---
title: "Basic Summary Statistics in R"
author: "Prof. Adam Loy"
output: html_document
---

```{r setup, include=FALSE}
knitr::opts_chunk$set(echo = TRUE)
library(ggplot2) # for plots
```

## Data

Let's again consider the [AmesHousing](http://www.amstat.org/publications/jse/v19n3/decock.pdf) data set, which provides information on the sales of individual residential properties in Ames, Iowa from 2006 to 2010. The data set contains 2930 observations, and a large number of explanatory variables involved in assessing home values. A full description of this data set can be found [here](http://www.amstat.org/publications/jse/v19n3/Decock/DataDocumentation.txt).

```{r}
AmesHousing <- read.csv("data/AmesHousing.csv")
```

After we load any data set, it can be useful to see how big it is

```{r}
dim(AmesHousing)
```

what variable types we have

```{r}
str(AmesHousing)
```

and the first few rows

```{r}
head(AmesHousing)
```



## Displaying the distribution of sales price

In lab we saw how to display univariate and bivariate distributions. For example, we can easily create a histogram of the sale price:

```{r}
ggplot(data = AmesHousing, mapping = aes(x = SalePrice)) +
  geom_histogram(fill = "steelblue2", color = "black", binwidth = 10000) +
  labs(x = "Sale price (in $)")
```

## Summarizing distributions

How much is a typical home in Ames, IA? The median seems like a reasonable choice.

```{r}
median(AmesHousing$SalePrice)
```

We can find out more information via the five-number summary:

```{r}
quantile(AmesHousing$SalePrice)
```

If we need to calculate the IQR, we can do so by hand from the above table, or use the `IQR` function.

```{r}
IQR(AmesHousing$SalePrice)
```

Another useful function is the `summary` function, which can be run a single variable, or an entire data set.

```{r}
# example with single quantitative variable
summary(AmesHousing$SalePrice)
```

```{r}
# example with single categorical variable
summary(AmesHousing$Central.Air)
```

```{r}
# example with entire data set
summary(AmesHousing)
```


Other useful summary statistics functions

- `mean`
- `sd`
- `min`
- `max`