Null Hypothesis

Student’s Name

Institutional Affiliation

A null hypothesis refers to a general statement that proposes that no statistical significance exists in a set of given observations. It shows that no variations exist between variables, or that a single variable is no different than zero. A null hypothesis is presumed to be true until statistical evidence nullifies it for an alternative hypothesis, (Koch, 2013). Null hypothesis is very important in research and should be treated in specific ways as illustrated below.

A null hypothesis is required in research since it is used in verifying statistical assumptions, to directly advance a theory, to verify that multiple experiments produce consistent results and to reduce scientific claims based on statistical noise. When drawing conclusions from collected data, a null hypothesis is rejected if there is strong enough evidence against the null hypothesis. However, a null hypothesis is accepted if there is no strong enough evidence against the null hypothesis.

There exists a relationship between a hypothesis and the identified problem. The research problem is the statement about an area of concern, a condition to be improved, a difficult situation or a troubling question. However, the identified problem does not state how to do something or to present a value question. For this reason, a hypothesis is developed to present the issue for research. During a study the identified problem is the question statement while the hypothesis is the answer to the question statement.

A feasible hypothesis refers to one which can be easily and conveniently done. A hypothesis is feasible if it includes an explanation of why the guess may be collect. A hypothesis is considered feasible where it explains the concrete terms expected to happen in the particular circumstance, and it should have two variables.

Any hypothesis should be testable and measurable. To ensure that a hypothesis is testable one needs to first begin by predicting about what will occur in a certain situation. One then assesses whether the hypothesis is observable. A testable hypothesis needs to be one that can be observed, for example a physical experiment, (Powers & Powers, 2012). To ascertain that the hypothesis is measurable, one has to make sure that the hypothesis can be compared to something else to verify whether it is true.

References

Koch, K. R. (2013). Parameter estimation and hypothesis testing in linear models. Springer Science & Business Media.

Powers, D. A., & Powers, D. I. A. N. N. E. (2012). Predicting gene frequencies in natural populations: a testable hypothesis. Isozymes. IV. Genetics and evolution, 63-84.