# Hypothesis Development

Concept, Characteristics, Null and Alternate Hypotheses with Examples

## Understand the Process of Hypothesis Development

## What is Hypothesis?

A hypothesis is an educated guess; it is referred to as an educated guess because it is based on the literature review. A good hypothesis must be predictable and testable.

After variables are identified, and a relationship among them is established, we now need to establish if the relationships hold true or not. This starts with the formulation of hypothesis.

**A hypothesis is defined as a logically conjectured relationship between two or more variables expressed in the form of a testable statement (Sekaran, 2003).**

Hypotheses are more specific than theories, and all terms and concepts are fully defined. For instance, a researcher may like to check if Employee Empowerment has an influence on employee commitment. In the above-mentioned variable, we have a clear dependent (Employee Commitment) and an independent variable (Employee Empowerment) whereas the research would like to evaluate the influence and the direction of the relationship is positive.

In order to check if the hypothesis is to be accepted or rejected the research needs to collect the data on both Employee Empowerment and Employee Commitment by developing an instrument that has questions pertinent o the variables under study. In most cases the studies we undertake, have dependent and independent variables, the hypothesis is established in order to evaluate if a certain kind of relationship exists between variables or across groups for a single variable.

Understanding the concept of hypothesis is important, as the tests are undertaken based on the nature of the hypothesis. Hypothesis testing is a process for choosing between different alternatives. In the example of Employee Empowerment and Employee Commitment, the following two options will have to be considered to verify the researcher’s claim:

- Employee Empowerment has a significant influence on employee Commitment.
- Employee Empowerment has no significant influence on employee Commitment.

We can see that these options are mutually exclusive as well as exhaustive. Typically, in hypothesis testing, we have two options to choose from. These are termed as null hypothesis and alternate hypothesis.

## Directional and non-directional hypothesis

If, in stating the relationship between two variables or comparing two groups, terms such as *positive*, *negative*, *more than*, *less than*, and the like are used, then these are **directional hypotheses **because the direction of the relationship between the variables (positive/negative) is indicated, as in the first example below, or the nature of the difference between two groups on a variable (more than/less than) is postulated, as in the second example.

*The greater the stress experienced in the job, the lower the job satisfaction of employees.*

On the other hand, **non-directional hypotheses **are those that do postulate a relationship or difference, but offer no indication of the direction of these relationships or differences. In other words, though it may be conjectured that there is a significant relationship between two variables, we may not be able to say whether the relationship is positive or negative. Likewise, even if we can conjecture that there will be differences between two groups on a particular variable, we may not be able to say which group will be more and which less on that variable, as in the example.

*There is a difference between the work ethic values of American and Asian employees.*

Non-directional hypotheses are formulated either because the relationships or differences have never been explored, and hence there is no basis for indicating the direction, or because there have been conflicting findings in previous research studies on the variables.

## Null and Alternate Hypothesis

The hypothetico‐deductive method requires that hypotheses are falsifiable: they must be written in such a way that other researchers can show them to be false. For this reason, hypotheses are sometimes accompanied by null hypotheses.

A **null hypothesis **(H0) is a hypothesis set up to be rejected in order to support an alternate hypothesis, labeled HA. When used, the null hypothesis is presumed true until statistical evidence, in the form of a hypothesis test, indicates otherwise.

For instance, the null hypothesis may state that advertising does not affect sales. In more general terms, the null hypothesis may state that the correlation between two variables is equal to zero or that the difference in the means of two groups in the population is equal to zero.

Typically, the null statement is expressed in terms of there being no (*significant*) relationship between two variables or no (*significant*) difference between two groups.

The **alternate hypothesis**, which is the opposite of the null, is a statement expressing a relationship between two variables or indicating differences between groups.

**Null Hypothesis (H0)** – It is the presumption that is accepted as correct unless there is strong evidence against it.

**Alternative Hypothesis (H1)** – It is accepted when H0 is rejected.

Null hypothesis is a statement of **no relationship** between the variables or **no difference** between groups for a dependent variable. It is important to explain the concept of relationship and difference in hypothesis.

Hypothesis may be formulated to check for relationships, these relationships are evaluated between the dependent and independent variables. For instance Advertisement has an effect on Consumer buying behavior, or GDP has a relationship with Inflation, in both the above mentioned hypothesis there is a dependent variable (Consumer buying behavior, Inflation) which is related to/affected by an independent variable (Advertisement, GDP). The ultimate objective of these hypotheses is to check for relationship and we have two different variables.

## Examples of Hypothesis

Now there might be situations where we would like to test for differences across groups. In this case, we will have a variable that could be divided into various groups. For instance, there is a subject name **Business Research Methods** that is taught by the same teacher to three different sections.

The teacher after the first monthly exam would like to evaluate the performance of different sections (A, B, and C), he/she would like to check if there are **differences** in the marks obtained by the three different sections for the course of **Business Research Methods.**

In order to do so, he formulates hypothesis that states

**“There are differences in marks obtained across the 3 sections (A, B and C)”**.

Looking a bit closer at the hypotheses would tell us that we have one dependent variable whose data is divided into three different groups, and we would like to check if there are differences in the values across the three groups.

Here is a relational hypothesis, where the researcher would like to investigate the relationship between a dependent and independent variable.

*H1: **Satisfaction with Training Session** has a significant positive relationship with **Job Satisfaction*

Hypothesis 1 (H1) can be statistically represented as follows

**H****a****: **ρ** > **0 (The Correlation is positive)

The null hypothesis for above alternate hypothesis can be expressed as follows

**H****0****: **ρ** = **0

We can formulate a few hypotheses that would test for difference across groups.

*H3: There are significant differences in **Satisfaction with Training and Development** across **age groups*

Hypothesis 3 (H3) can be statistically represented as follows

H3: µ1 ≠ µ2 ≠ µ3 ≠ µ4 ≠ …. ≠ µk

The null hypothesis for above alternate hypothesis would be

H0: µ1 = µ2 = µ3 = µ4 = …. = µk

Where µ refers to the means, and numbers (1, 2, 3, and 4) refers to different age groups