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))

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(data_days = n_distinct(Date..Local.),
        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 = (data_days/sum(data_days))*100)

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

df9 <- df6 %>%
    rbind(df8)

df7 <- df9 %>%
    pivot_wider(names_from = USDM.categorical, values_from = c(data_days, 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 = "Data Days", align = c("l", "c", "c", "c"))

Data Days
noaa_region	data_days_NoDrought	data_days_ModerateDrought	data_days_SevereDrought
Overall	6935	6935	6633
Northeast	6935	2734	423
Northern_rockies	6840	6546	2997
Northwest	6380	4365	1786
Ohio_valley	6935	4986	1418
South	6935	6537	4488
Southeast	6935	4896	2984
Southwest	6172	6844	3864
Upper_midwest	6918	4470	775
West	5472	6100	3545

# 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	41.53	44.03	45.99
Northeast	40.27	40.69	38.84
Northern_rockies	40.45	41.71	43.53
Northwest	35.59	39.12	41.76
Ohio_valley	43.45	45.42	47.38
South	39.51	40.97	42.37
Southeast	41.12	45.10	46.90
Southwest	46.40	46.33	50.41
Upper_midwest	41.72	40.97	40.68
West	41.86	44.91	45.18

# 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 Data Days", align = c("l", "c", "c", "c"))

Percentage Data Days
noaa_region	percentage_NoDrought	percentage_ModerateDrought	percentage_SevereDrought
Overall	33.82	33.82	32.35
Northeast	68.72	27.09	4.19
Northern_rockies	41.75	39.96	18.29
Northwest	50.91	34.83	14.25
Ohio_valley	51.99	37.38	10.63
South	38.61	36.40	24.99
Southeast	46.81	33.05	20.14
Southwest	36.56	40.55	22.89
Upper_midwest	56.88	36.75	6.37
West	36.20	40.35	23.45

# 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	14.21	15.06	15.02
Northeast	14.45	16.38	15.66
Northern_rockies	10.26	10.99	10.53
Northwest	12.33	12.84	12.05
Ohio_valley	14.20	16.49	17.68
South	14.21	14.58	15.11
Southeast	13.24	14.21	16.20
Southwest	12.56	12.23	12.37
Upper_midwest	12.93	13.76	14.57
West	16.38	16.73	15.33

Summary Statistics (All Data)

Loading Libraries

—- Data —-

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

— Statistics Table —