From the course: A Day In The Life of a Data Scientist
Join today to access over 22,500 courses taught by industry experts or purchase this course individually.
Biased data sets
- Working with data sets that are created by humans makes it really difficult to end up with a perfect or perfectly representative data set. Oftentimes in my experience, there is no such thing as a perfect data set. The way in which you can mitigate the outcomes of the analysis if you have a biased data set is by acknowledging the bias that it contains, really looking into who is in this data set? What does it represent? Are there questions that we want to ask this data set that we're just not going to be able to answer with it? Really getting ahead of all of the caveats that your data set contains can help you mitigate the bias of your analysis, but it's unlikely that you'll be able to capture or catch all of the bias that exists in it. The impact on people of having a biased dataset and analysis results in communities or groups of people feeling othered or unseen by the result of an analysis, or by the organization or…
Practice while you learn with exercise files
Download the files the instructor uses to teach the course. Follow along and learn by watching, listening and practicing.
Download courses and learn on the go
Watch courses on your mobile device without an internet connection. Download courses using your iOS or Android LinkedIn Learning app.