5.4.1 The Probability Distribution Table

In this topic we will learn how to:

  • draw a probability distribution table relating to a given situation involving a discrete random variable XX, and calculate E(X)E(X) and Var(X)Var(X)

A random variable is one that can take multiple values and in some cases these values may be defined by a function. Random variables are denoted by a capital letter, for example, XX. A discrete random variable only takes exact values, for example, 11, 22, 33, and so on. The sum of the probabilities of all the values governed by a particular random variable adds up to 11. This can be denoted by,
P(X=x)=1P(X = x) = 1Where XX represents the random variable and xx represents all the values that the random variable can take.
This may also be written as,
p=1p = 1Where pp represents P(X=x)P(X = x).

If we know the probabilities of the values that the random variable can take, we can draw a probability distribution table.
Let’s look at an example.


Example 1
The random variable XX, takes values 11, 22, 33 and 44. It is given that P(X=1)=0.1P(X = 1) = 0.1, P(X=2)=0.4P(X = 2) = 0.4, P(X=3)=0.4P(X = 3) = 0.4 and P(X=4)=0.1P(X = 4) = 0.1. Draw the probability distribution table.

The probability distribution table for the problem above would look like this,

xx
11
22
33
44
P(X=x)P(X = x)
0.10.1
0.40.4
0.40.4
0.10.1

Using the probability distribution table we can also find the E(X)E(X) and Var(X)Var(X). The formula for mean is,
E(X)=ΣxpE(X) = \Sigma xpThe formula for variance is,
Var(X)=Σx2p[E(X)]2Var(X) = \Sigma x^{2}p - [E(X)]^{2}Using the example above, let’s find E(X)E(X) and Var(X)Var(X),
E(X)=ΣxpE(X) = \Sigma xpE(X)=1(0.1)+2(0.4)+3(0.4)+4(0.1)E(X) = 1(0.1) + 2(0.4) + 3(0.4) + 4(0.1)E(X)=2.5E(X) = 2.5Var(X)=Σx2p[E(X)]2Var(X) = \Sigma x^{2}p - [E(X)]^{2}Σx2p=12(0.1)+22(0.4)+32(0.4)+42(0.1)\Sigma x^{2}p = 1^{2}(0.1) + 2^{2}(0.4) + 3^{2}(0.4) + 4^{2}(0.1)Σx2p=6.9\Sigma x^{2}p = 6.9Var(X)=6.9(2.5)2Var(X) = 6.9 - (2.5)^{2}Var(X)=0.65Var(X) = 0.65


Let’s look at some past paper questions.

1. The random variable XX takes the values 11, 22, 33, 44 only. The probability that xx takes the value xx is kx(5x)kx(5 - x), where kk is a constant. (9709/52/F/M/21 number 4)

(a) Draw up the probability distribution table for XX, in terms of kk.

We are given that,
P(X=x)=kx(5x)P(X = x) = kx(5 - x)We can use that function to find the probabilities for the values that xx takes. Let’s start with 11,
P(X=x)=kx(5x)P(X = x) = kx(5 - x)P(X=1)=k(1)(51)P(X = 1) = k(1)(5 - 1)P(X=1)=4kP(X = 1) = 4kLet’s evaluate 22,
P(X=x)=kx(5x)P(X = x) = kx(5 - x)P(X=2)=k(2)(52)P(X = 2) = k(2)(5 - 2)P(X=2)=6kP(X = 2) = 6kLet’s evaluate 33,
P(X=x)=kx(5x)P(X = x) = kx(5 - x)P(X=3)=k(3)(53)P(X = 3) = k(3)(5 - 3)P(X=3)=6kP(X = 3) = 6kLet’s evaluate 44,
P(X=x)=kx(5x)P(X = x) = kx(5 - x)P(X=4)=k(4)(54)P(X = 4) = k(4)(5 - 4)P(X=4)=4kP(X = 4) = 4kNow that we have all the probabilities in terms of kk, we can now draw up a probability distribution table,

xx
11
22
33
44
P(X=x)P(X = x)
4k4k
6k6k
6k6k
4k4k

Therefore, the final answer is,

xx
11
22
33
44
P(X=x)P(X = x)
4k4k
6k6k
6k6k
4k4k

(b) Show that Var(X)=1.05Var(X) = 1.05.

