Different studies might have different types of significance which are relevant to different populations or fields of study for different reasons. Mainly, there are some types of significance of the study, namely theoretical significance, practical significance, commercial significance, statistical significance, and clinical significance. However, the most common significance found in almost all studies are theoretical and practical significance or how the study can expand the body of knowledge and can solve the practical problems arising from the surroundings. Each of the significance types will be explained in detail in the following paragraphs.
Theoretical significance refers to the contribution that a study makes to the existing body of theories in a specific field. This type of significance may be confirming, refuting, or adding nuance to the existing theories in the field, or may be proposing an entirely new theory that expands the body of knowledge. The following is an example of theoretical significance of a study where it incorporates two different theories:
“This study contributes by exploring the factors that will help explain the mechanism to build a loyal customer based through CSR. Additionally, the present study integrates three theoretical approaches (i.e., social identity, stakeholder, and signaling theories). In doing so, it expands previous studies that have been based on the social identity perspective almost exclusively to understand the CSR-loyalty link.”
Practical significance refers to the condition where the expected results or findings of our proposed study will be meaningful to society at large in the ‘real world’, or where they can propose solutions that address real and immediate social problems. Sometimes, practical significance is also called social or political significance. The magnitude of this social significance refers to the population we set out for our study. Here is an example of social significance:
The continued development of state-of-the art NLP tools tailored to climate policy will allow climate researchers and policy makers to extract meaningful information from this growing body of text, to monitor trends over time and administrative units, and to identify potential policy improvements.
Commercial significance refers to the condition when the research results can be commercialized as a product or service. This significance might occur when the research is focusing on developing a specific technology that can be immediately adapted and sold. However, this type of significance is not relevant to most studies. The following is an example of commercial significance:
“The measurement technology described in this study provides state of the art performance and could enable the development of low cost devices for aerospace applications.”
Statistical significance refers to the condition where the results of our proposed study will imply a true causal relationship. This is usually found in an experimental research study. As the name suggests, statistical significance is obtained when we carry out statistical tests in hypothesis testing. The statistical significance can therefore be proven in the results and discussion section, which may be restated in the conclusion, and is rarely found in a separated sub-chapter in research proposals. Here is an example of reporting the statistical significance in a correlational study:
“Hours spent studying and GPA were strongly positively correlated, r(123) = .61, p = .011. Hours spent playing video games and GPA were moderately negatively correlated, r(123) = .32, p = .041.”
Meanwhile, clinical significance means that the expected findings of our proposed study will be applicable for treating patients and improving quality of life. This is commonly found in health and medical research. Clinical significance is a method determining the effective treatment for patients, and is closely related to statistical significance where the research hypothesis is being tested. To determine the clinical significance, we need to refer to the effect size of the statistical calculations, like in the following example:
With a one-tailed alpha level of .05, the correlation between health-related anxiety and functional status in this sample of 72 subjects was statistically significant and reflected a large effect size, r(70) = -.78, p < .005. The hypothesis, therefore, was supported.