Welcome to Data Analysis and Evaluation!
Congratulations on completing your experiments! But what do all those numbers and observations actually mean? This chapter is all about Analysis (working out what the data says) and Evaluation (working out how much we can trust those results). These skills are vital for your OCR exams, as they appear in both Component 01 and Component 02.
Think of yourself as a detective. The data is your evidence, and your job is to build a case to prove your conclusion while admitting where your evidence might be a bit shaky. Let’s dive in!
1. Analysis: Processing Your Results
Once you have your raw data, you need to "clean it up" so you can see the patterns. This is what we call processing.
Qualitative vs. Quantitative Data
- Qualitative data: These are non-numerical observations. For example, "The solution turned blue." You interpret these by looking for clear, visible changes.
- Quantitative data: These are numerical measurements. For example, "The mass increased by \(2.5\text{ g}\)." This is where we use our mathematical tools.
Using the Right Number of Significant Figures
A common mistake is writing down every single digit your calculator shows. In Biology, we follow a simple rule: Your final answer should have the same number of significant figures as the measurement with the fewest significant figures used in your calculation.
Example: If you measure a length as \(1.2\text{ cm}\) (2 sig figs) and a time as \(4.55\text{ s}\) (3 sig figs), your calculated speed should be rounded to 2 sig figs.
Essential Calculations to Know
You must be able to recall and use these formulas:
- Mean: Add all your repeats together and divide by the number of repeats. (Always exclude anomalies from your mean calculation!)
- Percentage Change: Use this to compare values when the starting points were different.
\( \text{Percentage Change} = \frac{\text{New Value} - \text{Original Value}}{\text{Original Value}} \times 100 \) - Rate: This tells you how fast something happened.
\( \text{Rate} = \frac{\text{Change in Quantity}}{\text{Time Taken}} \)
Quick Review: Analysis is the process of turning raw numbers into meaningful values like means, rates, or percentages so we can spot a trend.
2. Presenting Data: The Power of Graphs
A good graph makes your results easy to understand at a glance. Here is how to get full marks on your graph-plotting questions:
Choosing Your Axes
- The Independent Variable: This is the thing you changed (e.g., Temperature). It always goes on the x-axis (bottom).
- The Dependent Variable: This is the thing you measured (e.g., Enzyme activity). It always goes on the y-axis (side).
Scales and Labels
- Labels: Always include the quantity AND the unit (e.g., \( \text{Time / s} \) or \( \text{Concentration / mol dm}^{-3} \)).
- Scales: Your graph should fill at least half of the provided grid. Use sensible intervals (e.g., 2s, 5s, or 10s).
Gradients and Intercepts
Sometimes the exam will ask you to find the gradient (the steepness) of a line. This often represents a rate.
\( \text{Gradient} = \frac{\text{Change in } y}{\text{Change in } x} \)
If the graph is a curve, you can find the gradient at a specific point by drawing a tangent (a straight line that just touches the curve at that point) and calculating the gradient of that tangent.
3. Evaluation: How Good Was the Experiment?
Evaluation isn't about saying "I did a bad job." It's about being a critical scientist and identifying the uncertainties in your work.
Accuracy vs. Precision
These two terms are often confused, but they are very different!
- Accuracy: How close your measurement is to the "true" or "accepted" value.
- Precision: How close your repeated measurements are to each other. If you get the same result every time, your work is precise, even if it's not accurate!
Identifying Anomalies
An anomaly is a result that does not fit the trend. When you spot one, you should identify it, try to explain why it happened (e.g., a measurement error), and exclude it from your mean and your graph line.
Uncertainty and Percentage Error
Every piece of equipment has a limit to how "right" it can be. This is the margin of error. For example, a thermometer might be accurate to within \( \pm 0.5^{\circ}\text{C} \).
To compare how much this error matters, we calculate Percentage Error:
\( \text{Percentage Error} = \frac{\text{Uncertainty}}{\text{Reading}} \times 100 \)
Example: If you measure \(10\text{ cm}^3\) with a syringe that has an uncertainty of \(0.1\text{ cm}^3\):
\( \frac{0.1}{10} \times 100 = 1\% \text{ error} \)
Handy Hint: To reduce percentage error, use a larger volume or a piece of equipment with a smaller uncertainty!
4. Refining the Design
The final step of evaluation is suggesting improvements. If you identified a limitation (e.g., "The temperature was hard to keep constant"), your improvement must directly fix it (e.g., "Use a thermostatically controlled water bath").
Common Limitations and Fixes:
- Limitation: Judging a color change by eye is subjective.
Improvement: Use a colorimeter to get quantitative data. - Limitation: Not enough data points to see the exact peak of a trend.
Improvement: Take readings at smaller intervals (e.g., every \(5^{\circ}\text{C}\) instead of every \(10^{\circ}\text{C}\)). - Limitation: Heat lost to the surroundings.
Improvement: Use insulation or a lid.
Did you know? Even the most famous scientists in history had "margins of error." No experiment is perfect; the skill is in knowing exactly where the imperfections lie!
Key Takeaways for the Exam
- Process carefully: Use the correct significant figures and exclude anomalies from means.
- Graph perfectly: Independent on x, dependent on y, units in labels.
- Evaluate honestly: Distinguish between precision and accuracy, and always calculate percentage error if you have the values.
- Improve logically: Make sure your improvements solve a specific problem you identified.
Note: For more details on how to set up the experiment before you analyze it, see the chapter on Planning and implementing experiments.