概率论与数理统计 3 Discrete Random Variables and Probability Distributions(离散随机变量与概率分布) (上篇)

3.1 Random Variables

DEFINITION：

For a given sample space of some experiment, a random variable (rv) is any rule that associates a number with each outcome in（将数字与中每个结果关联起来） . In mathematical language, a random variable is a function whose domain is the sample space and whose range is the set of real numbers.

Random variables are customarily denoted by uppercase letters（大写字母表示）, such as X and Y, near the end of our alphabet.We will now use lowercase letters to represent some particular value of the corresponding random variable（用小写字母来表示相应随机变量的某些特定值）.

The notation X(s)=x means that x is the value associated with the outcome s by the rv X

DEFINITION:

Any random variable whose only possible values are 0 and 1 is called a Bernoulli random variable(伯努利随机变量).

Two Types of Random Variables

A discrete random variable（离散型随机变量） is an rv whose possible values either constitute a finite set(构成一个有限的集合) or else can be listed in an infinite sequence（在无限序列中列出） in which there is a first element, a second element, and so on ( “countably” infinite,无限可列).

A random variable is continuous（连续型随机变量） if both of the following apply:

• Its set of possible values consists either of all numbers in a single interval on the number line（数轴上单个区间内的所有数字） (possibly infinite in extent（可能是无限的范围），e.g.,from -$\infty$ to $\infty$)or all numbers in a disjoint union of such intervals(这些区间的不相交并集中的所有数,e.g.,$\left[0,10\right]\cup \left[20,30\right]$)
• No possible value of the variable has positive probability, that is, P(X = c) = 0 for any possible value c.

3.2 Probability Distributions for Discrete Random Variables

p(x) will denote the probability assigned to the value x, i.e.,p(i)=P(X=i).

DEFINITION:

The probability distribution(概率分布) or probability mass function (概率质量函数，pmf) of a discrete rv is defined for every number x by . p(x) = P(X = x) = P(all s $\in$ S: X(s)=x).

The conditions $p(x)\ge 0$and ${\sum }_{allpossiblex}^{}p(x)=1$ are required of any pmf.

A Parameter of a Probability Distribution

DEFINITION:

Suppose p(x) depends on a quantity that can be assigned any one of a number of possible values, with each different value determining a different probability distribution. Such a quantity is called a parameter of the distribution. The collection of all probability distributions for different values of the parameter is called a family(族) of probability distributions.

e.g.,

The Cumulative Distribution Function(累积分布函数)

DEFINITION：

The cumulative distribution function (cdf) F(x) of a discrete rv variable X with pmf p(x) is defined for every number x by

$$F(x)=P(X\le x)=\sum _{y:y\le x}p(y)$$

For any number x, F(x) is the probability that the observed value of X will be at most x.

For X a discrete rv, the graph of F(x) will have a jump at every possible value of X and will be flat(平的) between possible values. Such a graph is called a step function（跳跃函数）.

e.g.,

PROPOSITION:

For any two numbers a and b with $a\le b$,

$$P(a\le X\le b)=F(b)-F(a-)$$

where “a-” represents the largest possible X value that is strictly less than a.

In particular, if the only possible values are integers and if a and b are integers, then

$$P(a\le X\le b)=P(X=aora+1or...orb)=F(b)-F(a-1)$$

Taking a=b yields P(X = a) = F(a) - F(a - 1) in this case.

3.3 Expected Values

The Expected Value of X

DEFINITION:

Let X be a discrete rv with set of possible values D and pmf p(x). The expected value or mean value of X, denoted by E(X) or ${\mu }_X$ or just $\mu$, is

$$E(X)={\mu }_X=\sum _{x\in D}x\cdot p(x)$$

The Expected Value of a Function

Sometimes interest will focus on the expected value of some function h(X) rather than on just E(X).

PROPOSITION:

If the rv X has a set of possible values D and pmf p(x), then the expected value of any function h(X), denoted by E[h(X)] or ${\mu }_{h(X)}$ , is computed by

$$E[h(X)]=\sum _{D}h(x)\cdot p(x)$$

Rules of Expected Value

The h(X) function of interest is quite frequently a linear function . In this case, E[h(X)] is easily computed from E(X).

PROPOSITION:

$$E(aX+b)=a\cdot E(X)+b$$

(Or, using alternative notation, ${\mu }_{aX+b}=a\cdot {\mu }_X+b$)

Two special cases of the proposition yield two important rules of expected value.

• For any constant a, $E(aX)=a\cdot E(X)$ (take b = 0)
• For any constant b, $E(X+b)=E(X)+b$ (take a = 1)

The Variance of X

The expected value of X describes where the probability distribution is centered(概率分布的中心位置). Using the physical analogy(类比) of placing point mass p(x) at the value x on a onedimensional axis, if the axis were then supported by a fulcrum(支点) placed at $\mu$, there would be no tendency for the axis to tilt(该轴没有倾斜的趋势).

DEFINITION:

Let X have pmf p(x) and expected value $\mu$. Then the variance of X, denoted by V(X) or ${\sigma }_X^2$, or just ${\sigma }^2$, is

$$V(X)=\sum _D(x-\mu {)}^2\cdot p(x)=E[(X-\mu {)}^2]$$

The standard deviation (SD) of X is

$${\sigma }_X=\sqrt{{\sigma }_X^2}$$

A Shortcut Formula for ${\sigma }^2$

The number of arithmetic operations necessary to compute ${\sigma }^2$ can be reduced by using an alternative formula.

PROPOSITION:

$$V(X)={\sigma }^2=[\sum _D{x}^2\cdot p(x)]-{\mu }^2=E(X^2)-[E(X){]}^2$$

Rules of Variance

PROPOSITION:

$$V(aX+b)={\sigma }_{aX+b}^2=a^2\cdot {\sigma }_X^{2}and{\sigma }_{aX+b}=|a|\cdot {\sigma }_X$$

In particular,

$${\sigma }_{aX}=|a|\cdot {\sigma }_X,{\sigma }_{X+b}={\sigma }_X$$