91Ó°ÊÓ

A Probability Density Function (pdf) describes the likelihood of a continuous random variable taking on a specific value. For a variable uniformly distributed over the interval \([-c, c]\), the pdf is constant because each outcome within this interval is equally likely. Specifically, for the uniform distribution given in the exercise, the pdf is \( f_X(x) = \frac{1}{2c} \) for \( x \ \in [-c, c] \). This means that the probability is spread evenly across the interval \([-c, c]\). The pdf ensures that the total area under the curve equals 1, signifying the total probability of all outcomes. This foundational concept helps us calculate probabilities and expectations for continuous random variables.

Order statistics deal with the properties of ordered random variables. In our exercise, we are interested in finding the distribution of the median of a sample taken from a uniform distribution. For a sample of size \(2n + 1\), the median is the \( (n+1) \)-th smallest value. The pdf for the k-th order statistic in a uniform distribution is given by: \[ f_{X_{(k)}}(x) = \frac{(2n+1)!}{(k-1)!(2n+1-k)!}f_{X}(x) \bigg( \int_{-c}^{x} f_X(t) dt \bigg)^{k-1} \bigg( \int_{x}^{c} f_X(t) dt \bigg)^{2n+1-k} \] Since the median is the \( (n+1) \)-th value, we substitute \( k = n+1 \). For our uniform distribution, the integration helps find the probabilities that the median takes any given value within \([-c, c]\). By performing these integrations and simplifying, we derive the specific pdf for the median. This derived pdf shows us how the sample median is distributed.

Variance measures how spread out the values of a random variable are around the mean. For the median of our uniformly distributed sample, we start by confirming that the expectation \( E[Z] = 0 \), due to the symmetry around zero. The next goal is to find \( E[Z^2] \), which helps us calculate the variance \( \text{Var}(Z) \). Rather than solving a complex integral directly, we use known properties of the uniform distribution. For a sample median taken from a uniform distribution between \([-c, c]\), the variance formula is: \[ \text{Var}(Z) = \frac{c^2}{3n+2} \] This formula simplifies the calculation and shows the direct relationship between the spread of the uniform distribution \(c^2\) and the sample size \(n\). Higher sample sizes reduce the variance, indicating a more concentrated spread around the mean.

A continuous random variable can take any value within a given range, unlike a discrete random variable, which takes specific values. The uniform distribution on \([-c, c]\) is a classic example, where each point within the interval is equally likely. Analyzing continuous random variables involves integrating their pdf over certain ranges to find probabilities. In our example, the random variable \(X\) and the derived median \(Z\) are both continuous. When dealing with continuous variables, concepts like pdf, expected value, and variance become essential. Calculating the median's distribution requires understanding how the values of \(Z\) behave across the continuous interval \([-c, c]\). Being able to define and manipulate these continuous variables is crucial for a wide range of applications in statistics and probability theory.