Introduction: Why Do Biologists Need Maths?

Imagine you are investigating whether a new fertilizer makes mung beans grow taller. You measure ten plants with fertilizer and ten without. Some in the "fertilized" group are tall, but one or two are quite short. Some in the "unfertilized" group are actually taller than the others!

How do you know if the fertilizer actually worked, or if the differences you see are just down to random chance? This is where statistics come in. In your Unit 3 exam, you will be expected to process data and use statistical tests to draw valid conclusions from your practical work.

1. Describing the "Middle": Mean, Median, and Mode

When we collect a lot of data, we need a single number to represent the "typical" result. These are known as measures of central tendency.

The Mean (\( \bar{x} \))

The mean is the arithmetic average. It is the most common measure used in Biology. To find it, you add up all your values and divide by the total number of values (\( n \)).

\( \text{Mean} (\bar{x}) = \frac{\sum x}{n} \)

Quick Tip: If your data has one or two extreme "outliers" (values that are way higher or lower than the rest), the mean can be pulled away from the true center. Always check your data for anomalies before calculating!

Median and Mode

  • Median: The middle value when all data points are put in order.
  • Mode: The value that appears most often in your data set.

Key Takeaway: The mean is great for showing the "average" effect, but it doesn't tell us how spread out the data is. For that, we need more tools!

2. Measuring the "Spread": Range and Standard Deviation

Two sets of data could have the exact same mean but look completely different. One could be very consistent, while the other is all over the place. We call this dispersion.

The Range

The range is simply the difference between the largest and smallest values in a data set. While easy to calculate, it only looks at the two most extreme values and ignores everything else. It doesn't tell us if most of the data is clustered in the middle.

Standard Deviation (SD)

The standard deviation is a much more powerful tool. It tells us the average distance of each data point from the mean.

  • Small SD: The data points are all very close to the mean. This suggests your results are reliable and consistent.
  • Large SD: The data points are spread far from the mean. This suggests the results are less reliable and there is a lot of variation.

Did you know? If you plot a graph and the standard deviation bars (error bars) for two different means overlap, it usually means the difference between those means is not significant!

Key Takeaway: Standard deviation is better than range because it uses every data point and is less affected by single extreme outliers.

3. The Student's t-test: Comparing Two Means

The t-test is used when you want to find out if there is a significant difference between the means of two separate groups. For example: "Is the mean height of plants in the sun significantly different from the mean height of plants in the shade?"

How to interpret a t-test:

After doing the calculation (which involves the means and standard deviations of both groups), you get a \( t \) value. You compare this to a "critical value" in a table using a probability level (\( p \)) of \( 0.05 \).

  • If your calculated \( t \) value is greater than the critical value, the difference is significant. This means there is less than a 5% probability that the difference happened by chance.
  • If your \( t \) value is smaller than the critical value, the difference is not significant. It was likely just down to random luck.

Key Takeaway: Use a t-test when comparing two means of continuous data (like length, mass, or time).

4. The Chi-squared (\( \chi^2 \)) Test: Comparing Frequencies

The Chi-squared test is used when your data consists of frequencies (counts) in different categories. It compares the Observed (\( O \)) results you got with the Expected (\( E \)) results you thought you would get.

\( \chi^2 = \sum \frac{(O - E)^2}{E} \)

Common Exam Example: In genetics (Topic 2), if you cross two plants and expect a \( 3:1 \) ratio of tall to short offspring, you use Chi-squared to see if your actual count of plants fits that ratio.

Step-by-Step for Chi-squared:

  1. Work out what the expected numbers should be (e.g., based on a ratio).
  2. Calculate the difference between Observed and Expected (\( O - E \)).
  3. Square that difference to get rid of minus signs (\( (O - E)^2 \)).
  4. Divide by the Expected value.
  5. Add them all up to get your \( \chi^2 \) value.

Key Takeaway: Use Chi-squared when you have categorical data and want to see if your results "fit" a specific theory or ratio.

5. Correlation Coefficient: Relationships

Sometimes you aren't comparing means, but looking for a link between two variables (e.g., "As temperature increases, does the rate of enzyme activity increase?").

  • A correlation coefficient is a number between \( +1 \) and \( -1 \).
  • \( +1 \): A perfect positive correlation (both go up together).
  • \( -1 \): A perfect negative correlation (one goes up, the other goes down).
  • \( 0 \): No correlation at all.

Crucial Reminder: Correlation does not equal causation! Just because two things follow the same pattern doesn't mean one causes the other. (See Topic 1 for more on this!).

Quick Summary Checklist

Don't worry if these formulas look scary! In Unit 3, the focus is often on choosing the right test and interpreting the result. Ask yourself:

  • Am I looking for an average? Use the Mean.
  • Am I looking at the consistency of my data? Use Standard Deviation.
  • Am I comparing the means of two groups? Use the t-test.
  • Am I comparing counts/frequencies to an expected ratio? Use Chi-squared.
  • Am I looking for a relationship between two variables? Use a Correlation Coefficient.

Note: For more information on how to present this data in tables and graphs, refer to the chapter "Processing Data: Units, Significant Figures and Tables".