The formula for variance under discrete conditions is,
Var(X)=Σx2p[E(X)]2Var(X) = \Sigma x^{2}p - [E(X)]^{2}To be able to use this formula we need to find Σx2p\Sigma x^{2}p and the mean. To do that, we need to first evaluate kk, we will use the idea that,
P(X=x)=1P(X = x) = 1P(X=1)+P(X=2)+P(X=3)+P(X=4)=1P(X = 1) + P(X = 2) + P(X = 3) + P(X = 4) = 1Substitute in the values in terms of kk from the probability distribution table,
4k+6k+6k+4k=14k + 6k + 6k + 4k = 1Simplify and solve for kk,
20k=120k = 1k=120k = \frac{1}{20}We can now draw up a new probability distribution table in which the kk has been substituted,

xx
11
22
33
44
P(X=x)P(X = x)
420\frac{4}{20}
620\frac{6}{20}
620\frac{6}{20}
420\frac{4}{20}

We can now find the mean,
E(X)=ΣxpE(X) = \Sigma xpE(X)=1(420)+2(620)+3(620)+4(420)E(X) = 1\left(\frac{4}{20}\right) + 2\left(\frac{6}{20}\right) + 3\left(\frac{6}{20}\right) + 4\left(\frac{4}{20}\right)E(X)=2.5E(X) = 2.5Note: If the distribution is symmetrical, then the mean is the midpoint of the xx values.

Now let’s find Σx2p\Sigma x^{2}p,
Σx2p=12(420)+22(620)+32(620)+42(420)\Sigma x^{2}p = 1^{2}\left(\frac{4}{20}\right) + 2^{2}\left(\frac{6}{20}\right) + 3^{2}\left(\frac{6}{20}\right) + 4^{2}\left(\frac{4}{20}\right)Σx2p=7.3\Sigma x^{2}p = 7.3Now let’s substitute back into the formula for variance,
Var(X)=Σx2p[E(X)]2Var(X) = \Sigma x^{2}p - [E(X)]^{2}Var(X)=7.3(2.5)2Var(X) = 7.3 - (2.5)^{2}Var(X)=7.36.25Var(X) = 7.3 - 6.25Var(X)=1.05Var(X) = 1.05Therefore, we have proved that,
Var(X)=1.05Var(X) = 1.052. A fair spinner has sides numbered 11, 22, 22. Another fair spinner has sides numbered 2-2, 00, 11. Each spinner is spun. The number on the side on which a spinner comes to rest is noted. The random variable XX is the sum of the numbers for the two spinners. (9709/52/M/J/21 number 4)

(a) Draw up the probability distribution table for XX.

Since there are two spinners, we can draw a possibility space diagram to show all possible outcomes. Label the yy-axis with, spinner 11 and the xx-axis with, spinner 22. Inside the diagram add up the sum of the numbers for the two spinners,

Rendered by QuickLaTeX.com

From the diagram we can tell that,
P(X=1)=19P(X = -1) = \frac{1}{9}P(X=0)=29P(X = 0) = \frac{2}{9}P(X=1)=19P(X = 1) = \frac{1}{9}P(X=2)=39P(X = 2) = \frac{3}{9}P(X=3)=29P(X = 3) = \frac{2}{9}Now that we have all the probabilities, we can now draw a probability distribution table,

xx
1-1
00
11
22
33
P(X=x)P(X = x)
19\frac{1}{9}
29\frac{2}{9}
19\frac{1}{9}
39\frac{3}{9}
29\frac{2}{9}

Therefore, the final answer is,

xx
1-1
00
11
22
33
P(X=x)P(X = x)
19\frac{1}{9}
29\frac{2}{9}
19\frac{1}{9}
39\frac{3}{9}
29\frac{2}{9}

(b) Find E(X)E(X) and Var(X)Var(X).

To find the mean, we use the formula,
E(X)=ΣxpE(X) = \Sigma xpE(X)=1(19)+0(29)+1(19)+2(39)+3(29)E(X) = -1\left(\frac{1}{9}\right) + 0\left(\frac{2}{9}\right) + 1\left(\frac{1}{9}\right) + 2\left(\frac{3}{9}\right) + 3\left(\frac{2}{9}\right)E(X)=43E(X) = \frac{4}{3}To find the variance, we use the formula,
Var(X)=Σx2p[E(X)]2Var(X) = \Sigma x^{2}p - [E(X)]^{2}Let’s find Σx2p\Sigma x^{2}p,
Σx2p=(1)2(19)+02(29)+12(19)+22(39)+32(29)\Sigma x^{2}p = \left(-1\right)^{2}\left(\frac{1}{9}\right) + 0^{2}\left(\frac{2}{9}\right) + 1^{2}\left(\frac{1}{9}\right) + 2^{2}\left(\frac{3}{9}\right) + 3^{2}\left(\frac{2}{9}\right)Σx2p=329\Sigma x^{2}p = \frac{32}{9}Substitute back into the formula for variance,
Var(X)=Σx2p[E(X)]2Var(X) = \Sigma x^{2}p - [E(X)]^{2}Var(X)=329(43)2Var(X) = \frac{32}{9} - \left(\frac{4}{3}\right)^{2}Var(X)=169Var(X) = \frac{16}{9}Therefore, the final answer is,
Var(X)=169Var(X) = \frac{16}{9}