Map_MienDong
thongke.club
6/28/2020
Bản đồ VN
library(raster)## Loading required package: spvietnam <-getData("GADM", country="Vietnam", level=1)
library(ggplot2)
ggplot() + geom_polygon(data=vietnam,aes(x=long,y=lat,group=group,fill=id))## Regions defined for each Polygons
Bản đồ Miền Đông
setwd("d:/DATA2020/SieuNhanMap_Q4/")
library(readxl)
dulieu <-read_excel("miendong.xlsx")
head(dulieu)## # A tibble: 6 x 6
## Ten lo la id tile Tinh
## <chr> <dbl> <dbl> <dbl> <dbl> <chr>
## 1 H<U+1ED3> Chí Minh 107. 10.8 18 66.7 Ho Chi Minh
## 2 Bình Duong 107. 11.2 63 14.5 Binh Duong
## 3 Bình Phu<U+1EDB>c 107. 11.7 2 1.6 Binh Phuoc
## 4 Ð<U+1ED3>ng Nai 107. 11.0 9 5.6 Dong Nai
## 5 Bà R<U+1ECB>a - Vung Tàu 107. 10.5 61 9.8 Ba Ria - VungTau
## 6 Tây Ninh 106. 11.5 49 1.8 Tay Ninhlibrary(dplyr)##
## Attaching package: 'dplyr'## The following objects are masked from 'package:raster':
##
## intersect, select, union## The following objects are masked from 'package:stats':
##
## filter, lag## The following objects are masked from 'package:base':
##
## intersect, setdiff, setequal, uniondatapanel <-read_excel("data.PANEL.xlsx")
head(datapanel)## # A tibble: 6 x 31
## NAM TINH STT SO SME LnSME YSCH LnYSCH LABOR GDP LnGDP CAPITAL
## <dbl> <chr> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl>
## 1 1995 BINH~ 70 1 87 4.47 4.73 1.55 26701 390882 12.9 432316
## 2 1996 BINH~ 70 1 83 4.42 5.02 1.61 27359 468551 13.1 626583
## 3 1997 BINH~ 70 1 153 5.03 5.21 1.65 27523 553700 13.2 864822
## 4 1998 BINH~ 70 1 155 5.04 5.33 1.67 28353 537877 13.2 1265059
## 5 1999 BINH~ 70 1 241 5.48 5.58 1.72 28430 660326 13.4 1844163
## 6 2000 BINH~ 70 1 248 5.51 5.87 1.77 28021 909628 13.7 2016480
## # ... with 19 more variables: LnCAP <dbl>, C0 <dbl>, C1 <dbl>, C2 <dbl>,
## # C3 <dbl>, C4 <dbl>, C5 <dbl>, SMEH <dbl>, LnSMEH <dbl>, LnEDUC <dbl>,
## # LnSMER <dbl>, Schools <dbl>, LnSchool <dbl>, Age <dbl>, LnAge <dbl>,
## # INT <dbl>, LEND <dbl>, PCI <dbl>, CSTP8 <dbl>dtpanel <- datapanel %>% group_by(TINH)%>%summarize(trungbinh = mean(GDP))%>%mutate(tile =round(trungbinh/sum(trungbinh)*100,2))## `summarise()` ungrouping output (override with `.groups` argument)head(dtpanel)## # A tibble: 6 x 3
## TINH trungbinh tile
## <chr> <dbl> <dbl>
## 1 BINHDUONG 18782387. 14.5
## 2 BINHPHUOC 2044828 1.58
## 3 BR-VT 7177621 5.54
## 4 DONGNAI 12673357. 9.78
## 5 TAYNINH 2503213. 1.93
## 6 TPHCM 86436295. 66.7miendong <-vietnam[c(25,9,10,17,7,53),]
ggplot() + geom_polygon(data=miendong,aes(x=long,y=lat,group=group,fill=id),color = "white") + labs(x = NULL, y = NULL) + theme(legend.position = "none")## Regions defined for each Polygons
Kết nối dữ liệu
