Statistics is an inexact science as it is based on probabilities rather than certainties. However, the language used to present data and statistics in your thesis or research paper needs to be accurate to avoid misunderstandings when your work is read by others. If the written descriptions of your data and statistics are not clear and accurate, experienced researchers may lose confidence in your entire study and dismiss your results, no matter how compelling they may be.
The presentation of data in research and effective communication of statistical results requires writers to be very careful in their word choices. You must be confident that you understand the analysis you performed and the meaning of the results to really know how to present the data and statistics in your research paper effectively. Here are some terms and concepts that are often misused and may be confusing to early career researchers.
Average
Averages, the measures of the central tendency of a dataset, can be calculated in several different ways. The word “average” in non-scholarly writings typically refers to the arithmetic mean. However, the median and mode are two other frequently used measures. In your research paper, it is critical to state exactly what measure you are using. Therefore, don’t report an average but a mean, median, or mode.
Percentages
Percentages are commonly used in presentations of data in research. They can indicate concentrations, probabilities, or comparisons, and they are frequently used to report changes in values. For example, the annual crime rate increased by 25%. However, unless you have a basis for this number, it’s difficult to judge the meaningfulness of this increase1. Did the number of crimes increase from 4 incidents to 5 or from 4,000 incidents to 5,000? Be sure to include enough information for the reader to understand the context.
In addition, when used for comparison, make sure your comparison is complete. For instance, if the temperature was 17% higher in 2022, be sure to include that it was 17% higher than the temperature in 2017.
Descriptive vs. inferential statistics
Descriptive statistics deal with populations, while inferential statistics deal with samples. A population is a group of objects or measurements that includes all possible instances, and a sample is a subset of that population. For example, you measure the mass of all the 1.1 kg jars of peanut butter at your favorite grocery store and report the mean and standard deviation. These are descriptive statistics for this population of peanut butter jars. However, if you then say that this is the mean of all such jars of peanut butter produced, you are engaging in inferential statistics because you now have measured only a sample of jars. You are inferring a characteristic of a population based on a sample. Inferential statistics are usually reported with a margin of error or confidence interval, such as 1.1 ± .02 kg.
Hypotheses
A hypothesis is a testable statement about the relationship between two or more groups or variables that forms the basis of the scientific method. The appropriate language around the topic of hypotheses and hypothesis testing can be confusing for even seasoned researchers.
The alternative hypothesis is generally the researcher’s prediction for the study, and the null hypothesis is the negation of the alternative hypothesis. The aim of the study is to find evidence to reject the null hypothesis, which supports the truth of the alternative hypothesis.
When writing up the results of your hypothesis test, it is important to understand exactly what the results mean. Remember, hypothesis testing can never “prove” anything – it merely provides evidence for either rejecting or not rejecting the null hypothesis. Also, be careful that you don’t overgeneralize the meaning of the results. Just because you find evidence that the null hypothesis can be rejected in this case does not mean the same is true under all conditions.
Tips for effectively presenting statistics in academic writing
Presenting your data and statistical results can be very challenging. For researchers without extensive experience or statistical training, writing this part of the study report can be especially daunting. Here are some things to keep in mind when presenting your data and statistical results1.
- If you don’t completely understand a statistical procedure, do not attempt to write it up without guidance from an expert. This is the most important thing you can do.
- Keep your audience in mind. When you present your data and statistical results, think about how familiar your readers may be with the analysis and include the amount of detail needed for them to be comfortable2.
- Use tables and graphics to illustrate your results more clearly and make your writing more understandable.
We hope the points above help answer the question of how to present data and statistics in your research paper correctly. All the best!
References
- The University of North Carolina at Chapel Hill Writing Center. Statistics. https://writingcenter.unc.edu/tips-and-tools/statistics/ [Accessed October 10, 2022]
- Purdue University Online Writing Lab. Writing with statistics. https://owl.purdue.edu/owl/research_and_citation/using_research/writing_with_statistics/index.html [Accessed October 10, 2022]
Paperpal is a comprehensive AI writing toolkit that helps students and researchers achieve 2x the writing in half the time. It leverages 21+ years of STM experience and insights from millions of research articles to provide in-depth academic writing, language editing, and submission readiness support to help you write better, faster.
Get accurate academic translations, rewriting support, grammar checks, vocabulary suggestions, and generative AI assistance that delivers human precision at machine speed. Try for free or upgrade to Paperpal Prime starting at US$19 a month to access premium features, including consistency, plagiarism, and 30+ submission readiness checks to help you succeed.
Experience the future of academic writing – Sign up to Paperpal and start writing for free!