Loading Libraries

All installed packages were loaded to be used in the R Program.

library(plm)
library(knitr)
library(stringr)
library(stargazer)

## 
## Please cite as:

##  Hlavac, Marek (2022). stargazer: Well-Formatted Regression and Summary Statistics Tables.

##  R package version 5.2.3. https://CRAN.R-project.org/package=stargazer

library(tidyr)
library(dplyr)

## 
## Attaching package: 'dplyr'

## The following objects are masked from 'package:plm':
## 
##     between, lag, lead

## The following objects are masked from 'package:stats':
## 
##     filter, lag

## The following objects are masked from 'package:base':
## 
##     intersect, setdiff, setequal, union

library(lubridate)

## 
## Attaching package: 'lubridate'

## The following objects are masked from 'package:base':
## 
##     date, intersect, setdiff, union

—- Data —-

df <- load('Ozone_Drought_Final.RData')

df2 <- combinedAir.final %>%
    mutate(month = as.numeric(month)) %>%
    filter(between(month, 5, 9))

df3 <- read.csv("region_code.csv")

df2$State.Code = as.numeric(df2$State.Code)
df4 <- df2 %>%
    merge(df3, by = "State.Code")

— Calculating the Statistics (Total Monitor, Mean, SD) —

df5 <- df4 %>%
    group_by(noaa_region,USDM.categorical) %>%
    summarize(total_monitor = n(),
        ozone_max = mean(Max.Ozone),
        sd = sd(Max.Ozone))

## `summarise()` has grouped output by 'noaa_region'. You can override using the
## `.groups` argument.

df6 <- df5 %>%
    group_by(noaa_region) %>%
    mutate(percentage = (total_monitor/sum(total_monitor))*100)

df8 <- df4 %>%
    group_by(USDM.categorical) %>%
    summarize(total_monitor = n(),
        ozone_max = mean(Max.Ozone),
        sd = sd(Max.Ozone)) %>%
    ungroup() %>%
    mutate(percentage = (total_monitor/sum(total_monitor))*100,
    noaa_region = "Overall")

df9 <- df6 %>%
    rbind(df8)

df7 <- df9 %>%
    pivot_wider(names_from = USDM.categorical, values_from = c(total_monitor, ozone_max, percentage, sd)) %>%
    mutate(noaa_region = str_to_sentence(noaa_region)) %>%
    mutate_if(is.numeric, funs(round(., 2)))

## `mutate_if()` ignored the following grouping variables:
## • Column `noaa_region`

## Warning: `funs()` was deprecated in dplyr 0.8.0.
## ℹ Please use a list of either functions or lambdas:
## 
## # Simple named list: list(mean = mean, median = median)
## 
## # Auto named with `tibble::lst()`: tibble::lst(mean, median)
## 
## # Using lambdas list(~ mean(., trim = .2), ~ median(., na.rm = TRUE))
## Call `lifecycle::last_lifecycle_warnings()` to see where this warning was
## generated.

— Statistics Table —

# Move No Drought column to first column
df10 <- df7[, 1:4]
df11 <- df10[, c(1, 3, 2, 4)]

# Move the Overall row to the first row
ovr <- df11[df11$noaa_region == "Overall", ]
df12 <- rbind(ovr, df11[df11$noaa_region != "Overall", ])

kable(df12, caption = "Total Monitors", align = c("l", "c", "c", "c"))

Total Monitors
noaa_region	total_monitor_NoDrought	total_monitor_ModerateDrought	total_monitor_SevereDrought
Overall	2396798	714055	319251
Northeast	467861	49527	2371
Northern_rockies	66717	25237	9242
Northwest	54917	21232	2903
Ohio_valley	546239	69599	12344
South	274257	96036	43374
Southeast	384492	99951	45652
Southwest	130724	114636	79949
Upper_midwest	232698	30410	2777
West	238893	207427	120639

# Move No Drought column to first column
df13 <- df7[, c(1,5:7)]
df14 <- df13[, c(1, 3, 2, 4)]

# Move the Overall row to the first row
ovr <- df14[df14$noaa_region == "Overall", ]
df15 <- rbind(ovr, df14[df14$noaa_region != "Overall", ])

kable(df15, caption = "Ozone Max", align = c("l", "c", "c", "c"))

Ozone Max
noaa_region	ozone_max_NoDrought	ozone_max_ModerateDrought	ozone_max_SevereDrought
Overall	45.55	50.05	51.86
Northeast	44.94	47.11	45.93
Northern_rockies	44.26	46.32	48.41
Northwest	37.20	40.32	43.53
Ohio_valley	47.37	51.66	54.08
South	43.47	46.43	46.72
Southeast	42.17	48.11	50.84
Southwest	53.05	53.79	55.13
Upper_midwest	43.52	43.70	44.30
West	50.54	53.12	52.44

# Move No Drought column to first column
df16 <- df7[, c(1,8:10)]
df17 <- df16[, c(1, 3, 2, 4)]

# Move the Overall row to the first row
ovr <- df17[df17$noaa_region == "Overall", ]
df18 <- rbind(ovr, df17[df17$noaa_region != "Overall", ])

kable(df18, caption = "Percentage Monitor", align = c("l", "c", "c", "c"))

Percentage Monitor
noaa_region	percentage_NoDrought	percentage_ModerateDrought	percentage_SevereDrought
Overall	69.88	20.82	9.31
Northeast	90.01	9.53	0.46
Northern_rockies	65.93	24.94	9.13
Northwest	69.47	26.86	3.67
Ohio_valley	86.96	11.08	1.97
South	66.30	23.22	10.49
Southeast	72.53	18.86	8.61
Southwest	40.18	35.24	24.58
Upper_midwest	87.52	11.44	1.04
West	42.14	36.59	21.28

# Move No Drought column to first column
df18 <- df7[, c(1,11:13)]
df19 <- df18[, c(1, 3, 2, 4)]

# Move the Overall row to the first row
ovr <- df19[df19$noaa_region == "Overall", ]
df20 <- rbind(ovr, df19[df19$noaa_region != "Overall", ])
kable(df20, caption = "Standard Deviation", align = c("l", "c", "c", "c"))

Standard Deviation
noaa_region	sd_NoDrought	sd_ModerateDrought	sd_SevereDrought
Overall	14.51	15.51	14.94
Northeast	14.79	17.02	20.12
Northern_rockies	9.87	10.75	9.80
Northwest	12.15	12.80	11.79
Ohio_valley	13.42	15.06	14.90
South	15.40	16.05	16.67
Southeast	14.22	15.39	17.24
Southwest	9.89	10.14	10.22
Upper_midwest	13.09	14.21	14.47
West	16.87	16.93	15.49

Summary Statistics (Summer)

Loading Libraries

—- Data —-

— Calculating the Statistics (Total Monitor, Mean, SD) —

— Statistics Table —