library(tidyverse)## -- Attaching packages ---------------------------------------------------------------------------------------------------------- tidyverse 1.3.0 --## v tibble 3.0.1 v purrr 0.3.4
## v tidyr 1.1.0 v stringr 1.4.0
## v readr 1.3.1 v forcats 0.5.0## -- Conflicts ------------------------------------------------------------------------------------------------------------- tidyverse_conflicts() --
## x tidyr::extract() masks raster::extract()
## x dplyr::filter() masks stats::filter()
## x dplyr::lag() masks stats::lag()
## x dplyr::select() masks raster::select()mdong<-fortify(miendong)## Regions defined for each Polygons# id hiển thị ở đây names(mdong) hay mdong$id
data_noi <- merge(mdong, dulieu, by="id", all.x = TRUE)
head(data_noi)## id long lat order hole piece group Ten lo
## 1 18 106.9627 10.43849 1 FALSE 1 18.1 H<U+1ED3> Chí Minh 106.6571
## 2 18 106.9726 10.43316 2 FALSE 1 18.1 H<U+1ED3> Chí Minh 106.6571
## 3 18 106.9823 10.42475 3 FALSE 1 18.1 H<U+1ED3> Chí Minh 106.6571
## 4 18 106.9853 10.41820 4 FALSE 1 18.1 H<U+1ED3> Chí Minh 106.6571
## 5 18 106.9856 10.41320 5 FALSE 1 18.1 H<U+1ED3> Chí Minh 106.6571
## 6 18 106.9810 10.40523 6 FALSE 1 18.1 H<U+1ED3> Chí Minh 106.6571
## la tile Tinh
## 1 10.7639 66.7 Ho Chi Minh
## 2 10.7639 66.7 Ho Chi Minh
## 3 10.7639 66.7 Ho Chi Minh
## 4 10.7639 66.7 Ho Chi Minh
## 5 10.7639 66.7 Ho Chi Minh
## 6 10.7639 66.7 Ho Chi MinhVẽ đồ thị
library(ggthemes)
m1 <-ggplot(data=data_noi,aes(x = long, y = lat,group = group))+ geom_polygon(aes(fill = id), color = "white") + labs(x = NULL, y = NULL) + theme(legend.position = "none") + scale_fill_manual(values=c("red", "darkgreen", "chocolate","purple","lightpink4", "darkorange4" ))
m2 <- m1 + geom_point(aes(x=lo, y=la), col="#8C3F4D")
m3 <- m2 + geom_text(aes(x=lo, y=la, label= Tinh), vjust=- 0.8, col="#00046e")
m4 <- m3 + geom_text(aes(x=lo, y=la, label=tile), vjust= 1.5,col="#00046e")
m5 <- m4 + geom_text(aes(x=lo, y=la), label="%", vjust =1.5, hjust= -1, col="#00046e")
m6 <- m5 + guides(fill=FALSE, color=FALSE) + theme_wsj() + ggsave("miendong.png")## Saving 7 x 5 in imagem6
Vẽ đồ thị hình cột
dtpanel <-dtpanel %>% mutate(tb = round(trungbinh/1000,0))
dtpanel <-dtpanel %>% arrange(tb)
dtpanel$TenTinh <-c("Binh Phuoc","Tay Ninh","Ba Ria - Vung Tau","Dong Nai","Binh Duong","Ho Chi Minh")
head(dtpanel)## # A tibble: 6 x 5
## TINH trungbinh tile tb TenTinh
## <chr> <dbl> <dbl> <dbl> <chr>
## 1 BINHPHUOC 2044828 1.58 2045 Binh Phuoc
## 2 TAYNINH 2503213. 1.93 2503 Tay Ninh
## 3 BR-VT 7177621 5.54 7178 Ba Ria - Vung Tau
## 4 DONGNAI 12673357. 9.78 12673 Dong Nai
## 5 BINHDUONG 18782387. 14.5 18782 Binh Duong
## 6 TPHCM 86436295. 66.7 86436 Ho Chi Minhlibrary(hrbrthemes)## NOTE: Either Arial Narrow or Roboto Condensed fonts are required to use these themes.## Please use hrbrthemes::import_roboto_condensed() to install Roboto Condensed and## if Arial Narrow is not on your system, please see https://bit.ly/arialnarrowlibrary(ggplot2)
my_colors<-c("#8C3F4D")
