Analyzing Connecticut’s Republican primary results

This is the methodology used behind the story: Analyzing Trump’s win in Connecticut’s Republican primary.

Visit the repo for the data.

Who won the Republican presidential primary election in Connecticut?

zults <- rep_results %>%
  summarise(trump=sum(trump_count), kasich=sum(kasich_count)) %>%
  gather("candidate", "votes", 1:2)

ggplot(zults, aes(x = candidate, fill=candidate)) +
  geom_bar(stat="identity", aes(y=votes), position="dodge") +
  geom_text(aes(x= candidate, y=votes, label=paste0(as.character(round(votes/sum(votes)*100,0)),"%")), hjust=1) + coord_flip()

Mapping the results

library(rgdal)

## Loading required package: sp

## rgdal: version: 1.1-8, (SVN revision 616)
##  Geospatial Data Abstraction Library extensions to R successfully loaded
##  Loaded GDAL runtime: GDAL 2.1.0dev, released 2015/99/99
##  Path to GDAL shared files: /usr/local/share/gdal
##  Loaded PROJ.4 runtime: Rel. 4.9.2, 08 September 2015, [PJ_VERSION: 492]
##  Path to PROJ.4 shared files: (autodetected)
##  Linking to sp version: 1.2-3

require(maptools)

## Loading required package: maptools

## Checking rgeos availability: TRUE

town_shape <- readOGR(dsn="maps", layer="ctgeo")

## OGR data source with driver: ESRI Shapefile 
## Source: "maps", layer: "ctgeo"
## with 169 features
## It has 6 fields

town_shape_df <- fortify(town_shape, region="NAME10")

town_map <- rep_results %>%
  mutate(winner=ifelse(trump_per>kasich_per, "trump", "kasich"))

names(town_map)[names(town_map) == 'Town'] <- 'id'

voters_map <- left_join(town_shape_df, town_map)

## Joining by: "id"

theme_opts <- list(theme(panel.grid.minor = element_blank(),
                        panel.grid.major = element_blank(),
                        panel.background = element_blank(),
                        plot.background = element_rect(fill="#e6e8ed"),
                        panel.border = element_blank(),
                        axis.line = element_blank(),
                        axis.text.x = element_blank(),
                        axis.text.y = element_blank(),
                        axis.ticks = element_blank(),
                        axis.title.x = element_blank(),
                        axis.title.y = element_blank(),
                        plot.title = element_text(size=22)))

# plot map
ggplot(voters_map, aes(long,lat, group=group, fill=winner)) + 
  geom_polygon() + 
  geom_path(color = "white") +
  labs(title="Connecticut primary winner by town") + 
  coord_equal() + 
  theme_opts

---

Towns with the closest margins

total_margins <- rep_results[c("Town", "trump_count", "kasich_count", "vote_diff")]
total_margins <- arrange(total_margins, vote_diff)
total_margins <- subset(total_margins, (vote_diff<16) & (vote_diff > -16))

kable(total_margins)

	Town	trump_count	kasich_count	vote_diff
5	Salisbury	104	119	-15
6	Cornwall	54	43	11
7	Bloomfield	304	291	13
8	Lyme	137	124	13

Trump needed just 15 votes to tie Kasich in Salisbury.

Kasich was just 12 votes behind in Cornwall.

---

Where was Trump most successful against Kasich?

## Towns with the widest margins

percent_margins <- rep_results[c("Town", "trump_per", "kasich_per", "percent_diff")]
percent_margins <- arrange(percent_margins, percent_diff)

trump_lead <- tail(percent_margins, 5)
kable(trump_lead)

	Town	trump_per	kasich_per	percent_diff
165	Waterbury	72.1	13.5	58.6
166	Wolcott	73.8	13.7	60.1
167	East Haven	75.0	13.9	61.1
168	Sterling	75.4	14.2	61.2
169	Derby	75.3	12.4	62.9

Derby, Sterling, East Haven, and Wolcott saw the biggest win margins for Trump at about 5 to 1 votes to Kasich.

---

Where did Trump lose to Kasich?

kasich_lead <- head(percent_margins, 5)
kable(kasich_lead)

Town	trump_per	kasich_per	percent_diff
Darien	41.5	49.8	-8.3
New Canaan	41.0	47.8	-6.8
Salisbury	37.8	43.3	-5.5
West Hartford	42.7	45.1	-2.4
Westport	44.3	46.2	-1.9

Kasich beat Trump by single digit percent points in Darien, New Canaan, Salisbury, and West Hartford.

---

How did Trump do in this year’s primary election versus the 2008 primary?

rep2008 <- read.csv("data/rep2008.csv", stringsAsFactors=FALSE)
rep2008_total <- rep2008[c("Town", "mccain_total_2008")]
rep2008_percent <- rep2008[c("Town", "mccain_per_2008")]

timechange <- rep_results[c("Town", "trump_per", "trump_count")]
timechange_total <- timechange[c("Town", "trump_count")]
timechange_percent <- timechange[c("Town", "trump_per")]

timechange_total <- left_join(rep2008_total, timechange_total)

## Joining by: "Town"

timechange_percent <- left_join(rep2008_percent, timechange_percent)

## Joining by: "Town"

timechange_percent <- arrange(timechange_percent, trump_per)
timechange_percent$Town <- factor(timechange_percent$Town, levels=unique(timechange_percent$Town))

library(tidyr)
library(scales)
library(ggplot2)
devtools::install_github("hrbrmstr/ggalt")

