๐ Understanding Unbiased Estimators
In statistics, an estimator is considered unbiased if its expected value is equal to the true value of the population parameter it's estimating. In simpler terms, if you were to take many samples and calculate the estimator each time, the average of those estimates would converge to the actual population parameter.
๐ History and Background
The concept of unbiasedness became formally important with the development of statistical inference in the early 20th century, particularly through the work of statisticians like R.A. Fisher. It's a fundamental criterion for evaluating the quality of an estimator, ensuring it doesn't systematically over- or underestimate the parameter of interest.
๐ Key Principles: Unbiasedness of Sample Mean
- โ Definition of Sample Mean: The sample mean, denoted as $\bar{X}$, is calculated as the sum of all observations in a sample divided by the sample size: $\bar{X} = \frac{1}{n} \sum_{i=1}^{n} X_i$
- ๐งฎ Expected Value: The expected value of the sample mean, $E(\bar{X})$, can be derived using the linearity of expectation.
- โ Proof: $E(\bar{X}) = E(\frac{1}{n} \sum_{i=1}^{n} X_i) = \frac{1}{n} \sum_{i=1}^{n} E(X_i)$. If each $X_i$ is drawn from the same population with mean $\mu$, then $E(X_i) = \mu$ for all $i$. Therefore, $E(\bar{X}) = \frac{1}{n} \sum_{i=1}^{n} \mu = \frac{1}{n} (n\mu) = \mu$. Thus, the sample mean is an unbiased estimator of the population mean.
๐ Key Principles: Unbiasedness of Sample Variance
- ๐ Definition of Sample Variance: A common estimator for the population variance is the sample variance, often denoted as $S^2$. The formula is $S^2 = \frac{1}{n-1} \sum_{i=1}^{n} (X_i - \bar{X})^2$. Note the crucial $n-1$ term (Bessel's correction).
- ๐ง Why n-1? Using $n-1$ instead of $n$ in the denominator makes the sample variance an unbiased estimator of the population variance. If we used $n$, the estimator would be biased *low*.
- ๐งช Proof (Simplified): The proof is a bit more involved but relies on expressing the sum of squared deviations from the sample mean in terms of the deviations from the population mean. It shows that $E(S^2) = \sigma^2$, where $\sigma^2$ is the population variance. The key step involves showing that $E[\sum_{i=1}^{n} (X_i - \bar{X})^2] = (n-1)\sigma^2$.
๐ก Solved Problem 1: Sample Mean
Suppose you have a sample of 5 values: 2, 4, 6, 8, 10. Show that the sample mean is an unbiased estimator of the population mean.
Solution:
- ๐ข Calculate Sample Mean: $\bar{X} = (2+4+6+8+10)/5 = 6$
- ๐ If we assume the sample comes from a population with mean 6: Then $E(\bar{X}) = 6$, which equals the population mean, demonstrating unbiasedness.
๐งช Solved Problem 2: Sample Variance
Using the same sample: 2, 4, 6, 8, 10. Calculate the unbiased sample variance.
Solution:
- โ Calculate Deviations from the Mean: -4, -2, 0, 2, 4
- โ Square the Deviations: 16, 4, 0, 4, 16
- โ Sum the Squared Deviations and divide by n-1: $S^2 = (16 + 4 + 0 + 4 + 16) / (5-1) = 40/4 = 10$. This is an unbiased estimate of the population variance.
๐ Real-World Examples
- ๐ Quality Control: In manufacturing, the sample mean of product dimensions is used to estimate the average dimension of all products. Unbiasedness ensures consistent quality.
- ๐ Surveys: Pollsters use the sample mean of survey responses to estimate the average opinion in the population.
- ๐ฌ Scientific Experiments: Researchers use sample variance to understand the spread of data and its reliability in their experiments.
โญ Conclusion
Understanding the unbiasedness of estimators like the sample mean and variance is crucial for accurate statistical inference. By using the appropriate formulas (especially Bessel's correction for sample variance), we can obtain reliable estimates of population parameters from sample data.