dtpanel %>% ggplot(aes(x=reorder(TenTinh,tb),y=tb)) +
geom_bar(stat = "identity", width = 0.8, color=my_colors, fill=my_colors) +
geom_text(data=dtpanel%>%filter(tb <20000),aes(label = tb), hjust = -0.1, color = my_colors, size = 5.5) +
geom_text(data=dtpanel%>%filter(tb>20000), aes(label=tb), hjust=1.1, color="white", size=5.5)+
coord_flip() +
theme_wsj() +
theme(panel.grid = element_blank()) +
theme(axis.text.x = element_blank()) +
theme(axis.text.y = element_text(color = my_colors, size = 16)) +
theme(plot.title = element_text(size = 28)) +
theme(plot.subtitle = element_text( size = 16, color = "grey80")) +
theme(plot.caption = element_text( size = 13, face = "italic")) +
#scale_y_discrete(expand = c(0.2, 0)) +
#scale_x_discrete(expand = c(0,2)) +
theme(plot.margin = unit(c(1.2, 1.2, 1.2, 1.2), "cm")) +
labs(x = NULL, y = NULL) + ggsave("cotmiendong.png")## Saving 7 x 5 in image
Ve duong line
# Ve duong line SME
ggplot()+ theme_wsj()+ theme(legend.position = "none") +
geom_line(data=datapanel%>%dplyr::filter(SO==1),aes(x=NAM,y=LnSME),size=1.5,color="darkgreen") +
geom_line(data=datapanel%>%dplyr::filter(SO==2),aes(x=NAM,y=LnSME),size=1.5,color="chocolate") +
geom_line(data=datapanel%>%dplyr::filter(SO==3),aes(x=NAM,y=LnSME),size=1.5,color="lightpink4") +
geom_line(data=datapanel%>%dplyr::filter(SO==4),aes(x=NAM,y=LnSME),size=1.5,color="darkorange4") +
geom_line(data=datapanel%>%dplyr::filter(SO==5),aes(x=NAM,y=LnSME),size=1.5,color="purple") +
geom_line(data=datapanel%>%dplyr::filter(SO==6),aes(x=NAM,y=LnSME),size=1.5,color="red") +
geom_rect(aes(xmin=1995,xmax=2005,ymin=9.5,ymax=12.5),fill="gray",colour=NA,alpha=0.3) +
geom_point(data=datapanel%>%dplyr::filter(SO==1), aes(x=1995.3, y=12.3, size=0.52),colour="darkgreen", fill="darkgreen") +
geom_text(data=datapanel%>%dplyr::filter(SO==1), aes(x=1995.3, y=12.3, size=0.52),color="darkgreen", label="Binh Phuoc Province", hjust=-0.1)+
geom_point(data=datapanel%>%dplyr::filter(SO==2), aes(x=1995.3, y=11.8, size=0.52),colour="chocolate") +
geom_text(data=datapanel%>%dplyr::filter(SO==2), aes(x=1995.3, y=11.8, size=0.52),color="chocolate", label="Tay Ninh Province", hjust=-0.1)+
geom_point(data=datapanel%>%dplyr::filter(SO==3), aes(x=1995.3, y=11.3, size=0.52),colour="lightpink4") +
geom_text(data=datapanel%>%dplyr::filter(SO==3), aes(x=1995.3, y=11.3, size=0.52),color="lightpink4", label="Binh Duong Province", hjust=-0.1)+
geom_point(data=datapanel%>%dplyr::filter(SO==4), aes(x=1995.3, y=10.8, size=0.52),colour="darkorange4") +
