Security and Criminal Justice Scenario Predicting Total U.S. correctional population Review the data on persons supervised by U.S. adult correctional systems by correctional status. Scenario 2 Predict the number of the United States population that will be supervised by U.S. adult correctional system in 2018. Topic 2 Year 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 Total U.S. correctional population 6.467.800 6.584.900 6.730.900 6.886.800 6.997.000 7.055.600 7.199.700 7.339.600 7.313.600 7.235.200 7.086.500 6.989.200 6.945.100 6.903.200 6.851.000 Probation 3.839.400 3.934.500 3.995.000 4.073.800 4.140.400 4.162.300 4.236.800 4.293.000 4.270.100 4.196.200 4.053.600 3.969.400 3.940.800 3.910.600 3.864.100 Parole 725.500 731.100 753.100 773.500 775.900 784.400 798.200 826.100 828.200 824.100 840.700 854.600 857.800 855.200 856.900 nario ms by correctional status. sed by U.S. adult Running head: QUANTITATIVE REASONING PROJECT 1 QUANTITATIVE REASONING PROJECT 2 Quantitative Reasoning Project: Transmitting Information Through the use of Visuals Title of the project: Predicting total US correctional population Scenario 2 Background The present paper uses three different visuals in the representation of the information about the correctional population, it evaluates the total US correctional population and how this population has changed over time. In this regard, the proposed analysis builds a linear regression model based on the US correctional population between 2000 and 2014 and uses this model to estimate what the correctional population will be in 2018. Visual 1: Scatterplot The scatterplot shown in figure 1 contains the information about the correctional population each of the years. This visual is especially useful in understanding the existing trends. It shows two distinct regions, in which the correctional population increases (until 2007) and in which the correctional population decreases (after 2007). Visual 1. Scatterplot QUANTITATIVE REASONING PROJECT 3 Visual 2: Histogram Visual 2 shows the histogram resulting from the analysis of the information contained in the dataset. This visual is useful in identifying the most frequently found correctional population, as well as the minimum and maximum populations. However, it does not provide temporal information. Visual 2. Frequency distribution Visual 3. Box and whisker plot Lastly, visual 3 shows the box and whisker plot. This visual provides information about the average correctional population and the spread, measured through both the quartiles and the whiskers. It is especially useful for identifying outliers and observing the variability of data. QUANTITATIVE REASONING PROJECT 4 Figure 3. Variability Forecasting According to the data shown in figure 1, the model used in the forecast of the correctional population should only consider the data from 2007 on. Considering how the data after that date seem to follow a reasonably straight line, the linear regression model seems to be a suitable method for the estimation of the population in 2018. The equation for this linear regression model is 𝐶𝑜𝑟𝑟𝑒𝑐𝑡𝑖𝑜𝑛𝑎𝑙 𝑝𝑜𝑝𝑢𝑙𝑎𝑡𝑖𝑜𝑛 = 76664 ∗ 𝑌𝑒𝑎𝑟 + 1.61 ∗ 108 . Substituting the year by 2018, the forecasted population is 𝐶𝑜𝑟𝑟𝑒𝑐𝑡𝑖𝑜𝑛𝑎𝑙 𝑝𝑜𝑝𝑢𝑙𝑎𝑡𝑖𝑜𝑛 = 76664 ∗ 2018 + 1.61 ∗ 108 = 6,492,048. Central tendency The central tendency measures of the data are its mean and median values. According to the data provided, the mean value is of 6,964,257 and the median of 6,967,150. The high similarity between both values points to a low skewness of the data, confirming that there are no substantial outliers (Mitchell & Leachman, 2014). QUANTITATIVE REASONING PROJECT Reference Mitchell, M., & Leachman, M. (2014, October 28). Changing Priorities: State Criminal Justice Reforms and Investments in Education. Retrieved June 23, 2018, from https://www.cbpp.org/research/changing-priorities-state-criminal-justice-reforms-andinvestments-in-education 5
Purchase answer to see full attachment