MONDAY – OCTOBER 16, 2023.

Deviations of latitude and longitude:

The smallest longitude value, which is a negative number as large as -9.00718E 15, is likely an error in the data. This could be a data entry error, a formatting problem, or a coordinate that doesn’t make sense geographically. Such extreme values ​​should be investigated and possibly corrected if they are indeed errors.  The highest latitude value of 71.3012553 is also unusually high and may be an error. That’s well outside the typical US latitudes where most of your data might be. This should be re-examined.

Age restrictions:  

Age limits of 2 and 92 are not impossible, but they are at the extreme end of the age spectrum. It is important to consider whether these outliers represent genuine data points or data entry errors. For example, a 2-year-old involved in a police shooting would raise a question about the veracity of the information.

When dealing with anomalies, it is important to decide how to deal with them:

 Data entry errors:

If these anomalies are confirmed as errors, we should consider cleaning up the data either through deletion or correction. For example, if negative longitude values ​​are indeed errors, you may need to calculate or correct them. Valid data: When extreme values ​​represent valid data points, they can provide valuable information. With the analysis, for example, you can investigate why people so young or old are involved in police shootings. It is important to use domain knowledge and context to determine the meaning of these data points.

Leave a Reply

Your email address will not be published. Required fields are marked *