geom_text(data=datapanel%>%dplyr::filter(SO==4), aes(x=1995.3, y=10.8, size=0.52),color="darkorange4", label="Dong Nai Province", hjust=-0.1)+
geom_point(data=datapanel%>%dplyr::filter(SO==5), aes(x=1995.3, y=10.3, size=0.52),colour="purple") +
geom_text(data=datapanel%>%dplyr::filter(SO==5), aes(x=1995.3, y=10.3, size=0.52),color="purple", label="Ba Ria - Vung Tau Province", hjust=-0.08)+
geom_point(data=datapanel%>%dplyr::filter(SO==6), aes(x=1995.3, y=9.8, size=0.52),colour="red") +
geom_text(data=datapanel%>%dplyr::filter(SO==6), aes(x=1995.3, y=9.8, size=0.52),color="red", label="Ho Chi Minh City", hjust=-0.1) 
# Ve duong line SMEH
ggplot()+ theme_wsj()+ theme(legend.position = "none") +
geom_line(data=datapanel%>%dplyr::filter(SO==1),aes(x=NAM,y=SMEH),size=1.5,color="darkgreen") +
geom_line(data=datapanel%>%dplyr::filter(SO==2),aes(x=NAM,y=SMEH),size=1.5,color="chocolate") +
geom_line(data=datapanel%>%dplyr::filter(SO==3),aes(x=NAM,y=SMEH),size=1.5,color="lightpink4") +
geom_line(data=datapanel%>%dplyr::filter(SO==4),aes(x=NAM,y=SMEH),size=1.5,color="darkorange4") +
geom_line(data=datapanel%>%dplyr::filter(SO==5),aes(x=NAM,y=SMEH),size=1.5,color="purple") +
geom_line(data=datapanel%>%dplyr::filter(SO==6),aes(x=NAM,y=SMEH),size=1.5,color="red") +
geom_rect(aes(xmin=1995,xmax=2005,ymin=1.45,ymax=1.65),fill="gray",colour=NA,alpha=0.3) +
geom_point(data=datapanel%>%dplyr::filter(SO==1), aes(x=1995.3, y=1.63, size=0.52),colour="darkgreen", fill="darkgreen") +
geom_text(data=datapanel%>%dplyr::filter(SO==1), aes(x=1995.3, y=1.63, size=0.52),color="darkgreen", label="Binh Phuoc Province", hjust=-0.1)+
geom_point(data=datapanel%>%dplyr::filter(SO==2), aes(x=1995.3, y=1.6, size=0.52),colour="chocolate") +
geom_text(data=datapanel%>%dplyr::filter(SO==2), aes(x=1995.3, y=1.6, size=0.52),color="chocolate", label="Tay Ninh Province", hjust=-0.1)+
geom_point(data=datapanel%>%dplyr::filter(SO==3), aes(x=1995.3, y=1.57, size=0.52),colour="lightpink4") +
geom_text(data=datapanel%>%dplyr::filter(SO==3), aes(x=1995.3, y=1.57, size=0.52),color="lightpink4", label="Binh Duong Province", hjust=-0.1)+
geom_point(data=datapanel%>%dplyr::filter(SO==4), aes(x=1995.3, y=1.54, size=0.52),colour="darkorange4") +
geom_text(data=datapanel%>%dplyr::filter(SO==4), aes(x=1995.3, y=1.54, size=0.52),color="darkorange4", label="Dong Nai Province", hjust=-0.1)+
geom_point(data=datapanel%>%dplyr::filter(SO==5), aes(x=1995.3, y=1.51, size=0.52),colour="purple") +
geom_text(data=datapanel%>%dplyr::filter(SO==5), aes(x=1995.3, y=1.51, size=0.52),color="purple", label="Ba Ria - Vung Tau Province", hjust=-0.08)+
geom_point(data=datapanel%>%dplyr::filter(SO==6), aes(x=1995.3, y=1.48, size=0.52),colour="red") +
