How to Find Outliers in Your Data
As a scientist, you’re all too familiar with the importance of having good data. Gathering accurate information and insights is critical to uncovering trends, formulating conclusions, and communicating your findings effectively.
This course will explore what an outlier is and how you can use various methods to easily detect them in your data. By recognizing these unusual values or points, you can gain deeper insight into how these extreme cases are driving changes within the larger dataset — ultimately helping inform better decision-making for future research projects.
(Not yet enrolled? Enroll now.)
-
Chapter 1: Introduction
-
Chapter 2: Methods to Identify Outliers
-
Tukey’s Method or Interquartile Range (IQR)
A data point is an outlier if it falls outside of the bounds defined by the interquartile range (IQR).
-
Box Plot
A box plot shows distribution of the data, highlighting the mean and outliers, if any.
-
Z-Score
Z-score tells how many standard deviations away the data is from the mean.
-
Grubbs' Test
Grubbs’ test is used to identify whether a minimum value or a maximum value is an outlier.
-
Dixon's Q Test
Q test is used to identify outliers in a very small dataset.
-