ACT Science: Investigate Anomalies and Outliers to Understand Experimental Variation

An anomaly or outlier is a data point that deviates significantly from the pattern or trend shown by other data. Example: Temperature measurements show 20°C, 22°C, 21°C, 45°C, 23°C. The 45°C measurement is an outlier; it doesn't fit the tight cluster of 20-23°C readings. Why investigate anomalies? They reveal experimental errors, unusual conditions, or interesting variations in data. On ACT Science, when you spot an outlier, flag it. The passage may explain it, or a question may ask why it occurred. Students who notice anomalies show sophistication in data interpretation and catch details that peers miss.

Example: A study measures plant growth under a new fertilizer. Growth: 10cm, 12cm, 11cm, 5cm, 13cm. The 5cm measurement is an outlier. A careful reader would ask: Why did that plant grow so little? Was there an error in applying the fertilizer, or was that plant sick? The passage might provide context that explains the anomaly.

Trap 1: Ignoring outliers or assuming they're measurement errors. Sometimes outliers are real variations caused by legitimate factors (individual differences, environmental conditions). Don't dismiss them without explanation. Trap 2: Over-interpreting a single outlier as evidence of a broader pattern. One anomaly doesn't prove that the treatment is unreliable; you need context to understand whether it's an isolated incident or a sign of broader problems. When you spot an outlier, ask: "What could have caused this deviation? Is there an explanation in the passage, or should I expect a question about it?"

Mark every anomaly you spot in a table or graph. Circle it and write a question mark or possible explanation next to it. This habit makes you a careful data reader.

Data Set 1: pH measurements of water samples: 7.1, 7.0, 6.9, 3.2, 7.1, 7.0. Anomaly? 3.2 is dramatically lower than the others (all around 7). Possible explanation: The sample was from near an acid spill, or the measurement equipment malfunctioned at that point. Data Set 2: Student test scores after tutoring: 75, 78, 80, 82, 77. No clear anomaly; all scores cluster around 78, showing consistent improvement. Data Set 3: Bacterial colony size after treatment: 100, 105, 98, 200, 102, 101 mm. Anomaly? 200mm is roughly twice the others. Possible explanation: Cross-contamination, measurement error, or one bacterial strain grew exceptionally well. Spotting anomalies and considering explanations makes you a better experimental interpreter.

Take five Science passages with data. Identify any anomalies. For each, write one possible explanation. By test day, this habit will make you notice details others miss.

Recognizing and investigating anomalies shows that you're reading data critically, not just skimming for the main trend. Students who notice and investigate outliers answer experimental design and data interpretation questions with greater insight, often earning points for recognizing details that peers miss.

This week, mark and investigate every anomaly you see in Science data. By test day, your attention to outliers will be automatic, making you a more sophisticated data reader and improving your overall Science score.