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

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(State.Name, USDM.categorical) %>%
    summarize(total_monitor = n(),
        mean_O3 = mean(Max.Ozone),
        sd = sd(Max.Ozone))

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

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

df8 <- df4 %>%
    group_by(USDM.categorical) %>%
    summarize(total_monitor = n(),
        mean_O3 = mean(Max.Ozone),
        sd = sd(Max.Ozone)) %>%
    ungroup() %>%
    mutate(percentage = (total_monitor/sum(total_monitor))*100,
    State.Name = "Overall")

df9 <- df6 %>%
    rbind(df8)

df7 <- df9 %>%
    pivot_wider(names_from = USDM.categorical, values_from = c(total_monitor, mean_O3, percentage, sd)) %>%
    mutate_if(is.numeric, funs(round(., 2)))

## `mutate_if()` ignored the following grouping variables:
## • Column `State.Name`

## 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$State.Name == "Overall", ]
df12 <- rbind(ovr, df11[df11$State.Name != "Overall", ])

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

Total Monitors
State.Name	total_monitor_NoDrought	total_monitor_ModerateDrought	total_monitor_SevereDrought
Overall	4488807	1489317	611303
Alabama	79554	20489	10654
Arizona	55625	129243	71580
Arkansas	36344	10846	2432
California	522397	395018	225540
Colorado	116004	52083	17270
Connecticut	38670	6051	516
Delaware	31838	4021	663
Florida	280376	70340	22832
Georgia	58139	25744	14517
Idaho	7274	7437	2015
Illinois	190976	27352	4605
Indiana	145407	12312	1819
Iowa	64312	10326	1577
Kansas	41691	12993	4492
Kentucky	129993	13638	2355
Louisiana	130771	27624	9617
Maine	63384	8374	294
Maryland	71164	9524	1212
Massachusetts	70294	8795	1733
Michigan	100919	9191	31
Minnesota	48068	12428	1164
Mississippi	39139	7975	2215
Missouri	86701	18673	2789
Montana	18594	7252	1599
Nebraska	15640	3815	1115
Nevada	53296	54330	40135
New Hampshire	47737	5956	744
New Jersey	80788	10921	853
New Mexico	62855	54949	28824
New York	186049	17319	999
North Carolina	134856	34656	13852
North Dakota	38183	14217	1315
Ohio	191516	18006	696
Oklahoma	91517	35628	14100
Oregon	21096	7648	1188
Pennsylvania	247302	18351	774
Rhode Island	11002	1260	29
South Carolina	65301	29214	12940
South Dakota	18989	7054	3022
Tennessee	95095	20922	6031
Texas	300886	129517	53699
Utah	38866	44382	11849
Vermont	12278	1330	NA
Virginia	92936	14566	1425
Washington	46621	11217	842
West Virginia	35876	1629	89
Wisconsin	115754	17514	1071
Wyoming	56734	27187	12190

# 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$State.Name == "Overall", ]
df15 <- rbind(ovr, df14[df14$State.Name != "Overall", ])

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

Ozone Max
State.Name	mean_O3_NoDrought	mean_O3_ModerateDrought	mean_O3_SevereDrought
Overall	41.53	44.03	45.99
Alabama	42.12	45.50	48.64
Arizona	48.57	45.83	51.38
Arkansas	39.42	42.08	42.37
California	41.44	44.81	44.98
Colorado	45.57	47.11	47.64
Connecticut	44.63	44.89	36.04
Delaware	40.58	45.86	44.46
Florida	37.53	41.15	41.95
Georgia	43.22	47.66	48.02
Idaho	44.92	45.56	44.31
Illinois	37.98	36.68	36.28
Indiana	44.99	48.85	54.69
Iowa	40.62	40.39	40.56
Kansas	39.02	41.06	43.91
Kentucky	44.15	49.61	48.11
Louisiana	39.02	40.49	45.82
Maine	37.62	36.37	31.99
Maryland	44.76	48.09	48.89
Massachusetts	40.07	37.57	32.90
Michigan	43.30	45.34	62.97
Minnesota	38.48	38.01	35.16
Mississippi	42.81	45.66	49.71
Missouri	45.22	44.95	49.64
Montana	37.82	36.88	35.44
Nebraska	38.06	40.28	38.59
Nevada	45.96	45.61	46.30
New Hampshire	39.55	39.86	33.19
New Jersey	39.48	40.38	41.71
New Mexico	44.76	45.23	49.14
New York	37.85	36.90	35.66
North Carolina	45.37	49.50	52.61
North Dakota	37.13	35.77	43.88
Ohio	45.10	47.71	51.26
Oklahoma	42.67	42.11	46.09
Oregon	35.41	37.54	42.22
Pennsylvania	41.14	42.11	42.51
Rhode Island	44.39	41.03	37.38
South Carolina	40.98	45.33	46.13
South Dakota	38.66	41.39	40.69
Tennessee	45.91	50.22	51.90
Texas	38.41	40.37	40.34
Utah	48.40	48.22	51.71
Vermont	38.19	36.71	NA
Virginia	43.73	48.21	53.07
Washington	34.21	35.93	35.03
West Virginia	44.15	49.75	45.72
Wisconsin	42.30	41.12	46.23
Wyoming	44.79	46.39	45.72

