Analysis

[1] "景気ウォッチャー調査:北海道:季節調整値:景気の現状判断(方向性)DI:内閣府"
      Jan  Feb  Mar  Apr  May  Jun  Jul  Aug  Sep  Oct  Nov  Dec
2002 35.4 34.3 39.3 39.6 40.3 37.6 40.1 40.4 42.6 38.2 41.2 41.0
2003 40.5 41.2 40.9 30.9 33.2 39.2 41.2 43.2 45.4 46.0 46.9 47.2
2004 47.0 48.1 47.1 49.5 48.6 49.1 50.7 49.5 46.9 48.5 45.3 47.2
2005 48.7 45.9 48.5 47.2 49.5 48.6 48.7 47.5 50.6 46.9 53.7 54.0
2006 54.9 53.8 54.2 52.0 52.1 45.6 47.3 49.3 49.1 53.6 50.7 51.2
2007 48.5 49.9 46.9 46.8 43.9 47.9 44.4 44.6 43.3 40.2 38.9 36.7
2008 39.5 38.5 36.2 33.3 31.9 27.0 26.5 25.7 29.3 29.1 28.9 24.8
2009 24.2 24.7 27.0 33.7 36.1 42.4 42.7 45.3 44.2 46.2 44.3 45.9
2010 45.7 46.4 47.5 48.1 47.9 46.1 49.7 47.3 45.6 44.5 47.3 48.3
2011 48.3 51.5 25.1 24.7 32.5 45.0 49.8 47.5 48.0 48.2 49.9 49.8
2012 50.5 48.0 49.6 47.5 47.0 43.8 45.2 46.3 46.2 47.7 47.1 49.6
2013 50.2 53.6 53.7 54.4 52.8 56.5 55.0 54.4 57.3 58.6 57.9 57.5
2014 56.3 55.5 50.5 39.1 42.0 45.8 47.5 46.8 47.7 46.4 40.7 41.4
2015 46.3 49.1 50.3 54.1 52.3 51.1 51.4 50.3 50.1 48.2 48.8 49.5
2016 48.7 46.1 42.8 44.9 46.9 45.2 45.7 47.0 47.4 49.2 50.8 47.5
2017 48.9 48.2 48.5 45.9 50.4 49.9 51.2 51.9 48.8 49.8 49.6 50.9
2018 49.1 47.5 47.5 47.8 47.0 48.6 48.0 48.7 37.1 42.0 51.7 52.9
2019 48.8 51.4 45.5 49.6 48.0 47.9 42.8 41.3 49.3 40.5          
  • 民主党政権


Call:
lm(formula = value ~ ID)

Residuals:
     Min       1Q   Median       3Q      Max 
-21.1423  -0.0943   1.1863   2.6149   5.7475 

Coefficients:
            Estimate Std. Error t value            Pr(>|t|)    
(Intercept) 44.98920    1.90192  23.655 <0.0000000000000002 ***
ID           0.04490    0.08288   0.542               0.591    
---
Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1

Residual standard error: 5.825 on 37 degrees of freedom
Multiple R-squared:  0.00787,   Adjusted R-squared:  -0.01894 
F-statistic: 0.2935 on 1 and 37 DF,  p-value: 0.5912



    Two-sample Kolmogorov-Smirnov test

data:  lm_residuals and rnorm(n = length(lm_residuals), mean = 0, sd = sd(lm_residuals))
D = 0.30769, p-value = 0.04927
alternative hypothesis: two-sided



    Durbin-Watson test

data:  value ~ ID
DW = 0.8246, p-value = 0.000008902
alternative hypothesis: true autocorrelation is greater than 0



    studentized Breusch-Pagan test

data:  value ~ ID
BP = 0.02949, df = 1, p-value = 0.8637



    Box-Ljung test

data:  lm_residuals
X-squared = 14.346, df = 1, p-value = 0.0001521
  • 第二次安倍内閣~


Call:
lm(formula = value ~ ID)

Residuals:
     Min       1Q   Median       3Q      Max 
-11.7601  -2.1940   0.5546   2.3262   7.2859 