geom_text(data=datapanel%>%dplyr::filter(SO==6), aes(x=1995.3, y=1.48, size=0.52),color="red", label="Ho Chi Minh City", hjust=-0.1)
# Ve duong line LnSMER
ggplot()+ theme_wsj()+ theme(legend.position = "none") +
geom_line(data=datapanel%>%dplyr::filter(SO==1),aes(x=NAM,y=LnSMER),size=1.5,color="darkgreen") +
geom_line(data=datapanel%>%dplyr::filter(SO==2),aes(x=NAM,y=LnSMER),size=1.5,color="chocolate") +
geom_line(data=datapanel%>%dplyr::filter(SO==3),aes(x=NAM,y=LnSMER),size=1.5,color="lightpink4") +
geom_line(data=datapanel%>%dplyr::filter(SO==4),aes(x=NAM,y=LnSMER),size=1.5,color="darkorange4") +
geom_line(data=datapanel%>%dplyr::filter(SO==5),aes(x=NAM,y=LnSMER),size=1.5,color="purple") +
geom_line(data=datapanel%>%dplyr::filter(SO==6),aes(x=NAM,y=LnSMER),size=1.5,color="red") +
geom_rect(aes(xmin=1995,xmax=2005,ymin=13,ymax=15),fill="gray",colour=NA,alpha=0.3) +
geom_point(data=datapanel%>%dplyr::filter(SO==1), aes(x=1995.3, y=14.8, size=0.52),colour="darkgreen", fill="darkgreen") +
geom_text(data=datapanel%>%dplyr::filter(SO==1), aes(x=1995.3, y=14.8, size=0.52),color="darkgreen", label="Binh Phuoc Province", hjust=-0.1)+
geom_point(data=datapanel%>%dplyr::filter(SO==2), aes(x=1995.3, y=14.5, size=0.52),colour="chocolate") +
geom_text(data=datapanel%>%dplyr::filter(SO==2), aes(x=1995.3, y=14.5, size=0.52),color="chocolate", label="Tay Ninh Province", hjust=-0.1)+
geom_point(data=datapanel%>%dplyr::filter(SO==3), aes(x=1995.3, y=14.2, size=0.52),colour="lightpink4") +
geom_text(data=datapanel%>%dplyr::filter(SO==3), aes(x=1995.3, y=14.2, size=0.52),color="lightpink4", label="Binh Duong Province", hjust=-0.1)+
geom_point(data=datapanel%>%dplyr::filter(SO==4), aes(x=1995.3, y=13.9, size=0.52),colour="darkorange4") +
geom_text(data=datapanel%>%dplyr::filter(SO==4), aes(x=1995.3, y=13.9, size=0.52),color="darkorange4", label="Dong Nai Province", hjust=-0.1)+
geom_point(data=datapanel%>%dplyr::filter(SO==5), aes(x=1995.3, y=13.6, size=0.52),colour="purple") +
geom_text(data=datapanel%>%dplyr::filter(SO==5), aes(x=1995.3, y=13.6, size=0.52),color="purple", label="Ba Ria - Vung Tau Province", hjust=-0.08)+
geom_point(data=datapanel%>%dplyr::filter(SO==6), aes(x=1995.3, y=13.3, size=0.52),colour="red") +
geom_text(data=datapanel%>%dplyr::filter(SO==6), aes(x=1995.3, y=13.3, size=0.52),color="red", label="Ho Chi Minh City", hjust=-0.1)
#Hồi quy tổng
library(lmridge)
library(dplyr)
so <-seq(0,0.1,by=.001)
congthuc <-LnGDP~ LnSME + LnYSCH + LnCAP+ SMEH + LnSMER+ LnSchool+ PCI+ CSTP8
hoiquy <-lm(data=datapanel, congthuc)
summary(hoiquy)##
## Call:
## lm(formula = congthuc, data = datapanel)
##
## Residuals:
## Min 1Q Median 3Q Max
## -1.57846 -0.14854 0.01808 0.13696 0.89617
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 0.920650 2.036892 0.452 0.65249
