Dear Researchers
My two hypotheses were insignificant. I didn't report the confidence interval due to insignificant results. Moderating variable didn't moderate the association between x and y. the editor rejected my article on this basis, moderating results didn't report. Do I mention the CI=[ -----, -----] ? Please guide.
Dear Ali Mudassar
Basically, It just means, that your data can't show whether there is a difference or not. It may be one case or the other. To say it in logical terms: If A is true then –> B is true.
Best Regards
Dr. Fatemeh Khozaei
first, if your hypothesis is not significant, you can add a theoretical basis, is it appropriate or not? if it is not suitable, it must be explained why it is not in accordance with the theory
second, you can increase the level of significance if needed, so that it can change the decision of the hypothesis.
hope it helps
It is very unfortunate when articles get rejected only because of statistical non-significance. Non-significant findings, in principle, can be just as valuable as "significant" findings. That is, knowing that a hypothesized effect may not exist is also a potentially important finding.
I think that it is useful to report confidence intervals for both significant and non-significant effects/coefficients. This is relevant, for example, for meta analyses that may later include these effects in a larger summary "study of studies," aggregating effect sizes from different studies on the same topic.
Non-significance may simply be due to a small sample size. The effect may be statistically significant in a larger sample. Therefore, unstandardized and standardized effect sizes as well as confidence intervals should be reported for all effects--both significant and non-significant.
By using free power analysis programs such as G*Power, you can find out whether your sample size was too small to demonstrate the hypothesized effect as significant. It also allows you to estimate the optimal sample size for future studies.
Reporting about moderation, you should reflect, in your manuscript, that things are not always as easy as they appear or are thought to be, and that our understanding of the world must be subjected to certain conditions—not only statistical significance. To that end, you could go through the guidelines rendered by Hayes (2018, pp. 522–523) for dealing with three scenarios depicting incongruous moderation-analysis findings. Here is the full citation.
Hayes, A. F. (2018). Introduction to mediation, moderation, and conditional process analysis: A regression-based approach (2nd ed.). Guilford Press. https://www.guilford.com/books/Introduction-to-Mediation-Moderation-and-Conditional-Process-Analysis/Andrew-Hayes/9781462534654
Good luck,
- Badges
- Science topic
- Similar topics
- Computer Science
- Research Topics