Data Analysis, Statistics and Graphs (Unit 6)

Introduction to Data Analysis in Biology

Welcome to one of the most important parts of your International A Level Biology course! While doing experiments is exciting, the real "science" happens when you look at your results and figure out what they actually mean. In Unit 6, you aren't just expected to collect data; you must be able to process it, graph it, and use statistical tests to prove your findings aren't just down to luck. Whether you are looking at the rate of photosynthesis or the growth of bacteria, these tools will help you tell a clear and convincing story with your numbers.

1. Organizing and Presenting Data

Before you can analyze data, it must be organized properly. In the exam, you may be asked to tabulate data or record observations.

Tables and Units

When drawing tables, always follow these rules:

• The independent variable (what you change) goes in the first column.
• The dependent variable (what you measure) goes in the next columns.
• Units should only be in the column headings, never in the individual cells of the table. For example, use \( \text{mol dm}^{-3} \) or \( \text{cm}^{3} \).
• Use consistent significant figures. Your processed data (like an average) should not have more significant figures than your raw measurements.

Significant Figures and Standard Form

Biology often deals with very large numbers (like bacteria counts) or very small numbers (like solute concentrations). You must be comfortable with standard form.

Example: If a concentration is \( 0.0050 \text{ mol dm}^{-3} \), it is written in standard form as \( 5.0 \times 10^{-3} \text{ mol dm}^{-3} \).

Quick Review: Always check your calculations. If the exam asks you to "show that" a value is correct, provide your working to one more significant figure than the value given in the question to demonstrate precision.

2. Descriptive Statistics: Summarizing Data

When you have a large set of results, you need a way to summarize them. We use measures of central tendency and measures of dispersion.

Mean, Median, and Mode

• Mean: The average (sum of all values divided by the number of values).
• Median: The middle value when data is placed in order.
• Mode: The most common value.

Measures of Dispersion (Spread)

Knowing the average isn't enough; we need to know how "spread out" the data is.

• Range: The difference between the highest and lowest values. It is simple but can be misleading if there is one "weird" result (an outlier).
• Standard Deviation (SD): This is a more powerful tool. It shows how much the data varies around the mean. A small SD means your results are consistent and reliable; a large SD suggests the data is widely spread.

Common Mistake: Students often forget to ignore anomalies when calculating a mean. If one repeat is completely different from the others due to a mistake, leave it out of your average calculation!

3. Statistical Testing

In Unit 6, you must know when and why to use specific statistical tests. These tests help us decide whether to accept or reject a null hypothesis (a statement saying there is no significant difference or correlation).

The Student’s t-test

Use this when you want to compare the means of two different groups to see if the difference between them is "significant" (real) or just due to chance. Example: Comparing the mean height of plants grown in the light versus those grown in the shade.

The Chi-squared (\( \chi^{2} \)) Test

Use this when you have categorical data and you want to see if your observed results match the expected results. Example: Comparing the observed number of different colored snails in a habitat against what you expected to find based on a theory.

Correlation Coefficient

Use this to determine the strength of a relationship between two variables.

• A value of \( +1 \) is a perfect positive correlation.
• A value of \( -1 \) is a perfect negative correlation.
• A value of \( 0 \) means no correlation at all.

Did you know? Correlation does not equal causation. Just because two things happen at the same time doesn't mean one caused the other!

4. Graphs and Calculations

Graphs help visualize trends. In Unit 6, you need to be precise with your plotting and analysis.

Logarithmic Scales

Sometimes biological data covers a huge range. For example, a bacterial population might grow from 10 to 1,000,000 in a few hours. If you plotted this on a normal scale, the small numbers would all look like zero. We use logarithmic scales to "squash" the scale so we can see changes across several orders of magnitude.

Determining Gradients and Rates

To find the rate of a reaction from a graph, you calculate the gradient (slope).

• For a straight line: \( \text{gradient} = \frac{\text{change in } y}{\text{change in } x} \).
• For a curve: Draw a tangent (a straight line touching the curve at a specific point) and calculate the gradient of that line.
• The "Large Triangle" Rule: When calculating a gradient, always draw a large triangle that covers at least half of your line to ensure your calculation is accurate.

Math Rule: The equation for a straight line is \( y = mx + c \), where \( m \) is the gradient and \( c \) is the y-intercept.

5. Accuracy, Precision, and Errors

No experiment is perfect. You must be able to discuss the quality of your data.

Uncertainty and Percentage Error

Every piece of equipment has a limit to its precision (its resolution). The uncertainty is usually half of the smallest scale division.

To calculate percentage error, use this formula:
\( \text{Percentage Error} = \left( \frac{\text{Uncertainty}}{\text{Measured Value}} \right) \times 100 \)

Types of Error

• Systematic Error: An error that is the same every time, often caused by a poorly calibrated instrument (e.g., a balance that doesn't start at zero).
• Random Error: Unpredictable fluctuations caused by human error or slight changes in environmental conditions. Doing repeats helps reduce the effect of random errors.

Key Takeaway: Instrument calibration is vital! Always check that your pH meters or colorimeters are set correctly before starting your investigation.

6. Summary Checklist for the Exam

When analyzing data in your Unit 6 paper, ask yourself:

• Have I included the correct units in my table and final answer?
• Are my significant figures consistent with the raw data?
• Did I use a large triangle to find the gradient of the graph?
• Which statistical test is appropriate for this data (t-test, Chi-squared, or correlation)?
• Is there a null hypothesis I should be referring to? (Check the "Planning Investigations" section for more on this!)

Don't worry if the math feels heavy at first. With practice, identifying which formula or graph to use becomes second nature!