## LnSME -0.047066 0.122678 -0.384 0.70224
## LnYSCH 0.884249 1.315515 0.672 0.50339
## LnCAP 0.422983 0.125722 3.364 0.00117 **
## SMEH 0.004239 1.026077 0.004 0.99671
## LnSMER 0.577616 0.114753 5.034 2.85e-06 ***
## LnSchool -0.183947 0.189655 -0.970 0.33498
## PCI -0.001189 0.007082 -0.168 0.86707
## CSTP8 0.027043 0.033202 0.815 0.41774
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.3054 on 81 degrees of freedom
## (60 observations deleted due to missingness)
## Multiple R-squared: 0.9582, Adjusted R-squared: 0.9541
## F-statistic: 232.3 on 8 and 81 DF, p-value: < 2.2e-16#ridge <-lmridge(congthuc, data=datapanel, K=so)
#vif(ridge)
summary(lmridge(congthuc, data=datapanel, K=0.2))##
## Call:
## lmridge.default(formula = congthuc, data = datapanel, K = 0.2)
##
##
## Coefficients: for Ridge parameter K= 0.2
## Estimate Estimate (Sc) StdErr (Sc) t-value (Sc) Pr(>|t|)
## Intercept 2.4450 -178.9030 18.4511 -9.6961 <2e-16 ***
## LnSME 0.2442 3.4552 0.2153 16.0495 <2e-16 ***
## LnYSCH 0.9090 0.5782 0.2827 2.0451 0.0440 *
## LnCAP 0.2439 3.9295 0.1906 20.6158 <2e-16 ***
## SMEH 0.1318 0.1196 0.2736 0.4371 0.6631
## LnSMER 0.3802 4.5461 0.2381 19.0911 <2e-16 ***
## LnSchool -0.0636 -0.1760 0.2923 -0.6022 0.5486
## PCI 0.0102 0.5524 0.2874 1.9218 0.0580 .
## CSTP8 0.0335 0.3903 0.2913 1.3400 0.1838
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Ridge Summary
## R2 adj-R2 DF ridge F AIC BIC
## 0.84180 0.82830 4.59731 201.91968 -197.52923 218.94604
## Ridge minimum MSE= 31.93342 at K= 0.2
## P-value for F-test ( 4.59731 , 84.38263 ) = 3.004414e-44
## -------------------------------------------------------------------Tỉnh Bình Phước
#ridge1 <-lmridge(congthuc, data=datapanel%>%dplyr::filter(datapanel$SO==1) , K=so)
#vif(ridge1)
summary(lmridge(congthuc, data=datapanel%>%dplyr::filter(datapanel$SO==1) , K=0.1))##
## Call:
## lmridge.default(formula = congthuc, data = datapanel %>% dplyr::filter(datapanel$SO ==
## 1), K = 0.1)
##
##
## Coefficients: for Ridge parameter K= 0.1
## Estimate Estimate (Sc) StdErr (Sc) t-value (Sc) Pr(>|t|)
## Intercept 0.6437 -8.3327 8.9817 -0.9277 0.3762
## LnSME 0.1777 0.4147 0.0988 4.1969 0.0020 **
## LnYSCH 3.9195 1.0099 0.1566 6.4506 0.0001 ***
## LnCAP 0.1400 0.5973 0.0984 6.0719 0.0001 ***
## SMEH 0.6234 0.2232 0.1938 1.1516 0.2773
## LnSMER 0.1493 0.2478 0.1880 1.3185 0.2178
## LnSchool -0.0929 -0.1050 0.1573 -0.6676 0.5201
## PCI 0.0034 0.0930 0.1465 0.6350 0.5402
## CSTP8 0.0005 0.0021 0.1585 0.0130 0.9899
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Ridge Summary
