Contents
hide
Types and Formats of Hypothesis
The hypothesis is formulated based on the estimated relationship between two or more variables. The format of the hypothesis differs as per the nature of the relationship of variables. On the basis of formats used in research, hypotheses can be classified into different groups. They are given below:
Also Read: Concept of Hypothesis, Formulation of Hypothesis & Role of Hypothesis in Research
1. Descriptive hypothesis:
Descriptive hypothesis presents the existence, size, type, and distribution of variables. The descriptive hypothesis contains only one variable. So, it does not present the relationship between or among the variables. Thus, researchers often use a research question rather than a descriptive hypothesis. Generally, this hypothesis describes the situation and helps to clear their thinking about the likely relationships to be found. It also encourages the researcher to think about the implications of supported or rejected findings.
2. Relational hypothesis:
The hypothesis that explains the relationship between two or more two variables is known as the relational hypothesis. The relational hypothesis is divided into two groups i.e. correlation hypothesis and explanatory or causal hypothesis.
The correlational hypothesis states that the variables occur together in some specified manner without implying that one causes the other. Such weak claims are made when there are some causal forces that affect both variables or when we have not developed enough evidence to claim a stronger linkage. For example, An increase in income of people increases the market of the product.
A hypothesis that is formulated based on the assumption that change in one variable (independent variable) changes in another variable (dependent variable) is known as an explanatory or causal hypothesis. for example, sharing the company’s problem (independent variable) to the employees leads to favorable attitudes (dependent variable).
3. Directional and non-directional hypothesis:
A hypothesis that is formulated using the words more and less likes and dislikes or comparing two variables is known as a directional hypothesis. It is known as directional because it gives the direction to the relationship of two variables. For example, an employee with more work tenure in the same organization has more commitment towards the organization. Another example is, women employees are more loyal towards the organization than male employees.
If any hypothesis shows the relationship or differences between variables but does not direct the relationship such hypothesis is known as a non-directional hypothesis. In other words, even though the relationship between various variables can be estimated but their relationship remains positive or negative that cannot be declared then such a hypothesis is known as a non-directional hypothesis. For example, there is a relationship between age and job satisfaction. Another example is, there is a difference between the work culture of Nepalese employees and Bhutanese employees. These examples showed the relationship between two variables but they do not present the degree of relationship. So, they are a non-directional hypothesis.
4. Null and alternative hypothesis:
The null hypothesis is a proposition that states a definite or exact relationship between two variables. It states that the population correlation between two variables is equal to zero or that the difference in the means of sample and population is zero. In general, the null statement is expressed as no relationship between two variables or no difference between Ovo groups. The alternative hypothesis is a statement expressing a relationship between two variables or indicating differences between groups. it is exactly the opposite of the null hypothesis. The null hypothesis is denoted by Ho and the alternative hypothesis is denoted by H1. If a researcher wants to test whether training increases productivity or not then he/she can formulate the hypotheses as follows:
H0: Effective training does not increase the productivity of employees.
H1: Effective training increases the productivity of employees.
In statistics, the null and alternative hypothesis is formulated as follows:
Null hypothesis (H0): m1-m2=0 (No significant difference between a sample and population mean)
Alternative hypothesis (H1): m1-m2=0 (there is a significant difference between a sample and population mean)
Where,
m1= sample mean
m2= population mean
m1= sample mean
m2= population mean
There may be two types of errors in the use of hypothesis in research. They are given below:
Type- I error: Such error takes place when the researcher rejects the hypothesis because statistical tools reject it even though it is correct.
Type- Il error: Such error takes place when the researcher accepts a hypothesis even though it is wrong because statistical tools accept it. Such an error is more harmful than the previous error.
The researcher can draw reliable results if he/she minimizes type- I and type- Il errors. Thus, researchers should try to minimize such errors.
Some examples of hypotheses generally used by management researchers are given below:
a. Directional Hypotheses
- The more amount of remuneration, the high level of employee satisfaction.
- Men are more laborious than women.
b. Non-directional hypotheses
- There is a relationship between the tenure of employees and commitment.
- There is a difference in the attitude of Nepalese and Japanese employees.
c. Proposition based hypothesis
- Nepal’s growth is influenced by remittance inflow and their interest in investment.
d. If then hypothesis
- If employees motivated, then they will be committed.
e. Relational hypothesis
- There is a positive relationship between brand equity and sales.
Format of the statement of hypothesis
Null Hypothesis (H0): Change in promotion package does -not increase the sale of the product.
Alternative hypothesis (H1): Change in promotion package increases the sale of the product.
