Total Quarterly Wage Permutation

Import Data

GOV <- read_excel("Local Government all industries.xlsx")
TTU <- read_excel("Private Trade transportation and utilities.xlsx")
CON <- read_excel("Private Construction.xlsx")
ES <- read_excel("Private Education and health services.xlsx")
FI <- read_excel("Private Financial activities.xlsx")
GOO <- read_excel("Private Goods producing.xlsx")
LEI <- read_excel("Private Leisure and hospitality.xlsx")
MAN <- read_excel("Private Manufacturing.xlsx")
NMI <- read_excel("Private Natural resources and mining.xlsx")
BSS <- read_excel("Private Professional and business services.xlsx")
PRV <- read_excel("Private Service providing.xlsx")
TOT <- read_excel("Total Covered all industries.xlsx")


## Theme Plot
plot.theme <- theme(legend.position="bottom",
                    legend.direction = 'horizontal',
                    legend.key = element_blank(),axis.text.x = element_text(angle = 45, hjust = 1),
                    legend.background = element_blank(),
                    plot.title = element_text(hjust = 0.5, size = 12,face = "bold"),
                    axis.text = element_text(size = 8),axis.title = element_text(size = 9),
                    )

Total Quarterly Wage

TOT$permut<-TOT$lg-TOT$`sdid-intecept`
TOT$Date<-as.Date(TOT$Date)

TOTx<-TOT%>%
  group_by(AreaName)%>%
  mutate(MSE=(mean(permut[24:27]))^2,
         Date=as.Date(Date)) ## Calculate MSE in period one year after treated period

Nor<-TOTx%>%
  filter(AreaName=="New Orleans-Metairie, LA MSA")%>%
  data.frame()

TOTx<-TOTx%>%
  filter(MSE<=Nor$MSE*1.5) %>% ## Subset MSE that less than New Orlean MSE and multiply 1.5
  data.frame()

pl.0<-ggplot()+
  geom_line(data=TOTx,aes(x=Date,y=permut,group=AreaName,colour="controls"))+
  geom_line(data=Nor,aes(x=Date,y=permut,group=AreaName,colour="treated"))+theme_bw()+
  ylab("Quarterly Wage")+xlab("Year")+plot.theme +labs(color="")+
  geom_vline(xintercept = as.Date("2005-07-01"),linetype=2)+
  scale_color_manual(values = c("treated"="black","controls"="gray"),breaks = c("treated","controls"))

Good Producing

GOO$permut<-GOO$lg-GOO$`sdid-intecept`
GOO$Date<-as.Date(GOO$Date)

GOOx<-GOO%>%
  group_by(AreaName)%>%
  mutate(MSE=(mean(permut[24:27]))^2,
         Date=as.Date(Date)) ## Calculate MSE in period one year after treated period

Nor<-GOOx%>%
  filter(AreaName=="New Orleans-Metairie, LA MSA")%>%
  data.frame()

GOOx<-GOOx%>%
  filter(MSE<=Nor$MSE*1.5) %>% ## Subset MSE that less than New Orlean MSE and multiply 1.5
  data.frame()

pl.1<-ggplot()+
  geom_line(data=GOOx,aes(x=Date,y=permut,group=AreaName,colour="controls"))+
  geom_line(data=Nor,aes(x=Date,y=permut,group=AreaName,colour="treated"))+theme_bw()+
  ylab("Good Producing")+xlab("Year")+plot.theme +labs(color="")+
  geom_vline(xintercept = as.Date("2005-07-01"),linetype=2)+
  scale_color_manual(values = c("treated"="black","controls"="gray"),breaks = c("treated","controls"))

Natural Resources and Mining

NMI$permut<-NMI$lg-NMI$`sdid-intecept`
NMI$Date<-as.Date(NMI$Date)

NMIx<-NMI%>%
  group_by(AreaName)%>%
  mutate(MSE=(mean(permut[24:27]))^2,
         Date=as.Date(Date)) ## Calculate MSE in period one year after treated period

Nor<-NMIx%>%
  filter(AreaName=="New Orleans-Metairie, LA MSA")%>%
  data.frame()