## R2 adj-R2 DF ridge F AIC BIC
## 0.92160 0.84310 4.36663 41.06235 -55.90824 -12.19569
## Ridge minimum MSE= 25.29538 at K= 0.1
## P-value for F-test ( 4.36663 , 9.725674 ) = 3.888101e-06
## -------------------------------------------------------------------summary(lmridge(congthuc, data=datapanel%>%dplyr::filter(datapanel$SO==2) , K=0.1))##
## Call:
## lmridge.default(formula = congthuc, data = datapanel %>% dplyr::filter(datapanel$SO ==
## 2), K = 0.1)
##
##
## Coefficients: for Ridge parameter K= 0.1
## Estimate Estimate (Sc) StdErr (Sc) t-value (Sc) Pr(>|t|)
## Intercept -5.0092 -9.0941 7.0539 -1.2892 0.2281
## LnSME -0.0658 -0.1160 0.1432 -0.8101 0.4379
## LnYSCH 1.6999 0.4649 0.1083 4.2925 0.0018 **
## LnCAP 0.1147 0.3194 0.0499 6.4037 0.0001 ***
## SMEH 0.6189 0.2335 0.0899 2.5967 0.0279 *
## LnSMER 1.2623 0.6334 0.1208 5.2425 0.0005 ***
## LnSchool -0.0570 -0.0644 0.1145 -0.5628 0.5868
## PCI 0.0092 0.2052 0.1160 1.7690 0.1092
## CSTP8 -0.0141 -0.0660 0.1011 -0.6523 0.5298
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Ridge Summary
## R2 adj-R2 DF ridge F AIC BIC
## 0.90150 0.80290 4.58868 32.08111 -66.30032 -22.43055
## Ridge minimum MSE= 21.02934 at K= 0.1
## P-value for F-test ( 4.58868 , 9.497572 ) = 1.321324e-05
## -------------------------------------------------------------------summary(lmridge(congthuc, data=datapanel%>%dplyr::filter(datapanel$SO==3) , K=0.1))##
## Call:
## lmridge.default(formula = congthuc, data = datapanel %>% dplyr::filter(datapanel$SO ==
## 3), K = 0.1)
##
##
## Coefficients: for Ridge parameter K= 0.1
## Estimate Estimate (Sc) StdErr (Sc) t-value (Sc) Pr(>|t|)
## Intercept 13.2939 111.6566 30.3634 3.6773 0.0044 **
## LnSME 0.1291 0.3019 0.3851 0.7840 0.4517
## LnYSCH -1.0878 -0.2776 0.3917 -0.7088 0.4951
## LnCAP -0.0242 -0.0568 0.2404 -0.2365 0.8180
## SMEH 1.7810 0.6384 0.3613 1.7669 0.1085
## LnSMER 0.7026 0.3870 0.3958 0.9776 0.3519
## LnSchool -0.4875 -0.5512 0.3840 -1.4357 0.1824
## PCI -0.0657 -1.5383 0.4397 -3.4987 0.0060 **
## CSTP8 0.1003 0.5622 0.3962 1.4189 0.1871
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Ridge Summary
## R2 adj-R2 DF ridge F AIC BIC
## 0.69530 0.39070 4.24710 5.83354 -29.96980 13.65811
## Ridge minimum MSE= 32.11381 at K= 0.1
## P-value for F-test ( 4.2471 , 9.783155 ) = 0.01081276
## -------------------------------------------------------------------summary(lmridge(congthuc, data=datapanel%>%dplyr::filter(datapanel$SO==4) , K=0.1))##
## Call:
## lmridge.default(formula = congthuc, data = datapanel %>% dplyr::filter(datapanel$SO ==
## 4), K = 0.1)
##
##
## Coefficients: for Ridge parameter K= 0.1
## Estimate Estimate (Sc) StdErr (Sc) t-value (Sc) Pr(>|t|)
## Intercept -0.3898 -1.4645 6.9218 -0.2116 0.8369
## LnSME 0.1300 0.2721 0.0788 3.4511 0.0067 **
## LnYSCH 1.5330 0.4000 0.1041 3.8437 0.0036 **
## LnCAP 0.0992 0.2255 0.0752 2.9994 0.0141 *
## SMEH 1.0397 0.3884 0.1267 3.0659 0.0126 *
## LnSMER 0.6631 0.3184 0.1324 2.4055 0.0381 *
## LnSchool 0.0954 0.1079 0.1194 0.9041 0.3882
## PCI 0.0078 0.0894 0.1050 0.8512 0.4156
## CSTP8 -0.0029 -0.0112 0.1039 -0.1081 0.9162
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Ridge Summary
