Every researcher is required to establish hypotheses in order to predict, tentatively, the outcome of the research.
What is a null hypothesis and why does research need one?
Every researcher is required to establish hypotheses in order to predict, tentatively, the outcome of the research (Leedy & Ormrod, 2016). A null hypothesis is “the result of chance alone”, there’s no patterns, differences or relationships between variables (Leedy & Ormrod, 2016). Whether the outcome is positive or negative, the requirement of a null hypothesis in addition of your alternative hypothesis means that your research (and you as the researcher as well) is not one-sided (Bland & Altman, 1994). In other words, you and the research are open to the possibility that maybe or maybe not a difference between the variables exists and open to the possibility that the outcome of the research is due to a reason (alternative hypothesis) or a chance (null hypothesis) (Leedy & Ormrod, 2016; Pierce, 2008 & Bland & Altman, 1994).
After collecting data, the hypotheses must be tested in order to reach a conclusion (Daniel & Cross, 2013). A null hypothesis is tested when the probability of the results are “due to chance alone” but the data collected reasonably suggest that something (a factor, a reason or other variable) in the studied environment/population leads to a difference/relationship/pattern between them (Leedy & Ormrod, 2016 & Pierce, 2008). A null hypothesis is used to draw conclusions from the collected data when the “process of comparing data” with the expected outcome (results) of chance alone (Leedy & Ormrod, 2016). When the result is because of “something other than chance”, the null hypothesis is rejected and the alternative hypothesis comes to play because the data, indirectly, led us to support it (Leedy & Ormrod, 2016). The alternative hypothesis might be the one the researcher wants to be accepted, however, it “can only be accepted” if after the collected data shows that the null hypothesis “has been rejected” (Pierce, 2008).
Bland, J. M., & Altman, D. G. (1994). Statistics Notes: One and two sided tests of significance. British Medical Journal (BMJ), 309, 248-248. doi:10.1136/bmj.309.6949.248
Daniel, W. W., & Cross, C. L. (2013). Chapter 7 Hypothesis Testing. In Biostatistics: A Foundation for Analysis in the Health Sciences (10th ed., pp. 214-303). Hoboken, NJ: Wiley. Retrieved February 13, 2018, from https://msph1blog.files.wordpress.com/2016/10/biostatistics-_daniel-10th1.pdf.
Leedy, P. D., & Ormrod, J. E. (2016). Practical Research: Planning and Design (11th ed.). NJ: Pearson Education. Retrieved February 13, 2018, from https://digitalbookshelf.argosy.edu/#/books/9781323328798/cfi/6/6!/4/2/2/[email protected]:0.
Pierce, T. (2008, September). Independent samples t-test. Retrieved February 13, 2018, from http://www.radford.edu/~tpierce/610%20files/Data%20Analysis%20for%20Professional%20Psychologists/Independent%20samples%20t-test%2010-02-09.pdf