## Skipping install for github remote, the SHA1 (111bdccb) has not changed since last install.
##   Use `force = TRUE` to force installation

library(ggalt)


gg <- ggplot(timechange_percent, aes(x=trump_per, xend=mccain_per_2008, y=Town, group=Town))
gg <- gg + geom_dumbbell(color="#a3c4dc", size=0.5, point.colour.l="#0e668b")
# gg <- gg + scale_x_continuous(label=percent)
gg <- gg + labs(x=NULL, y=NULL)
gg <- gg + theme_bw()
gg <- gg+ theme(axis.title = element_text(family = "Trebuchet MS", color="#666666", face="bold", size=6)) 
gg <- gg + theme(plot.background=element_rect(fill="#f7f7f7"))
gg <- gg + theme(panel.background=element_rect(fill="#f7f7f7"))
gg <- gg + theme(panel.grid.minor=element_blank())
gg <- gg + theme(panel.grid.major.y=element_blank())
gg <- gg + theme(panel.grid.major.x=element_line())
gg <- gg+ geom_vline(xintercept = 50)
gg <- gg + theme(axis.ticks=element_blank())
gg <- gg + theme(axis.text = element_text(size = 7))
gg <- gg + labs(title = "Percentage of votes by town, McCain 2008 vs. Trump 2016")
gg <- gg + annotate("text", x = 68, y = 40, label = "2008", size=3, colour="gray30")
gg <- gg + annotate("text", x = 68, y = 43, label = "2016", size=3, colour="gray30")
gg <- gg + annotate("point", x = 66, y = 40, colour = "#a3c4dc", size = 2) 
gg <- gg + annotate("point", x = 66, y = 43, colour = "#0e668b", size = 2)
gg <- gg + theme(legend.position="top")
gg <- gg + theme(panel.border=element_blank())
gg

## Warning: Removed 1 rows containing missing values (geom_dumbbell).

Results in towns that McCain won in 2008

## How'd Trump and Kasich do in McCain towns?

mccain_towns <- subset(rep2008, mccain_per_2008>romney_per_2008)
mccain_towns <- left_join(mccain_towns, percent_margins)

## Joining by: "Town"

names(mccain_towns)[names(mccain_towns) == 'Town'] <- 'id'

mccain_town_map <- mccain_towns %>%
  mutate(winner=ifelse(trump_per>kasich_per, "trump", "kasich"))

mccain_voters_map <- left_join(town_shape_df, mccain_town_map)

## Joining by: "id"

mccain_voters_map <- mccain_voters_map[!is.na(mccain_voters_map$winner),]

# plot map
ggplot(mccain_voters_map, aes(long,lat, group=group, fill=winner)) + 
  geom_polygon() + 
    geom_path(color = "white") +
  labs(title="2016 winners in towns that McCain won in 2008") + 
  coord_equal() + 
  theme_opts

m_town_results <- mccain_town_map %>%
  group_by(winner) %>%
  summarise(towns=n())
kable(m_town_results)

winner	towns
kasich	5
trump	159
NA	1

In 2016, trump picked up 159 towns out of the 165 towns that McCain won in 2008.

---

Results in towns that Romney won in 2008

romney_towns <- subset(rep2008, mccain_per_2008<romney_per_2008)
romney_towns <- left_join(romney_towns, percent_margins)

## Joining by: "Town"

names(romney_towns)[names(romney_towns) == 'Town'] <- 'id'

romney_town_map <- romney_towns %>%
  mutate(winner=ifelse(trump_per>kasich_per, "trump", "kasich"))

romney_voters_map <- left_join(town_shape_df, romney_town_map)

## Joining by: "id"

romney_voters_map <- romney_voters_map[!is.na(romney_voters_map$winner),]

# plot map
ggplot(romney_voters_map, aes(long,lat, group=group, fill=winner)) + 
  geom_polygon() +
    geom_path(color = "white") +
  labs(title="2016 winners in towns that Romney won in 2008") + 
  coord_equal() + 
  theme_opts

r_town_results <- romney_town_map %>%
  group_by(winner) %>%
  summarise(towns=n())
kable(r_town_results)

winner	towns
trump	4

Mitt Romney only won 4 towns in Connecticut in 2008. Trump won them all in 2016.

---

urban <- read.csv("data/urban_rural.csv", stringsAsFactors=FALSE)
urban <- urban[c("NAME10", "Type")]
colnames(urban) <- c("Town", "Type")

rep_results2 <- left_join(rep_results, urban)

## Joining by: "Town"

rep_percent <- rep_results2 %>%
  select(Town, Type, trump_per, kasich_per) %>%
  gather("candidate", "percent", 3:4)

rep_percent$candidate <- gsub("_per", "", rep_percent$candidate )

Votes by town category

ggplot(rep_percent, aes(x = Type, y = percent, fill = candidate)) +
geom_boxplot() + labs(title="Candidate support winner by town type") 

## Warning: Removed 2 rows containing non-finite values (stat_boxplot).

Trump won the majority in all town types.

rep_total <- rep_results2 %>%
  select(Type, trump_count, kasich_count) %>%
  gather("candidate", "votes", 2:3) %>%
  group_by(Type, candidate) %>%
  summarise(votes=sum(votes))
  

rep_total$candidate <- gsub("_count", "", rep_total$candidate )

ggplot(rep_total, aes(x=candidate, y=votes, fill=Type)) + geom_bar(stat="identity")  + coord_flip() +
   labs(title="Primary votes by town type")