Outlier Detection Statistics Example 3
Follow the full solution, then compare it with the other examples linked below.
Example 3
mediumA scientist records reaction times (ms): 245, 260, 255, 270, 250, 980, 265, 258. Use the rule to determine if 980 is an outlier. Should it be removed from the analysis?
Solution
- 1 Step 1: Sorted: 245,250,255,258,260,265,270,980. , , . Upper fence: . Since 980 > 290, it is an outlier.
- 2 Step 2: Whether to remove depends on context. If 980 ms resulted from a distraction or equipment malfunction, removal is justified. If it represents a genuine slow reaction, it should be kept but noted. Investigate the cause before deciding.
Answer
980 ms is an outlier (exceeds the upper fence of 290 ms). Whether to remove it depends on whether it resulted from an error or a genuine observation — investigate the cause.
Statistical outlier detection identifies unusual values, but the decision to remove them requires domain knowledge. Outliers may represent errors (remove), rare but genuine phenomena (keep), or data entry mistakes (correct). Blindly removing outliers can introduce bias.
About Outlier Detection
Outlier detection is the process of identifying data points that are unusually far from the rest of the dataset, using techniques like the IQR rule, z-scores, or visual inspection of box plots and scatter plots. These anomalous values may indicate measurement errors, data entry mistakes, or genuinely extreme observations.
Learn more about Outlier Detection →More Outlier Detection Examples
Example 1 easy
The data set is: 10, 12, 11, 13, 12, 14, 11, 50. Identify the outlier and explain how you know.
Example 2 mediumTest scores: 72, 75, 78, 80, 82, 85, 88, 90, 92, 95. A new student's score of 25 is added. How does
Example 4 hardA data set has mean [formula] and standard deviation [formula]. Using the z-score method, determine