Coefficients:
            Estimate Std. Error t value             Pr(>|t|)    
(Intercept) 52.07082    0.88728  58.686 < 0.0000000000000002 ***
ID          -0.07567    0.01857  -4.074             0.000108 ***
---
Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1

Residual standard error: 3.981 on 80 degrees of freedom
Multiple R-squared:  0.1719,    Adjusted R-squared:  0.1615 
F-statistic:  16.6 on 1 and 80 DF,  p-value: 0.0001079



    Two-sample Kolmogorov-Smirnov test

data:  lm_residuals and rnorm(n = length(lm_residuals), mean = 0, sd = sd(lm_residuals))
D = 0.085366, p-value = 0.9286
alternative hypothesis: two-sided



    Durbin-Watson test

data:  value ~ ID
DW = 0.7272, p-value = 0.00000000001256
alternative hypothesis: true autocorrelation is greater than 0



    studentized Breusch-Pagan test

data:  value ~ ID
BP = 2.9148, df = 1, p-value = 0.08777



    Box-Ljung test

data:  lm_residuals
X-squared = 33.087, df = 1, p-value = 0.000000008812
  • 白川日銀総裁


Call:
lm(formula = value ~ ID)

Residuals:
    Min      1Q  Median      3Q     Max 
-19.685  -4.251   1.233   5.586   8.572 

Coefficients:
            Estimate Std. Error t value             Pr(>|t|)    
(Intercept) 31.35447    1.75983  17.817 < 0.0000000000000002 ***
ID           0.36197    0.05101   7.095        0.00000000221 ***
---
Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1

Residual standard error: 6.673 on 57 degrees of freedom
Multiple R-squared:  0.469, Adjusted R-squared:  0.4597 
F-statistic: 50.34 on 1 and 57 DF,  p-value: 0.000000002207



    Two-sample Kolmogorov-Smirnov test

data:  lm_residuals and rnorm(n = length(lm_residuals), mean = 0, sd = sd(lm_residuals))
D = 0.11864, p-value = 0.8052
alternative hypothesis: two-sided



    Durbin-Watson test

data:  value ~ ID
DW = 0.47366, p-value = 0.00000000000007958
alternative hypothesis: true autocorrelation is greater than 0



    studentized Breusch-Pagan test

data:  value ~ ID
BP = 1.1617, df = 1, p-value = 0.2811



    Box-Ljung test

data:  lm_residuals
X-squared = 36.122, df = 1, p-value = 0.000000001853
  • 黒田日銀総裁~


Call:
lm(formula = value ~ ID)

Residuals:
     Min       1Q   Median       3Q      Max 
-11.6935  -2.4761   0.5595   2.4070   7.3624 

Coefficients:
            Estimate Std. Error t value             Pr(>|t|)    
(Intercept) 51.75579    0.91822  56.365 < 0.0000000000000002 ***
ID          -0.07402    0.01994  -3.712             0.000387 ***
---
Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1

Residual standard error: 4.042 on 77 degrees of freedom
Multiple R-squared:  0.1518,    Adjusted R-squared:  0.1408 
F-statistic: 13.78 on 1 and 77 DF,  p-value: 0.0003871



    Two-sample Kolmogorov-Smirnov test

data:  lm_residuals and rnorm(n = length(lm_residuals), mean = 0, sd = sd(lm_residuals))
D = 0.063291, p-value = 0.9977
alternative hypothesis: two-sided



    Durbin-Watson test

data:  value ~ ID
DW = 0.72269, p-value = 0.00000000002266
alternative hypothesis: true autocorrelation is greater than 0



    studentized Breusch-Pagan test

data:  value ~ ID
BP = 4.4683, df = 1, p-value = 0.03453



    Box-Ljung test

data:  lm_residuals
X-squared = 31.953, df = 1, p-value = 0.00000001579
  • 特記その他
  1. 時系列データの特徴(誤差構造、負数の有無その他等)に関わらず線形回帰を求めている。よってあくまでも対象とした期間における線形回帰そしてその残差の傾向を確認しているのみであり結果の外挿は出来ない。
  2. 民主党政権:2009-09-16~2012-12-25
  3. 白川方明氏の日銀総裁就任期間:2008-04-09~2013-03-19