# dataset from url
violence <- read.csv("https://raw.githubusercontent.com/maharjansudhan/DATA620/master/USArrests.csv", sep = ",", header = TRUE)
violence
##             State Murder Assault Rape UrbanPop TotalCrime
## 1         Alabama   13.2     236 21.2       58      270.4
## 2          Alaska   10.0     263 44.5       48      317.5
## 3         Arizona    8.1     294 31.0       80      333.1
## 4        Arkansas    8.8     190 19.5       50      218.3
## 5      California    9.0     276 40.6       91      325.6
## 6        Colorado    7.9     204 38.7       78      250.6
## 7     Connecticut    3.3     110 11.1       77      124.4
## 8        Delaware    5.9     238 15.8       72      259.7
## 9         Florida   15.4     335 31.9       80      382.3
## 10        Georgia   17.4     211 25.8       60      254.2
## 11         Hawaii    5.3      46 20.2       83       71.5
## 12          Idaho    2.6     120 14.2       54      136.8
## 13       Illinois   10.4     249 24.0       83      283.4
## 14        Indiana    7.2     113 21.0       65      141.2
## 15           Iowa    2.2      56 11.3       57       69.5
## 16         Kansas    6.0     115 18.0       66      139.0
## 17       Kentucky    9.7     109 16.3       52      135.0
## 18      Louisiana   15.4     249 22.2       66      286.6
## 19          Maine    2.1      83  7.8       51       92.9
## 20       Maryland   11.3     300 27.8       67      339.1
## 21  Massachusetts    4.4     149 16.3       85      169.7
## 22       Michigan   12.1     255 35.1       74      302.2
## 23      Minnesota    2.7      72 14.9       66       89.6
## 24    Mississippi   16.1     259 17.1       44      292.2
## 25       Missouri    9.0     178 28.2       70      215.2
## 26        Montana    6.0     109 16.4       53      131.4
## 27       Nebraska    4.3     102 16.5       62      122.8
## 28         Nevada   12.2     252 46.0       81      310.2
## 29  New Hampshire    2.1      57  9.5       56       68.6
## 30     New Jersey    7.4     159 18.8       89      185.2
## 31     New Mexico   11.4     285 32.1       70      328.5
## 32       New York   11.1     254 26.1       86      291.2
## 33 North Carolina   13.0     337 16.1       45      366.1
## 34   North Dakota    0.8      45  7.3       44       53.1
## 35           Ohio    7.3     120 21.4       75      148.7
## 36       Oklahoma    6.6     151 20.0       68      177.6
## 37         Oregon    4.9     159 29.3       67      193.2
## 38   Pennsylvania    6.3     106 14.9       72      127.2
## 39   Rhode Island    3.4     174  8.3       87      185.7
## 40 South Carolina   14.4     279 22.5       48      315.9
## 41   South Dakota    3.8      86 12.8       45      102.6
## 42      Tennessee   13.2     188 26.9       59      228.1
## 43          Texas   12.7     201 25.5       80      239.2
## 44           Utah    3.2     120 22.9       80      146.1
## 45        Vermont    2.2      48 11.2       32       61.4
## 46       Virginia    8.5     156 20.7       63      185.2
## 47     Washington    4.0     145 26.2       73      175.2
## 48  West Virginia    5.7      81  9.3       39       96.0
## 49      Wisconsin    2.6      53 10.8       66       66.4
## 50        Wyoming    6.8     161 15.6       60      183.4
names(violence)
## [1] "State"      "Murder"     "Assault"    "Rape"       "UrbanPop"  
## [6] "TotalCrime"
# lets' find out the highest murder, assault, rape 

high_murder <- subset(violence, Murder == max(Murder))
print(high_murder)
##      State Murder Assault Rape UrbanPop TotalCrime
## 10 Georgia   17.4     211 25.8       60      254.2
high_assault <- subset(violence, Assault == max(Assault))
print(high_assault)
##             State Murder Assault Rape UrbanPop TotalCrime
## 33 North Carolina     13     337 16.1       45      366.1
high_rape <- subset(violence, Rape == max(Rape))
print(high_rape)
##     State Murder Assault Rape UrbanPop TotalCrime
## 28 Nevada   12.2     252   46       81      310.2

It is confirmed that Georgia, North Carolina and Nevada has the somewhat highest crime rates.

# lets' find out the lowest murder, assault, rape 

low_murder <- subset(violence, Murder == min(Murder))
print(low_murder)
##           State Murder Assault Rape UrbanPop TotalCrime
## 34 North Dakota    0.8      45  7.3       44       53.1
low_assault <- subset(violence, Assault == min(Assault))
print(low_assault)
##           State Murder Assault Rape UrbanPop TotalCrime
## 34 North Dakota    0.8      45  7.3       44       53.1
low_rape <- subset(violence, Rape == min(Rape))
print(low_rape)
##           State Murder Assault Rape UrbanPop TotalCrime
## 34 North Dakota    0.8      45  7.3       44       53.1

It seems like North Dakota has the least crime rates in USA.

population <- lm(TotalCrime ~ UrbanPop, data = violence)
summary(population)
## 
## Call:
## lm(formula = TotalCrime ~ UrbanPop, data = violence)
## 
## Residuals:
##     Min      1Q  Median      3Q     Max 
## -159.32  -67.09  -18.31   76.49  202.83 
## 
## Coefficients:
##             Estimate Std. Error t value Pr(>|t|)  
## (Intercept)   83.280     60.046   1.387   0.1719  
## UrbanPop       1.778      0.895   1.986   0.0528 .
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## Residual standard error: 90.69 on 48 degrees of freedom
## Multiple R-squared:  0.07593,    Adjusted R-squared:  0.05668 
## F-statistic: 3.944 on 1 and 48 DF,  p-value: 0.05276
qqnorm(resid(population))
qqline(resid(population))

It seems like lower the population there is low chances of crime and higher the population more crimes happen. The data is also linear.