Applications: Estimating Probabilities and Means
You'll learn how to use the Law of Large Numbers to practically estimate unknown probabilities and population means from observed data.
The Core Idea
The Law of Large Numbers tells us that as we collect more and more observations, sample averages converge to the true population mean. This isn't just theoretical—it's a powerful practical tool for estimation.
When we don't know a probability or a population mean, we can estimate it by:
- Collecting a large sample of observations
- Computing the sample average
- Using this average as our estimate of the true value
The larger our sample, the more confident we can be that our estimate is close to the truth.
Estimating Probabilities
To estimate an unknown probability P(A), we can:
- Perform the experiment n times
- Count how many times event A occurs (call this k)
- Use the relative frequency k/n as our estimate
For example, if you want to estimate the probability a thumbtack lands point-up, drop it 1000 times. If it lands point-up 620 times, your estimate is 620/1000 = 0.62.
Estimating Population Means
To estimate a population mean μ:
- Draw a random sample of size n
- Calculate the sample mean (average) of these observations
- This sample mean is your estimate of μ
For instance, to estimate the average height of students at a university, measure a random sample of 500 students and compute their average height.
Why This Works
Think of it like taking a photograph with increasing resolution. A small sample is blurry, but as you add more data points, the picture becomes sharper and sharper, converging to the true image.
Key Takeaway: The Law of Large Numbers transforms a theoretical convergence result into a practical estimation method—use large samples and relative frequencies or sample averages to reliably estimate unknown probabilities and means.