Significance testing, also referred to as hypothesis testing, is a method used to determine the likelihood that a relationship between two or more variables is real or simply due to chance. It is widely used in the field of statistics to make decisions and draw conclusions about data. The purpose of significance testing is to determine the strength of evidence that supports the hypothesis that two variables are related or that a single variable has an effect on another variable. This article provides an overview of the concept of significance testing and its application in various fields.
Significance testing is based on the principles of probability and statistical inference. It involves comparing an observed result with an expected result based on a null hypothesis, which is a statement that there is no relationship between the two variables being studied. The observed result is then tested against the expected result to determine whether the observed result is statistically significant. If the observed result is statistically significant, then the null hypothesis is rejected and the alternative hypothesis is accepted. This process can be repeated for multiple variables and variables can be combined to test for overall significance.
Significance testing is used in many fields, including psychology, economics, and medical research. In psychology, the tests are used to evaluate the validity of experimental results and to determine whether a particular treatment is effective. In economics, the tests are used to determine the strength of relationships between economic variables. In medical research, the tests are used to determine whether a particular treatment is effective in reducing the symptoms of a particular disease.
Significance testing is usually performed using a variety of statistical tests, such as t-tests, ANOVAs, and chi-square tests. These tests compare the observed data with the expected data based on the null hypothesis. If the observed data is significantly different from the expected data, then the null hypothesis is rejected and the alternative hypothesis is accepted.
Significance testing is an important part of statistical analysis and can help researchers make informed decisions about their data. It is important to remember that the results of significance tests should not be interpreted as absolute truths, but rather as a means of providing guidance in making decisions.
References
Cooper, H. & Hedges, L. V. (2009). Research Synthesis and Meta-Analysis: A Step-by-Step Approach. Thousand Oaks, CA: Sage Publications.
Müller, K. E. (2019). Introduction to Significance Testing. Retrieved from https://www.statisticshowto.com/significance-testing/
Salkind, N. J. (2017). Statistics for People Who (Think They) Hate Statistics (6th ed.). Thousand Oaks, CA: Sage Publications.