NMIx<-NMIx%>%
  filter(MSE<=Nor$MSE*1.5) %>% ## Subset MSE that less than New Orlean MSE and multiply 1.5
  data.frame()

pl.2<-ggplot()+
  geom_line(data=NMIx,aes(x=Date,y=permut,group=AreaName,colour="controls"))+
  geom_line(data=Nor,aes(x=Date,y=permut,group=AreaName,colour="treated"))+theme_bw()+
  ylab("Natural Resources and Mining")+xlab("Year")+plot.theme +labs(color="")+
  geom_vline(xintercept = as.Date("2005-07-01"),linetype=2)+
  scale_color_manual(values = c("treated"="black","controls"="gray"),breaks = c("treated","controls"))

Construction

CON$permut<-CON$lg-CON$`sdid-intecept`
CON$Date<-as.Date(CON$Date)

CONx<-CON%>%
  group_by(AreaName)%>%
  mutate(MSE=(mean(permut[24:27]))^2,
         Date=as.Date(Date)) ## Calculate MSE in period one year after treated period

Nor<-CONx%>%
  filter(AreaName=="New Orleans-Metairie, LA MSA")%>%
  data.frame()

CONx<-CONx%>%
  filter(MSE<=Nor$MSE*1.5) %>% ## Subset MSE that less than New Orlean MSE and multiply 1.5
  data.frame()

pl.3<-ggplot()+
  geom_line(data=CONx,aes(x=Date,y=permut,group=AreaName,colour="controls"))+
  geom_line(data=Nor,aes(x=Date,y=permut,group=AreaName,colour="treated"))+theme_bw()+
  ylab("Construction")+xlab("Year")+plot.theme +labs(color="")+
  geom_vline(xintercept = as.Date("2005-07-01"),linetype=2)+
  scale_color_manual(values = c("treated"="black","controls"="gray"),breaks = c("treated","controls"))

Manufacturing

MAN$permut<-MAN$lg-MAN$`sdid-intecept`
MAN$Date<-as.Date(MAN$Date)

MANx<-MAN%>%
  group_by(AreaName)%>%
  mutate(MSE=(mean(permut[24:27]))^2,
         Date=as.Date(Date)) ## Calculate MSE in period one year after treated period

Nor<-MANx%>%
  filter(AreaName=="New Orleans-Metairie, LA MSA")%>%
  data.frame()

MANx<-MANx%>%
  filter(MSE<=Nor$MSE*1.5) %>% ## Subset MSE that less than New Orlean MSE and multiply 1.5
  data.frame()

pl.4<-ggplot()+
  geom_line(data=MANx,aes(x=Date,y=permut,group=AreaName,colour="controls"))+
  geom_line(data=Nor,aes(x=Date,y=permut,group=AreaName,colour="treated"))+theme_bw()+
  ylab("Manufacturing")+xlab("Year")+plot.theme +labs(color="")+
  geom_vline(xintercept = as.Date("2005-07-01"),linetype=2)+
  scale_color_manual(values = c("treated"="black","controls"="gray"),breaks = c("treated","controls"))

Service providing

PRV$permut<-PRV$lg-PRV$`sdid-intecept`
PRV$Date<-as.Date(PRV$Date)

PRVx<-PRV%>%
  group_by(AreaName)%>%
  mutate(MSE=(mean(permut[24:27]))^2,
         Date=as.Date(Date)) ## Calculate MSE in period one year after treated period

Nor<-PRVx%>%
  filter(AreaName=="New Orleans-Metairie, LA MSA")%>%
  data.frame()

PRVx<-PRVx%>%
  filter(MSE<=Nor$MSE*1.5) %>% ## Subset MSE that less than New Orlean MSE and multiply 1.5
  data.frame()

pl.5<-ggplot()+
  geom_line(data=PRVx,aes(x=Date,y=permut,group=AreaName,colour="controls"))+
  geom_line(data=Nor,aes(x=Date,y=permut,group=AreaName,colour="treated"))+theme_bw()+
  ylab("Service providing")+xlab("Year")+plot.theme +labs(color="")+
  geom_vline(xintercept = as.Date("2005-07-01"),linetype=2)+
  scale_color_manual(values = c("treated"="black","controls"="gray"),breaks = c("treated","controls"))

Trade transportation and utilities

TTU$permut<-TTU$lg-TTU$`sdid-intecept`
TTU$Date<-as.Date(TTU$Date)

TTUx<-TTU%>%
  group_by(AreaName)%>%
  mutate(MSE=(mean(permut[24:27]))^2,
         Date=as.Date(Date)) ## Calculate MSE in period one year after treated period

