King’oriah (2004, p. 176) defines hypothesis as “ a theoretical proposition, which has some remote possibility of being tested statistically or indirectly.” He further explains it as some statement of some future event which could either be unknown or known vaguely at the time of prediction; but set in such a way that it can either be accepted or rejected after appropriate testing. Hypothesis meant to be tested statistically are usually formulated in a negative way.
The importance of hypothesis lies in the fact that they guide the researcher to delimit the area of research and to keep him/her in the right track. Hypothesis testing is also the basic activity of all research. No researcher will base his research findings on hearsay or unsubstantiated facts. He must have some hypothesis to test!
Characteristics of a well defined hypothesis
A well-defined hypothesis according to Ogula (1998, p.33) should have the following characteristics:
It must be testable with the available techniques
It should be possible to reject or accept the null hypothesis after data collection and analysis
It should conjecture upon a relationship between two or more variables
It should be stated clearly and unambiguously
Types of hypothesis
There are two main types of hypothesis:
Null Hypothesis
Alternative hypothesis
a) Null hypothesis
King’oriah (2004, p.177) defines null hypothesis as “the negative statement of the suspected truth that is going to be investigated through data collection and data manipulation.” For example, if one wishes to investigate whether there is any significant relationship between teacher/parental factors and students’ academic performance in private secondary schools, there could be two possibilities, one negative and the other positive:
There is no significant relationship between teacher/parental factors and students’ academic performance in private secondary schools
There is significant relationship between teacher/parental factors and students’ academic performance in private secondary schools
The negative statement (a) is stated as null hypothesis, thus:
H0 1: There is no significant relationship between teacher/parental factors and students’ academic performance in private secondary schools
b) Alternative hypothesis
King’oria op-cit (2004) defines alternative hypothesis as “the alternative set of facts that are accepted or proven to be true if the null hypothesis is rejected or proven to be not true.” From the afore given example (b), the alternative hypothesis could be stated as:
HA 1: There is significant relationship between teacher/parental factors and students’ academic performance in private secondary schools
It should be noted that occasionally you might come across some research problems that do not necessarily require statement of a working hypothesis; not all studies test hypothesis, for instance exploratory or case studies. However, as a general rule statement of a working hypothesis is a basic activity of every scientific research! Read more…