library(dplyr)

Introduction

This report is based on the data set about the prison and jail population per 100,000 people per county/state between the year 1990 to 2018. More specifically focused on the county, races, gender and urbanity. The variables that I focused on are: year(from 1990 to 2018), urbancity(‘urban’,‘suburban’,‘small/mid’,‘rural’, ‘unspecified’), county names, white_jail_pop_rate, black_jail_pop_rate, latinx_jail_pop_rate, male_jail_pop_rate, and female_jail_pop_rate.

The reasons for me to focused on these variables are: first, I am curious about how these variables vary from each other and the connections between each of them. The second reason would be due to the importance of understand the increasing racial problems.

Summary Information

The highest total jail population rate is in rural urbanicity which is not surprised. And the highest total jail population rate in 2018 is in the King County, TX. And the lowest total jail population rate in 2018 is in the Wade Hampton Census Area, AK. In this case, the geometry place kind of place an important role here, specially for Alaska which is a state with less population base.There’s a significant differences between the maximum male and female jail population rate in 2018. The value for male is 71732.52, for female is 9169.99. The jail rate for male is nearly 8 times than the female jail rate. It brings thinking about the gender differences and how that influences othe perspective, in this case, the jail population rate.

## -- Attaching packages --------------------------------------- tidyverse 1.3.1 --
## v ggplot2 3.3.6     v purrr   0.3.4
## v tibble  3.1.6     v dplyr   1.0.8
## v tidyr   1.2.0     v stringr 1.4.0
## v readr   2.1.2     v forcats 0.5.1
## -- Conflicts ------------------------------------------ tidyverse_conflicts() --
## x dplyr::filter() masks stats::filter()
## x dplyr::lag()    masks stats::lag()

The Dataset

Who collected the data? Vera, the institute of justice. How was the data collected or generated? The data collected with combined sources. The prison variables draw on the NCRP and data collected directly from state departments of correction. When NCRP data is not available, these two sources are combined to create the prison variables. The jails data draws on the ASJ, COD and DCRP. The ASJ and COJ data are combined to create the jail variables. The separate variables are created using the DCRP data. Why was the data collected? Because the purpose of such data set is to provide detailed county-level data on prison and jail incarceration and related measures over time for the entire United States. So people could use such data set for more analysis. **How many observations (rows) are in your data?** 91031 **How many features (columns) are in the data?** 23 **What, if any, ethical questions or questions of power do you need to consider when working with this data?** I think one of the important ethical question I need to consider is the weight of the data set. They are not just numbers but people that lives behind the bars. What are possible limitations or problems with this data? (at least 200 words) Some of the limitations that I might face when working with this data set are the N/A values in total prison pop rate, the female prison pop rate, male prison pop rate, aapi prison pop rate, black prison pop rate, Latinx prison pop rate, native prison pop rate, and the white prison pop rate. These data have a significant number of N/A values compared to the other features. There are still a number of N/A values in other features; however, they are not substantial compared to these features listed above. The N/A values in this cause might be because the statistics are so large and complex to collect. The N/A values may lead to bias when analyzing specific categories or features of the data set. Another limitation to this data set is that the most up-to-date data is for 2018, which might be a bit outdated if I want to understand the current situation or analyze what the data shows for the recent years. A four-year data gap seems like a big problem when considering analyzing the trend of the data sets or the spread of the data. Another possible problem with the data is what is classified as “black” or “white”? Or any race? What if a person is of mixed race or mixed cultures? It might also be a factor that influences the result when computing the data.

Variable Comparison Chart

I choose to have a graph to represent the comparison between two variables, which are male jail population rate and female population rate in Los Angeles County from year 1990 to year 2018. Because gender differences is essential for us to consider about, in this case, analyze the jail population between genders could show us valuable information. The chart clearly indicates that male has a significant higher jail population rate and with a less smooth trend than female. However, both male and female have a overall decreasing pattern over time.

Map

I included this chart to show how each county link to the U.S. as the relationship of jail population rate. I choose not to use state because to use each county would offer a more precise view than states. And the N/A values could be seen more visible. According to the map, most of the counties have relatively low total jail population rate. Some of the counties have higher total jail population rate as the map indicates the red color. It’s hard to tell if there’s a pattern on the spread of high total jail population counties.

## 
## Attaching package: 'plotly'
## The following object is masked from 'package:ggplot2':
## 
##     last_plot
## The following object is masked from 'package:stats':
## 
##     filter
## The following object is masked from 'package:graphics':
## 
##     layout