 99.5 94.8 91.0 107.3 103.0 88.8 89.1 90.8 91.6 89.2 90.8 86.3
2012 90.5 92.6 101.7 103.7 102.2 102.2 106.4 106.7 109.7 108.5 110.0 108.9
2013 102.2 99.8 99.0 95.8 95.1 95.7 95.5 92.0 93.5 92.2 89.2 91.2
2014 91.6 93.0 83.8 96.6 99.0 105.6 102.2 104.7 102.5 103.3 104.4 103.6
2015 101.4 102.4 102.0 99.0 98.8 99.3 98.8 100.1 98.4 96.6 100.4 102.1
2016 99.1 96.9 101.6 103.5 105.7 106.1 105.7 105.8 106.2 104.9 102.6 105.1
2017 108.3 108.1 109.1 109.4 107.6 106.4 106.9 105.3 108.9 111.2 110.6 109.2
2018 113.2 111.9 114.9 109.8 112.6 110.9 112.3 110.0 104.9 112.5 106.9 118.1
2019 109.4 108.2 115.0 106.5 111.4 116.8 111.0 113.6 110.5
Call:
lm(formula = value ~ ID)
Residuals:
Min 1Q Median 3Q Max
-12.7775 -5.6933 0.5288 5.4509 13.6056
Coefficients:
Estimate Std. Error t value Pr(>|t|)
(Intercept) 93.2796 2.1961 42.474 <0.0000000000000002 ***
ID 0.2147 0.0957 2.244 0.0309 *
---
Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
Residual standard error: 6.726 on 37 degrees of freedom
Multiple R-squared: 0.1198, Adjusted R-squared: 0.096
F-statistic: 5.035 on 1 and 37 DF, p-value: 0.0309
Two-sample Kolmogorov-Smirnov test
data: lm_residuals and rnorm(n = length(lm_residuals), mean = 0, sd = sd(lm_residuals))
D = 0.12821, p-value = 0.9114
alternative hypothesis: two-sided
Durbin-Watson test
data: value ~ ID
DW = 0.48878, p-value = 0.0000000009322
alternative hypothesis: true autocorrelation is greater than 0
studentized Breusch-Pagan test
data: value ~ ID
BP = 0.37553, df = 1, p-value = 0.54
Box-Ljung test
data: lm_residuals
X-squared = 19.723, df = 1, p-value = 0.00000895
Call:
lm(formula = value ~ ID)
Residuals:
Min 1Q Median 3Q Max
-13.6184 -2.3580 0.1779 2.4137 8.2684
Coefficients:
Estimate Std. Error t value Pr(>|t|)
(Intercept) 93.68253 0.84352 111.06 <0.0000000000000002 ***
ID 0.24906 0.01787 13.94 <0.0000000000000002 ***
---
Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
Residual standard error: 3.761 on 79 degrees of freedom
Multiple R-squared: 0.7108, Adjusted R-squared: 0.7072
F-statistic: 194.2 on 1 and 79 DF, p-value: < 0.00000000000000022
Two-sample Kolmogorov-Smirnov test
data: lm_residuals and rnorm(n = length(lm_residuals), mean = 0, sd = sd(lm_residuals))
D = 0.1358, p-value = 0.4462
alternative hypothesis: two-sided
Durbin-Watson test
data: value ~ ID
DW = 1.0032, p-value = 0.0000003763
alternative hypothesis: true autocorrelation is greater than 0
studentized Breusch-Pagan test
data: value ~ ID
BP = 4.2697, df = 1, p-value = 0.0388
Box-Ljung test
data: lm_residuals
X-squared = 17.997, df = 1, p-value = 0.00002213
Call:
lm(formula = value ~ ID)
Residuals:
Min 1Q Median 3Q Max
-18.088 -9.499 -4.359 6.919 31.594
Coefficients:
Estimate Std. Error t value Pr(>|t|)
(Intercept) 109.00877 3.09948 35.170 <0.0000000000000002 ***
ID -0.22029 0.08985 -2.452 0.0173 *
---
Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
Residual standard error: 11.75 on 57 degrees of freedom
Multiple R-squared: 0.0954, Adjusted R-squared: 0.07953
F-statistic: 6.011 on 1 and 57 DF, p-value: 0.0173
Two-sample Kolmogorov-Smirnov test
data: lm_residuals and rnorm(n = length(lm_residuals), mean = 0, sd = sd(lm_residuals))
D = 0.18644, p-value = 0.2582
alternative hypothesis: two-sided
Durbin-Watson test
data: value ~ ID
DW = 0.20526, p-value < 0.00000000000000022
alternative hypothesis: true autocorrelation is greater than 0
studentized Breusch-Pagan test
data: value ~ ID
BP = 7.63, df = 1, p-value = 0.00574
Box-Ljung test
data: lm_residuals
X-squared = 47.62, df = 1, p-value = 0.000000000005175
Call:
lm(formula = value ~ ID)
Residuals:
Min 1Q Median 3Q Max
-12.8592 -2.2992 0.3088 2.1890 8.1366
Coefficients:
Estimate Std. Error t value Pr(>|t|)
(Intercept) 93.44256 0.82016 113.93 <0.0000000000000002 ***
ID 0.26806 0.01804 14.86 <0.0000000000000002 ***
---
Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
Residual standard error: 3.587 on 76 degrees of freedom
Multiple R-squared: 0.7439, Adjusted R-squared: 0.7406
F-statistic: 220.8 on 1 and 76 DF, p-value: < 0.00000000000000022
Two-sample Kolmogorov-Smirnov test
data: lm_residuals and rnorm(n = length(lm_residuals), mean = 0, sd = sd(lm_residuals))
D = 0.14103, p-value = 0.4221
alternative hypothesis: two-sided
Durbin-Watson test
data: value ~ ID
DW = 1.126, p-value = 0.0000132
alternative hypothesis: true autocorrelation is greater than 0
studentized Breusch-Pagan test
data: value ~ ID
BP = 1.8876, df = 1, p-value = 0.1695
Box-Ljung test
data: lm_residuals
X-squared = 14.788, df = 1, p-value = 0.0001203