91影视

The results from people aged 18-44 to detect the level of carboxyhemoglobin (based on the data from the Carbon Monoxide Test which was used to identify smokers).

The conditional probability of an event is the probability obtained with the additional information that some other event has already occurred.

Notation for conditional probability$P\left(B|A\right)$denotes the conditional probability of event B occurring, given that event A has already occurred.

Formula for conditional probability is as,

$P\left(B|A\right)=\frac{P\left(A鈥�鈥�\text{and}鈥�鈥�B\right)}{P\left(A\right)}$

The test for smoking involves 500 people. Out of the 500 people, 106 are smokers and 394 are non-smokers. And, 73 people get the positive test results and 427 get the negative test results.

The given information is summarized as follow in the table.

The expression $P\left(\text{Smoker| Positive}鈥�鈥�\text{test}鈥�鈥�\text{result}\right)$means:the probability that the subject is a smoker, given that the test yields a positive result.

For simplicity,define the two events as,

A be the event that the test yields positive results and B be the event that the subject is a smoker.

The probabilitythat the subject is a smoker, given that the test yields a positive result is $P\left(B|A\right)$.

The probability that the test yields a positive result, given that the subject is a smoker, is $P\left(A|B\right)$.

By using conditional probability,

$$\begin{gathered} P\left(B\left|A\right.\right)=\frac{P\left(A鈥�鈥�鈥�\text{and}鈥�鈥�鈥�B\right)}{P\left(A\right)}鈥�鈥�鈥�鈥�鈥�鈥�鈥�鈥�鈥�鈥�鈥�鈥�鈥�鈥�鈥�鈥�鈥�鈥�鈥�鈥�鈥�鈥�鈥�鈥�鈥�...\left(1\right) \\ P\left(A\left|B\right.\right)=\frac{P\left(A鈥�鈥�鈥�\text{and}鈥�鈥�鈥�B\right)}{P\left(B\right)}鈥�鈥�鈥�鈥�鈥�鈥�鈥�鈥�鈥�鈥�鈥�鈥�鈥�鈥�鈥�鈥�鈥�鈥�鈥�鈥�鈥�鈥�鈥�鈥�鈥�...\left(1\text{'}\right) \end{gathered}$$

The probability that the test yields a positive result is,

$$\begin{gathered} P\left(A\right)=\frac{\text{Subjects with positive}鈥�鈥�\text{test}鈥�鈥�\text{reults}}{\text{Total subjects}} \\ =\frac{73}{500}...\left(2\right) \\ P\left(B\right)=\frac{\text{Subjects}\text{who}\text{smoke}}{\text{Total}\text{subjects}} \\ =\frac{106}{500}...\left(3\right) \end{gathered}$$

The probability that the subject is a smoker and the test yields a positive test result is,

$$\begin{gathered} P\left(A鈥�鈥�\text{and}鈥�鈥�B\right)=\frac{\text{Subjects who smokes and yield positive test result}}{\text{Total subjects}} \\ =\frac{49}{500}...\left(4\right) \end{gathered}$$

Substitute the probability values found in equations (2) and (4) in equation (1).

$$\begin{gathered} P\left(\text{A|B}\right)=\frac{P\left(A鈥�鈥�鈥�\text{and}鈥�鈥�鈥�B\right)}{P\left(B\right)} \\ =\frac{\frac{49}{500}}{\frac{106}{500}} \\ =\frac{49}{106} \\ =0.4623 \end{gathered}$$

Thus, the probability that the subject is a smoker, given that the test yields a positive result, is 0.671.

By observing these two cases,the confusion of the inverse is as,

$P\left(\text{Smoker| Positive}鈥�鈥�\text{test}鈥�鈥�\text{result}\right)鈮�P\left(\text{Positive}鈥�鈥�\text{test}鈥�鈥�\text{result|smoker}\right)$

Here, the confusion of the inverse states that 鈥渢he probability that the subject is a smoker, given that the test yields a positive result鈥� is not equal to 鈥渢he probability of event that the subject tests positive, given that he is a smoker鈥�.