## R2 adj-R2 DF ridge F AIC BIC
## 0.91060 0.82130 4.47837 27.09396 -65.45786 -21.66620
## Ridge minimum MSE= 5.993427 at K= 0.1
## P-value for F-test ( 4.47837 , 9.671695 ) = 2.518875e-05
## -------------------------------------------------------------------summary(lmridge(congthuc, data=datapanel%>%dplyr::filter(datapanel$SO==5) , K=0.1))##
## Call:
## lmridge.default(formula = congthuc, data = datapanel %>% dplyr::filter(datapanel$SO ==
## 5), K = 0.1)
##
##
## Coefficients: for Ridge parameter K= 0.1
## Estimate Estimate (Sc) StdErr (Sc) t-value (Sc) Pr(>|t|)
## Intercept -2.6132 -76.8412 19.2318 -3.9955 0.0029 **
## LnSME -0.1194 -0.3202 0.2512 -1.2748 0.2332
## LnYSCH 0.9604 0.2400 0.3436 0.6986 0.5018
## LnCAP 0.3485 1.1012 0.2745 4.0121 0.0028 **
## SMEH -0.1693 -0.0636 0.3428 -0.1856 0.8567
## LnSMER 0.5498 0.6721 0.3390 1.9823 0.0776 .
## LnSchool -0.1669 -0.1887 0.3208 -0.5882 0.5703
## PCI 0.0791 1.0423 0.2922 3.5672 0.0057 **
## CSTP8 0.2090 0.7838 0.2838 2.7619 0.0213 *
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Ridge Summary
## R2 adj-R2 DF ridge F AIC BIC
## 0.810900 0.621800 4.665390 11.298152 -35.432789 8.491295
## Ridge minimum MSE= 16.51895 at K= 0.1
## P-value for F-test ( 4.66539 , 9.396127 ) = 0.001040666
## -------------------------------------------------------------------summary(lmridge(congthuc, data=datapanel%>%dplyr::filter(datapanel$SO==6) , K=0.1))##
## Call:
## lmridge.default(formula = congthuc, data = datapanel %>% dplyr::filter(datapanel$SO ==
## 6), K = 0.1)
##
##
## Coefficients: for Ridge parameter K= 0.1
## Estimate Estimate (Sc) StdErr (Sc) t-value (Sc) Pr(>|t|)
## Intercept 6.2324 -8.5954 9.2908 -0.9252 0.3778
## LnSME 0.0847 0.1973 0.0955 2.0646 0.0674 .
## LnYSCH 1.3226 0.3281 0.1399 2.3452 0.0422 *
## LnCAP 0.1238 0.4522 0.1469 3.0780 0.0124 *
## SMEH 0.5394 0.2014 0.1597 1.2612 0.2373
## LnSMER 0.2585 0.1684 0.1355 1.2428 0.2438
## LnSchool -0.0195 -0.0220 0.1342 -0.1641 0.8731
## PCI 0.0206 0.1737 0.1338 1.2985 0.2248
## CSTP8 0.0429 0.1576 0.1185 1.3294 0.2148
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Ridge Summary
## R2 adj-R2 DF ridge F AIC BIC
## 0.89500 0.78990 4.50461 17.71586 -60.26232 -16.45208
## Ridge minimum MSE= 1.462445 at K= 0.1
## P-value for F-test ( 4.50461 , 9.56448 ) = 0.0001656931
## -------------------------------------------------------------------