Chapter 1 Introduction

What does a statistical paper look like? As with all scientific papers, it should have some commonly expected structures which include components such as title, abstract, keywords, introduction, methods, results, discussion, acknowledgements, references, appendix, and supplement. Due to the specificity of the statistical discipline and application areas, however, statistical papers could look quite different one from another.

There are different types of statistical papers. A theory paper would look similar to a paper in mathematics, with statement of the problem, presentation of some theorems, and technical proofs. Such papers are not covered here. We focus on two types of statistical papers: application papers and method papers. Application papers focus on a specific application problem in a certain domain where the research discoveries depend on applications of existing or novel statistical methods. Method papers, on the other hand, aim to provide a general methodological solution to a class of applied problems. Often, methods paper have a theoretical component, for example, the establishment of the asymptotic properties of a new estimator. An applied paper in statistics could be a method paper in the domain of the problem it solves.

An author should always keep the target audience in mind when writing. There are many statistical journals on the wide spectrum from applied to theoretical papers. Each one has its own aims and scope, with different target readerships. Writings such as customary statistical reports that are not intended for journal publications also have target readerships. Regardless of the audience, any scientific paper should be convincing and concise. You need to show the readers that your work is important, valid, and useful. You don’t want to waste the time of any readers.

1.1 Applied papers

An applied paper has a widely accepted structure:

  • Introduction
  • Data description
  • Methods
  • Results
  • Discussion

An applied paper can be applying existing statistical methods to solve an applied problem. See, for example, Price and Yan (2022); D. J. Caplan et al. (2019).

When sensitivity analysis is desired for the applications, one can have a section on simulation studies. See, for example, J. Jiao et al. (2022); Li et al. (2021).

Some applied papers can involve novel methodology development that is motivated by an applied problem. In such cases, simulation studies become necessary, where you validate your methods with simulated data so you can check your estimator with the truth. Such check is not feasible when analyzing real data. See, for example, Jieying Jiao, Hu, and Yan (2021); Hu et al. (2021).

1.2 Methods papers

A methods paper focuses on a novel method that is applicable to a general class of problems arising in different domains. A commonly seen structure is:

  • Introduction
  • Methods (e.g., estimation, hypothesis tests, diagnosis)
  • Properties
  • Simulations
  • Illustrations (with real applications)
  • Discussion/Conclusions.

The simulations section is often needed for methods papers. Any method has assumptions. Any reasonably good method should work as expected when the assumptions hold. It would be even better if it remains working when some of the assumptions are violated. Simulation studies can be designed to check whether the proposed estimators are unbiased and more efficient than competing estimators; whether the proposed tests retains their sizes and are more powerful than competing tests.

Here are some examples: Li et al. (2023); Lau and Yan (2022).

1.3 Scientific Writing

Many resources on scientific writing are available. For example, Gopen and Swan (1990) was selected by its publisher, American Scientist, as one of its 36 “Classic Articles” from the first 100 years of its publishing history. Popular books are Oshima and Hogue (2000), Gopen (2004), Hairston and Keene (2003), and Lebrun and Lebrun (2021).

References

Caplan, D J, Y Li, W Wang, S Kang, L Marchini, HJ Cowen, and J Yan. 2019. “Dental Restoration Longevity Among Geriatric and Special Needs Patients.” JDR Clinical & Translational Research 4 (1): 41–48. https://doi.org/10.1177/2380084418799083.
Gopen, George D. 2004. Expectations: Teaching Writing from the Reader’s Perspective. Pearson.
Gopen, George D, and Judith A Swan. 1990. “The Science of Scientific Writing.” American Scientist 78 (6): 550–58.
Hairston, Maxine, and Michael L Keene. 2003. Successful Writing. 5th ed. W. W. Norton & Company.
Hu, Chaoran, Mark Elbroch, Thomas Meyer, Vladimir Pozdnyakov, and Jun Yan. 2021. “Moving-Resting Process with Measurement Error in Animal Movement Modeling.” Methods in Ecology and Evolution 12 (11): 2221–33. https://doi.org/10.1111/2041-210X.13694.
Jiao, Jieying, Guanyu Hu, and Jun Yan. 2021. “A Bayesian Marked Spatial Point Processes Model for Basketball Shot Chart.” Journal of Quantitative Analysis in Sports 17 (2): 77–90. https://doi.org/10.1515/jqas-2019-0106.
Jiao, J., Z. Tang, M. Yue, P. Zhang, and J. Yan. 2022. “Cyberattack-Resilient Load Forecasting with Adaptive Robust Regression.” International Journal of Forecasting 38 (3): 910–19. https://doi.org/10.1016/j.ijforecast.2021.06.009.
Lau, Abby Y. Z., and Jun Yan. 2022. “Bias Analysis of Generalized Estimating Equations Under Measurement Error and Practical Bias Correction.” Stat 11 (1): e418. https://doi.org/10.1002/sta4.418.
Lebrun, Jean-Luc, and Justin Lebrun. 2021. Scientific Writing 3.0: A Reader and Writer’s Guide. World Scientific.
Li, Yan, Kun Chen, Jun Yan, and Xuebin Zhang. 2021. “Uncertainty in Optimal Fingerprinting Is Underestimated.” Environmental Research Letters 16 (8): 084043. https://doi.org/10.1088/1748-9326/ac14ee.
———. 2023. “Regularized Fingerprinting in Detection and Attribution of Climate Change with Weight Matrix Optimizing the Efficiency in Scaling Factor Estimation.” Annals of Applied Statistics 17 (1): 225–39. https://doi.org/10.1214/22-AOAS1624.
Oshima, Alex, and Ann Hogue. 2000. Writing Academic English. Longman.
Price, Michael, and Jun Yan. 2022. “The Effects of the NBA COVID Bubble on the NBA Playoffs: A Case Study for Home-Court Advantage.” American Journal of Undergraduate Research 18(4): 3–15. https://doi.org/10.33697/ajur.2022.051.