# 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$State.Name == "Overall", ]
df18 <- rbind(ovr, df17[df17$State.Name != "Overall", ])

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

Percentage Monitor
State.Name	percentage_NoDrought	percentage_ModerateDrought	percentage_SevereDrought
Overall	68.12	22.60	9.28
Alabama	71.87	18.51	9.62
Arizona	21.69	50.40	27.91
Arkansas	73.24	21.86	4.90
California	45.71	34.56	19.73
Colorado	62.58	28.10	9.32
Connecticut	85.48	13.38	1.14
Delaware	87.17	11.01	1.82
Florida	75.06	18.83	6.11
Georgia	59.08	26.16	14.75
Idaho	43.49	44.46	12.05
Illinois	85.67	12.27	2.07
Indiana	91.14	7.72	1.14
Iowa	84.38	13.55	2.07
Kansas	70.45	21.96	7.59
Kentucky	89.04	9.34	1.61
Louisiana	77.83	16.44	5.72
Maine	87.97	11.62	0.41
Maryland	86.89	11.63	1.48
Massachusetts	86.97	10.88	2.14
Michigan	91.63	8.34	0.03
Minnesota	77.96	20.16	1.89
Mississippi	79.34	16.17	4.49
Missouri	80.16	17.26	2.58
Montana	67.75	26.42	5.83
Nebraska	76.03	18.55	5.42
Nevada	36.07	36.77	27.16
New Hampshire	87.69	10.94	1.37
New Jersey	87.28	11.80	0.92
New Mexico	42.87	37.48	19.66
New York	91.04	8.47	0.49
North Carolina	73.55	18.90	7.55
North Dakota	71.08	26.47	2.45
Ohio	91.10	8.57	0.33
Oklahoma	64.79	25.22	9.98
Oregon	70.48	25.55	3.97
Pennsylvania	92.82	6.89	0.29
Rhode Island	89.51	10.25	0.24
South Carolina	60.77	27.19	12.04
South Dakota	65.33	24.27	10.40
Tennessee	77.92	17.14	4.94
Texas	62.15	26.75	11.09
Utah	40.87	46.67	12.46
Vermont	90.23	9.77	NA
Virginia	85.32	13.37	1.31
Washington	79.45	19.12	1.43
West Virginia	95.43	4.33	0.24
Wisconsin	86.17	13.04	0.80
Wyoming	59.03	28.29	12.68

# 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$State.Name == "Overall", ]
df20 <- rbind(ovr, df19[df19$State.Name != "Overall", ])
kable(df20, caption = "Standard Deviation", align = c("l", "c", "c", "c"))

Standard Deviation
State.Name	sd_NoDrought	sd_ModerateDrought	sd_SevereDrought
Overall	14.21	15.06	15.02
Alabama	13.27	13.64	15.36
Arizona	12.61	11.89	12.07
Arkansas	12.88	14.71	13.38
California	16.56	17.12	15.51
Colorado	12.91	12.80	13.41
Connecticut	15.03	15.79	12.86
Delaware	15.00	17.78	19.08
Florida	11.79	12.60	13.85
Georgia	13.74	14.84	16.44
Idaho	10.80	11.44	11.38
Illinois	14.47	15.66	19.09
Indiana	13.63	15.87	13.10
Iowa	11.61	12.94	14.07
Kansas	13.59	14.28	14.08
Kentucky	13.06	15.87	16.24
Louisiana	13.57	14.00	17.70
Maine	11.57	12.41	7.48
Maryland	15.35	17.45	22.14
Massachusetts	13.49	12.96	8.77
Michigan	13.92	15.54	14.21
Minnesota	11.60	11.63	10.36
Mississippi	12.91	13.83	16.42
Missouri	13.32	14.50	15.50
Montana	9.57	10.05	11.98
Nebraska	11.63	12.52	12.89
Nevada	13.79	13.47	14.22
New Hampshire	12.19	12.49	8.72
New Jersey	15.82	19.16	11.79
New Mexico	11.19	11.75	12.11
New York	13.83	15.21	10.78
North Carolina	13.40	14.50	17.76
North Dakota	9.98	9.81	9.64
Ohio	14.47	16.56	18.54
Oklahoma	13.22	14.04	14.26
Oregon	12.24	12.24	11.52
Pennsylvania	14.93	17.43	19.03
Rhode Island	13.55	14.41	9.63
South Carolina	13.01	14.16	15.76
South Dakota	10.50	11.35	11.00
Tennessee	13.67	15.40	15.23
Texas	14.96	14.83	14.50
Utah	12.87	12.81	12.26
Vermont	10.84	10.39	NA
Virginia	14.07	15.53	18.18
Washington	11.95	12.57	11.79
West Virginia	13.50	16.88	12.94
Wisconsin	12.97	14.03	16.42
Wyoming	8.51	9.20	9.13

Summary Statistics by State

—- Data —-

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

— Statistics Table —