Nor<-TTUx%>%
  filter(AreaName=="New Orleans-Metairie, LA MSA")%>%
  data.frame()

TTUx<-TTUx%>%
  filter(MSE<=Nor$MSE*1.5) %>% ## Subset MSE that less than New Orlean MSE and multiply 1.5
  data.frame()

pl.6<-ggplot()+
  geom_line(data=TTUx,aes(x=Date,y=permut,group=AreaName,colour="controls"))+
  geom_line(data=Nor,aes(x=Date,y=permut,group=AreaName,colour="treated"))+theme_bw()+
  ylab("Trade transportation and utilities")+xlab("Year")+plot.theme +labs(color="")+
  geom_vline(xintercept = as.Date("2005-07-01"),linetype=2)+
  scale_color_manual(values = c("treated"="black","controls"="gray"),breaks = c("treated","controls"))

Financial activities

FI$permut<-FI$lg-FI$`sdid-intecept`
FI$Date<-as.Date(FI$Date)

FIx<-FI%>%
  group_by(AreaName)%>%
  mutate(MSE=(mean(permut[24:27]))^2,
         Date=as.Date(Date)) ## Calculate MSE in period one year after treated period

Nor<-FIx%>%
  filter(AreaName=="New Orleans-Metairie, LA MSA")%>%
  data.frame()

FIx<-FIx%>%
  filter(MSE<=Nor$MSE*1.5) %>% ## Subset MSE that less than New Orlean MSE and multiply 1.5
  data.frame()

pl.7<-ggplot()+
  geom_line(data=FIx,aes(x=Date,y=permut,group=AreaName,colour="controls"))+
  geom_line(data=Nor,aes(x=Date,y=permut,group=AreaName,colour="treated"))+theme_bw()+
  ylab("Financial activities")+xlab("Year")+plot.theme +labs(color="")+
  geom_vline(xintercept = as.Date("2005-07-01"),linetype=2)+
  scale_color_manual(values = c("treated"="black","controls"="gray"),breaks = c("treated","controls"))

Professional and business services

BSS$permut<-BSS$lg-BSS$`sdid-intecept`
BSS$Date<-as.Date(BSS$Date)

BSSx<-BSS%>%
  group_by(AreaName)%>%
  mutate(MSE=(mean(permut[24:27]))^2,
         Date=as.Date(Date)) ## Calculate MSE in period one year after treated period

Nor<-BSSx%>%
  filter(AreaName=="New Orleans-Metairie, LA MSA")%>%
  data.frame()

BSSx<-BSSx%>%
  filter(MSE<=Nor$MSE*1.5) %>% ## Subset MSE that less than New Orlean MSE and multiply 1.5
  data.frame()

pl.8<-ggplot()+
  geom_line(data=BSSx,aes(x=Date,y=permut,group=AreaName,colour="controls"))+
  geom_line(data=Nor,aes(x=Date,y=permut,group=AreaName,colour="treated"))+theme_bw()+
  ylab("Professional and business services")+xlab("Year")+plot.theme +labs(color="")+
  geom_vline(xintercept = as.Date("2005-07-01"),linetype=2)+
  scale_color_manual(values = c("treated"="black","controls"="gray"),breaks = c("treated","controls"))

Education and health services

ES$permut<-ES$lg-ES$`sdid-intecept`
ES$Date<-as.Date(ES$Date)

ESx<-ES%>%
  group_by(AreaName)%>%
  mutate(MSE=(mean(permut[24:27]))^2,
         Date=as.Date(Date)) ## Calculate MSE in period one year after treated period

Nor<-ESx%>%
  filter(AreaName=="New Orleans-Metairie, LA MSA")%>%
  data.frame()

ESx<-ESx%>%
  filter(MSE<=Nor$MSE*1.5) %>% ## Subset MSE that less than New Orlean MSE and multiply 1.5
  data.frame()

pl.9<-ggplot()+
  geom_line(data=ESx,aes(x=Date,y=permut,group=AreaName,colour="controls"))+
  geom_line(data=Nor,aes(x=Date,y=permut,group=AreaName,colour="treated"))+theme_bw()+
  ylab("Education and health services")+xlab("Year")+plot.theme +labs(color="")+
  geom_vline(xintercept = as.Date("2005-07-01"),linetype=2)+
  scale_color_manual(values = c("treated"="black","controls"="gray"),breaks = c("treated","controls"))

