### Definition#

By definition the P-value is a measure of the probability of obtaining a result that is different from the null hypothesis. The Null Hypotheis is the hypothesis that the result is the same as the one we are testing, in other words, the hypothesis that nothing has changed.

The P-value is a number between 0 and 1. The closer to 0 the p-value is, the more likely the result is to be different from the null hypothesis. Otherwise, if the p-value is closer to 1, the result is more likely to be the same as the null hypothesis.

### How to calculate#

To calculate the p-value, we sum 3 components:

1. The probability of the result being the observation.
2. The probability of the result being something else that is equally rate to the observation.
3. The probability of observing something rarer or more extreme than the observation.

Let’s see an example in practice.

### Example#

You have flipped a coin 2 times. Both times the coin landed on heads. You start to think that your coin is special, and you want to know if it is. To check that you start with the Null Hypothesis.

• Null Hypothesis (H0): Even thought my coin landed heads twice in a row, it is no different from any other coin.
• The alternative hypothesis (H1): My coin is special.

The possible outcomes for flipping a coin 2 times are:

• Tails and Tails

With those possibilities in mind, we can start to calculate the p-value, using the 3 components I previously mentioned.

(1) The probability of the result being the observation.

1 possibility of it being Heads and Heads, out of 4 outcomes.

``````1/4 = 0.25
``````

(2) The probability of the result being something else that is equally rate to the observation.

1 possibility of it being Tails and Tails, out of 4 outcomes.

``````1/4 = 0.25
``````

(3) The probability of observing something rarer or more extreme than the observation.

There is no other possibility that is more rarer or extreme that the observation.

``````0
``````

Now we can calculate the p-value.

``````P-value = 0.25 + 0.25 + 0 = 0.5
``````

With the P-value in hand, we define the threshold of significance. A common threshold is 0.05, which means that if the p-value is lower than 0.05, we can say that the result is different from the null hypothesis. In our case the P-value is 0.5, which is higher than 0.05, so we can say that the result is the same as the null hypothesis.

The conclusion is that our coin is not special.