Analyse Data (HSC SSCE Mathematics Advanced): Revision Notes

Analyse Data

Learning objectives

Understanding relative frequency

When we collect data from experiments or surveys, we often want to know how frequently different outcomes occur. Relative frequency gives us a way to express this as a proportion rather than just a raw count.

Relative frequency is the proportion of times a particular outcome occurs within a dataset. It tells us what fraction of the total observations consists of that specific outcome.

Think of relative frequency as the "part over whole" - it answers the question "what portion of my total data is this specific outcome?"

Using relative frequency to estimate probability

Relative frequency has an important connection to probability. When we conduct experiments, we can use relative frequency to estimate the probability of outcomes, especially when we don't know the theoretical probability.

For a random variable $X$, the relative frequency approximates the probability:

$P(X = x) \approx \frac{\text{frequency of } x}{\text{total frequency}}$

Here, $P(X = x)$ represents the estimated probability that the random variable $X$ takes the specific value $x$. The symbol $\approx$ means "approximately equal to" because relative frequency gives us an estimate based on our sample, not an exact theoretical probability.

Worked example: estimating probability from die rolls

Key idea: Relative frequency, calculated as $\frac{\text{Frequency}}{\text{Total frequency}}$, estimates $P(X = x)$ for a random variable $X$.

Applying relative frequency in experiments

Relative frequencies become particularly useful when we're working with experiments where the theoretical probabilities are unknown. In these situations, we must rely on experimental data to estimate probabilities.

An important principle to remember is that larger sample sizes yield more accurate estimates. When we increase the number of trials in an experiment, the relative frequency tends to get closer to the true probability. This is why statisticians prefer to work with larger datasets when making predictions.

Worked example: quality control predictions

Key idea: Relative frequencies from experiments estimate probabilities when theoretical values are unknown. These estimates improve with larger samples and can be visualised using histograms.

Exam tips

Remember!