Leisure and hospitality

LEI$permut<-LEI$lg-LEI$`sdid-intecept`
LEI$Date<-as.Date(LEI$Date)

LEIx<-LEI%>%
  group_by(AreaName)%>%
  mutate(MSE=(mean(permut[24:27]))^2,
         Date=as.Date(Date)) ## Calculate MSE in period one year after treated period

Nor<-LEIx%>%
  filter(AreaName=="New Orleans-Metairie, LA MSA")%>%
  data.frame()

LEIx<-LEIx%>%
  filter(MSE<=Nor$MSE*1.5) %>% ## Subset MSE that less than New Orlean MSE and multiply 1.5
  data.frame()

pl.10<-ggplot()+
  geom_line(data=LEIx,aes(x=Date,y=permut,group=AreaName,colour="controls"))+
  geom_line(data=Nor,aes(x=Date,y=permut,group=AreaName,colour="treated"))+theme_bw()+
  ylab("Leisure and hospitality")+xlab("Year")+plot.theme +labs(color="")+
  geom_vline(xintercept = as.Date("2005-07-01"),linetype=2)+
  scale_color_manual(values = c("treated"="black","controls"="gray"),breaks = c("treated","controls"))

Local Government

GOV$permut<-GOV$lg-GOV$`sdid-intecept`
GOV$Date<-as.Date(GOV$Date)

GOVx<-GOV%>%
  group_by(AreaName)%>%
  mutate(MSE=(mean(permut[24:27]))^2,
         Date=as.Date(Date)) ## Calculate MSE in period one year after treated period

Nor<-GOVx%>%
  filter(AreaName=="New Orleans-Metairie, LA MSA")%>%
  data.frame()

GOVx<-GOVx%>%
  filter(MSE<=Nor$MSE*1.5) %>% ## Subset MSE that less than New Orlean MSE and multiply 1.5
  data.frame()

pl.11<-ggplot()+
  geom_line(data=GOVx,aes(x=Date,y=permut,group=AreaName,colour="controls"))+
  geom_line(data=Nor,aes(x=Date,y=permut,group=AreaName,colour="treated"))+theme_bw()+
  ylab("Local Government")+xlab("Year")+plot.theme +labs(color="")+
  geom_vline(xintercept = as.Date("2005-07-01"),linetype=2)+
  scale_color_manual(values = c("treated"="black","controls"="gray"),breaks = c("treated","controls"))

Arrange

# extract legend Name
lge <- lapply(list(pl.0),
    function(p) {
  # Extract the legend from the plot
  g_legend <- function(p) {
    tmp <- ggplotGrob(p)
    leg <- which(sapply(tmp$grobs, function(x) x$name) == "guide-box")
    legend <- tmp$grobs[[leg]]
    return(legend)
  }
  g_legend(p)
})

#Arrange The Plot
main_plot <- grid.arrange(
    pl.0 + theme(legend.position = "none") + xlab(""),
    pl.1 + theme(legend.position = "none") + xlab(""),
    pl.2 + theme(legend.position = "none") + xlab(""),
    pl.3 + theme(legend.position = "none") + xlab(""),
    pl.4 + theme(legend.position = "none") + xlab(""),
    pl.5 + theme(legend.position = "none") + xlab(""),
    pl.6 + theme(legend.position = "none") + xlab(""),
    pl.7 + theme(legend.position = "none") + xlab(""),
    pl.8 + theme(legend.position = "none") + xlab(""),
    pl.9 + theme(legend.position = "none") + xlab(""),
    pl.10 + theme(legend.position = "none") + xlab(""),
    pl.11 + theme(legend.position = "none") + xlab(""), nrow = 4,
    left = textGrob("Log Total Quarterly Wage", rot = 90,
        gp = gpar(fontface = "bold", fontsize = 10)),
    bottom = textGrob("Year", gp = gpar(fontface = "bold", fontsize = 10)))

png("Total Log Quarterly Wage Permutation 1.5x.png",width = 16,height = 12,units = "in",res=400)
grid.arrange(main_plot, lge[[1]], nrow = 2, heights = c(20, 1))
dev.off()

## png 
##   2

Total Quarterly Wage Permutation

2023-07-07

Import Data

Total Quarterly Wage

Good Producing

Natural Resources and Mining

Construction

Manufacturing

Service providing

Trade transportation and utilities

Financial activities

Professional and business services

Education and health services

Leisure and hospitality

Local Government

Arrange