### Become an OU student

Data analysis: hypothesis testing

Start this free course now. Just create an account and sign in. Enrol and complete the course for a free statement of participation or digital badge if available.

# 1 Two types of hypotheses

During the process of data-driven decision making, managers typically follow four key steps:

1. Formulating a hypothesis
2. Identifying and obtaining the appropriate data to test the hypothesis
3. Executing the test
4. Making a decision based on the results.

In this course, your focus will be on gaining a comprehensive understanding of what a hypothesis is and how to effectively formulate one.

The term hypothesis refers to an explanation proposed for a phenomenon or idea (e.g. ‘the sky is blue’). In order for a hypothesis to be considered scientific, it must be tested scientifically. In simple terms, a hypothesis is a ‘guess’ that can be tested.

Figure 2 iPhone

For example, say when conducting market research, a respondent states that the selling price of Apple iPhones was too high (i.e. it was too expensive). This is a supposition but cannot be tested. This is because you do not know what is meant by the term ‘expensive’. However, if the respondent mentions that the Apple iPhone costs over £500, this can be considered as expensive. In this case, the respondent’s supposition becomes a hypothesis. In order to test the hypothesis, market researchers need to collect some data (typically by surveying a small group of people – a sample) to study the population. The concept of population refers to the complete collection of individuals or objects that are of interest in a given context. This can include, for example, all small- and medium-sized businesses within a particular country, or the entirety of online shoppers.

The concepts of null hypothesis and alternative hypothesis are fundamental in business decision making.

The null hypothesis is an algebraic statement that expresses the currently accepted value for a parameter in the population. It is commonly used as the default position when testing a hypothesis, and the researcher presumes it to be true unless there is sufficient evidence to the contrary. The null hypothesis is usually represented by ‘H0’. For instance, if it is believed that the average annual salary in the UK is approximately £26,000, it can be considered as the null hypothesis, which can be formally stated as:

H0: The average annual salary in the UK is £26,000.

On the other hand, the alternative hypothesis is a statement or assumption that challenges the null hypothesis. It is the opposite of the null hypothesis and is what the researcher aims to demonstrate to be true. The alternative hypothesis is denoted as ‘Ha’ or ‘H1’.

An alternative hypothesis is needed because it provides an alternative explanation or theory to the null hypothesis. You will look at more examples in the next section.