PRDV200: Communicating with Data

When a data set is missing data, full of mistakes, or in a rough form, data scientists call it "dirty data". Data analysis software will sometimes return an error and not analyze dirty data. In other cases, the software will run an analysis, but the dirty data will bias results. This video will show you how data can become dirty and some ways to clean it. Think about data you have worked with in the past. What errors were present in the data sets?