With the given data and the analysis:
-
I cleaned it first by importing the data. I then changed the name of the first column to "Country" so that I can read the data and make it work.
-
I then removed the columns that were redundant.
-
I then added NA values for missing data.
-
I then removed the countries with missing data, the data was removed such that there were no missing values.
-
I then added a new column that summed up data for all columns(offences) and added it to Total offences column, for this I first converted all columns from chr to dbl and then summed it up using rowSums()
-
I then produced a table showing country names and record of participation in organized crimes. The table shows data in decreasing order with 1 decimal place.
-
I then produced the country name that has the highest participation in organized criminal group, the country was found to be Spain.
-
I then created a scatter plot displaying relationship between Robbery and Unlawful acts involving controlled drugs or precursors columns.
-
I found out something different from that data that Spain had highest number of cases in participation of organized crimes yet it had the least corruption.
-
I then plot a correlation matrix to find some other relations in the offences.
-
I found that there is a positive correlation between Corruption and Attempted intentional homicide, which makes sense as corruption in governance increases the chances of law and order going down increases which can be seen in the number of attempts in homicides.
-
To confirm my suspicion I also fit the model using lm() and found the Std Error to be small (0.016) which supported the positive co-linearity which was found in the correlation plot.