A Review of Fundamentals of Statistical Concepts in Clinical Trials

Kyungmee Choi; Jongtae Lee; Sangil Jeon; Taegon Hong; Jeongki Paek; Seunghoon Han; Dong-Seok Yim

doi:10.0000/jkscpt.2012.20.2.109

Journal List > J Korean Soc Clin Pharmacol Ther > v.20(2) > 1055102

Go to TopGo to Top Go to BottomGo to Bottom

TOOLS

Choi, Lee, Jeon, Hong, Paek, Han, and Yim: A Review of Fundamentals of Statistical Concepts in Clinical Trials

Review Article

Journal of Korean Society for Clinical Pharmacology and Therapeutics

Journal of Korean Society for Clinical Pharmacology and Therapeutics 2012; 20(2): 109-124.

Published online: 31 December 2012

DOI: https://doi.org/10.0000/jkscpt.2012.20.2.109

A Review of Fundamentals of Statistical Concepts in Clinical Trials

Kyungmee Choi¹, Jongtae Lee², Sangil Jeon², Taegon Hong², Jeongki Paek², Seunghoon Han², Dong-Seok Yim²

¹Divison of Mathematics, College of Science and Technology, Hongik University at Sejong, Jochiwon, Chungnam, Republic of Korea.

²Department of Pharmacology, College of Medicine, the Catholic University of Korea and Department of Clinical Pharmacology and Therapeutics, Seoul St. Mary's Hospital, Seoul, Republic of Korea.

Corresponding author (kmchoi@hongik.ac.kr)

Received 14 June 2012 Revised 2 November 2012 Accepted 6 November 2012

Abstract

Statistical analysts engaged in typical clinical trials often have to confront a tight schedule to finish massive statistical analyses specified in a Standard Operation Procedure (SOP). Thus, statisticians or not, most analysts would want to reuse or slightly modify existing programs. Since even a slight misapplication of statistical methods or techniques can easily drive a whole conclusion to a wrong direction, analysts should arm themselves with well organized statistical concepts in advance. This paper will review basic statistical concepts related to typical clinical trials.

The number of variables and their measurement scales determine an appropriate method. Since most of the explanatory variables in clinical trials are designed beforehand, the main statistics we review for clinical trials include univariate data analysis, design of experiments, and categorical data analysis. Especially, if the response variable is binary or observations collected from a subject are correlated, the analysts should pay special attention to selecting an appropriate method. McNemar's test and multiple McNemar's test are respectively recommended for comparisons of proportions between correlated two samples or proportions among correlated multi-samples.

Keywords: Measurement scale, Two-sample T-test, Crossover study, Chi-square test, Multiple McNemar's test

Figures and Tables

Table 1

Two-sample location tests

^*One-sample T-test with degree of freedom (n-1). ^†Two-sample T-test with degree of freedom (n₁+n₂-2) or min (n₁-1, n₂-1). ^‡Levene's Test for equality of variances.

Table 2

Analysis of variance for crossover studies with A corporation's drug

^*Degree of Freedom. ^†Sum of Squares. ^‡Mean Square=Sum of Squares/Degree of Freedom. ^§F-stat=(MS Sequence)/(MS Sequence×subject).^∥F-stat=(MS Form)/(MS Error). ^¶F-stat=(MS Period)/(MS Error).

Table 3

Goodness-of-fit test for categorical variables in B corporation's drug data

^*Fisher's exact test. ^†Pearson's chi-square test.

References

1. Chen HL, Yang A. Common Pitfalls in SAS Statistical Analysis Macros in a Mass Production Environment. NESUG 2007; Statsitics and Data Analysis. last visited on 8 May 2012. http://www.nesug.org/proceedings/nesug07/sa/sa05.pdf [Online].

2. Montgomery DC. Design and Analysis of Experiments. 2012. 8th ed. John Wiley & Sons.

3. Meyers LS, Gamst G, Guarino AJ. Applied multivariate research: Design and interpretation. 2006. Sage publications.

4. McClave JT, Sincich T. Statistics. 2009. 11th ed. Pearson Prentice Hall.

5. Jamieson S. Likert scales: How to (ab)use them. Med Educ. 2004. 38:1217–1218.

6. University of Northern Iowa (UNI). SPSS techniques Series: Statistics on Likert Scale Surveys. last visited on 31 May 2012. http://www.uni.edu/its/support/article/604 [Online].

7. Allen IE, Seaman CA. Likert Scales and Data Analyses. Qual Prog. 2007. 40:64–65.

8. Mood AM, Graybill FA, Boes DC. Introduction to the theory of Statistics. 1974. 3rd ed. McGraw-Hill Higher Education.

9. Rosner B. Fundamentals of Biostatistics. 2000. 7th ed. Cengage Learning;666–673.

10. Simmons B, Bland MJ, Wojciechowski B. AP Statistics. 2010. Kaplan, Inc..

11. Sternstein M. AP Statistics. 2010. 5th ed. Barron's Educational Series Inc..

12. Patterson S, Jones B. Bioequivalence and Statistics in Clinical Pharmacology. 2005. Chapman and Hall/CRC;39–77.

13. SAS Institute Inc. SAS/STAT User's Guide. 1990.

14. Pinheiro JC, Bates DM. Mixed-Effects Models in S and S-PLUS. 2004. Springer.

15. Park SH. Modern Design of Experiment. 2006. Minyoungsa.

16. Feng WW, Ding D. SAS@ application in 2×2 crossover clinical trial. last visited on 8 May 2012. http://www.lexjansen.com/pharmasug/2004/statisticspharmacokinetics/sp02.pdf [Online].

17. Simpson PM, Hamer RM, Lensing S. Crossover studies off your list. last visited on 8 May 2012. http://www2.sas.com/proceedings/sugi24/Posters/p221-24.pdf [Online].

18. Chinchilli VM, Esinhart JD. Design and analysis of intra-subject variability in cross-over experiments. Stat Med. 1996. 15(15):1619–1634.

19. Brunelle R. Review various methods to perform the analysis of a 2 treatment, 2 period crossover study. last visited on 29 May 2012. http://www.math.iupui.edu/~indyasa/crosover.pdf [Online].

20. Dallal GE. The computer-aided analysis of crossover studies. last visited on 29 May 2012. http://www.jerrydallal.com/LHSP/crossovr.htm [Online].

21. Nagelkerke NJD, Hart AAM, Oosting J. The two period binary response cross-over trial. Biomed J. 1986. 28(7):863–869.

22. Consonni G, Rocca LL. Tests Based on Intrinsic Priors for the Equality of Two Correlated Proportions. J Acoust Soc Am. 2008. 103(483):1260–1269.

23. Westfall PH, Troendle JF, Pennello G. Multiple McNemar test. Biometrics. 2010. 66(4):1185–1191.

24. Choi K. Common misapplications of independent sample analyses in SAS to correlated adverse events in crossover designs. 2012. Submitted to Quantitative Bio-science.

TOOLS

Similar articles