---
title: 'Lecture 9: Summarizing Data'
author: "Matt Blackwell"
date: "2023-10-03"
output: pdf_document
---

```{r setup, include=FALSE}
knitr::opts_chunk$set(echo = TRUE)
```

## Descriptive Stats


```{r}
library(tidyverse)
library(gapminder)
gapminder
```



```{r}
ggplot(gapminder, mapping = aes(x = lifeExp)) +
  geom_histogram(binwidth = 1) +
  geom_vline(mapping = aes(xintercept = mean(lifeExp)), color = "indianred") +
  geom_vline(mapping = aes(xintercept = median(lifeExp)), color = "dodgerblue")
```




```{r}
ggplot(gapminder, mapping = aes(x = gdpPercap)) +
  geom_histogram(binwidth = 5000) +
  geom_vline(mapping = aes(xintercept = mean(gdpPercap)), color = "indianred") +
  geom_vline(mapping = aes(xintercept = median(gdpPercap)), color = "dodgerblue")
```
```{r}
ggplot(gapminder, mapping = aes(y = lifeExp)) +
  geom_boxplot()
```




## CCES

```{r}
library(gov50data)
cces_2020
```



```{r}
cces_2020 |> 
  drop_na(turnout_self)
```



```{r}
## available case analysis

cces_2020 |> 
  summarize(mean(turnout_self, na.rm = TRUE))

```


```{r}

## complete case/listwise deletion. 
cces_2020 |> 
  drop_na() |>
  summarize(mean(turnout_self))
```



```{r}
c(5, 6, NA, 9) == NA

sum(is.na(c(5, 6, NA, 9, NA)))
mean(is.na(c(5, 6, NA, 9, NA)))
```


```{r}

cces_2020 |> 
  group_by(pid3) |>
  summarize(
    mean_turnout = mean(turnout_self, na.rm = TRUE),
    missing_turnout = mean(is.na(turnout_self))
  )
```



## Proportion tables


```{r}
cces_2020 |> 
  filter(pres_vote %in% c("Joe Biden (Democrat)", "Donald J. Trump (Republican)")) |>
  group_by(pres_vote, pid3) |>
  summarize(n = n()) |> 
  mutate(prop = n / sum(n))

```


```{r}
cces_2020 |> 
  filter(pres_vote %in% c("Joe Biden (Democrat)", "Donald J. Trump (Republican)")) |>
  group_by(pres_vote, pid3) |>
  summarize(n = n(), .groups = "drop" ) |> 
  mutate(prop = n / sum(n))
```


### Cross tabs


```{r}
cces_2020 |> 
  filter(pres_vote %in% c("Joe Biden (Democrat)", "Donald J. Trump (Republican)")) |>
  group_by(pid3, pres_vote) |>
  summarize(n = n()) |> 
  mutate(prop = n / sum(n)) |>
  pivot_wider(
    id_cols = pid3,
    names_from = pres_vote,
    values_from = prop
  )


```


```{r}
vote_by_party <- cces_2020 |> 
  filter(pres_vote %in% c("Joe Biden (Democrat)", "Donald J. Trump (Republican)")) |>
  group_by(pid3, pres_vote) |>
  summarize(n = n()) |> 
  mutate(prop = n / sum(n)) 

vote_by_party
```


```{r}
ggplot(vote_by_party, 
       mapping = aes(x = pid3, y = prop, fill = pres_vote)) +
  geom_col(position = "dodge")
```