The t-test is a mainstay statistical test that allows researchers to use the observed averages (arithmetic means) of data samples to draw evidence-supported conclusions about the corresponding averages in the populations they represent. This article serves as an introduction to this common and useful technique for clinicians with a limited statistical background, who seek to deepen their understanding of the t-test, its reasoning, and its implications in clinical research. We describe the three basic forms of the t-test, its applications and alternatives, and some related concepts while avoiding technical concepts and jargon as much as possible.
Student. The probable error of a mean. Biometrika. 1908;6(1):1-25. doi:10.2307/2331554.
2.
CherukuSRFoxAAHeraviH, et al.Thoracic interfascial plane blocks and outcomes after minithoracotomy for valve surgery. Semin CardioThorac Vasc Anesth. 2023;27(1):8-15. doi:10.1177/10892532221136386.
3.
AbboudPPetersenTREhsanianRKertaiMDAbramsBHansonR. Advances in medicine: the convergence of data, experience, and story. Semin Cardiothorac Vasc Anesth Published online October. 2025;29(4):237-239. doi:10.1177/10892532251391796
4.
KrauseMNguyenAO’BrienOKhocheSSchmidtU. A randomized pilot study assessing if SEDLine monitoring during induction of surgical patients is associated with reduced dosage of administered induction agents. Semin CardioThorac Vasc Anesth. 2022;26(4):260-265. doi:10.1177/10892532221130660.
5.
KianiFJorfiSSoltaniFGhanbariSRezaeeRMohammadiMJ. Exposure to anesthetic gases in the operating rooms and assessment of non-carcinogenic risk among health care workers. Toxicol Rep. 2023;11:1-8. doi:10.1016/j.toxrep.2023.06.007.
6.
RajkumarSJhaAKParidaSThangaswamyCRPanneerselvamSPrasadSKS. Effect of acute vasodilator testing using oxygen in pulmonary hypertension due to left heart disease. Semin CardioThorac Vasc Anesth. 2024;28(1):8-17. doi:10.1177/10892532241227082.
7.
ColemanSRCiosTJRielaSRobertsSM. The effects of propofol on left ventricular global longitudinal strain. Semin CardioThorac Vasc Anesth. 2021;25(3):185-190. doi:10.1177/1089253221991372.
DivineGWNortonHJBarónAEJuarez-ColungaE. The wilcoxon–mann–whitney procedure fails as a test of medians. Am Statistician. 2018;72(3):278-286. doi:10.1080/00031305.2017.1305291.
10.
WestRM. Best practice in statistics: use the welch t-test when testing the difference between two groups. Ann Clin Biochem. 2021;58(4):267-269. doi:10.1177/0004563221992088.
11.
RaschDKubingerKDModerK. The two-sample t test: pre-testing its assumptions does not pay off. Stat Papers. 2011;52(1):219-231. doi:10.1007/s00362-009-0224-x.
12.
MoserBKStevensGR. Homogeneity of variance in the two-sample means test. Am Statistician. 1992;46(1):19-21. doi:10.1080/00031305.1992.10475839.
13.
ZhouYZhuYWongWK. Statistical tests for homogeneity of variance for clinical trials and recommendations. Contemp Clin Trials Commun. 2023;33:101119. doi:10.1016/j.conctc.2023.101119.
14.
RochonJGondanMKieserM. To test or not to test: preliminary assessment of normality when comparing two independent samples. BMC Med Res Methodol. 2012;12(1):81. doi:10.1186/1471-2288-12-81.
15.
KniefUForstmeierW. Violating the normality assumption May be the lesser of two evils. Behav Res Methods. 2021;53(6):2576-2590. doi:10.3758/s13428-021-01587-5.
