Hypothesis Testing

Hypothesis testing implies a statistical method to test an assumption on a population parameter using sample data. It involves creating a null hypothesis which is the statement of the status quo. The alternate hypothesis is mutually exclusive to the null hypothesis, which means that only one out of the two can be true. 
 

The level of significance is the probability of observing the phenomena in the sample, given the null hypothesis is true. If the level of significance is very less, it means that the probability of the null hypothesis being true is also very less, and hence alternate hypothesis can be accepted.

For instance, the hypothesis is that the market will trend bearish. On the contrary, the alternate hypothesis can be that the market will trend bullish. 
If you think the market is trending bullish, you may buy the asset or if you believe the market is trending bearish, you may short the asset. But to validate the hypothesis, you need to perform the hypothesis testing.

The typical process of hypothesis testing consists of the following steps:

1. Formulate the null hypothesis.

2. Identify a test statistic that can be used to assess the validity of the null hypothesis.

3. Compute the P-value.

4. Compare the P-value to an acceptable significance value.

5. Based on whether P-value is greater or less than the significance level, accept or reject the null hypothesis