Tips and Tricks for Successful Application of Statistical Methods to Biological Data

  • Evelyn Schlenker
Part of the Methods in Molecular Biology book series (MIMB, volume 1366)


This chapter discusses experimental design and use of statistics to describe characteristics of data (descriptive statistics) and inferential statistics that test the hypothesis posed by the investigator. Inferential statistics, based on probability distributions, depend upon the type and distribution of the data. For data that are continuous, randomly and independently selected, as well as normally distributed more powerful parametric tests such as Student’s t test and analysis of variance (ANOVA) can be used. For non-normally distributed or skewed data, transformation of the data (using logarithms) may normalize the data allowing use of parametric tests. Alternatively, with skewed data nonparametric tests can be utilized, some of which rely on data that are ranked prior to statistical analysis.

Experimental designs and analyses need to balance between committing type 1 errors (false positives) and type 2 errors (false negatives). For a variety of clinical studies that determine risk or benefit, relative risk ratios (random clinical trials and cohort studies) or odds ratios (case–control studies) are utilized. Although both use 2 × 2 tables, their premise and calculations differ. Finally, special statistical methods are applied to microarray and proteomics data, since the large number of genes or proteins evaluated increase the likelihood of false discoveries. Additional studies in separate samples are used to verify microarray and proteomic data. Examples in this chapter and references are available to help continued investigation of experimental designs and appropriate data analysis.

Key words

Descriptive statistics Parametric tests Nonparametric tests Type 1 and type 2 errors Microarray studies 


  1. 1.
    Ellis PD (2010) The essential guide to effect sizes: statistical power, meta-analysis, and the interpretation of research results. Cambridge University Press, New York, p 187CrossRefGoogle Scholar
  2. 2.
    Ren J, Ding X, Funk GD, Greer JJ (2012) Anxiety-related mechanisms of respiratory dysfunction in a mouse model of Rett syndrome. J Neurosci 32(48):17230–17240CrossRefGoogle Scholar
  3. 3.
    Rossouw JE, Anderson GL, Prentice RL et al (2002) Risks and benefits of estrogen plus progestin in healthy postmenopausal women: principal results from the Women’s Health Initiative randomized controlled trial. JAMA 288(3):321–333CrossRefGoogle Scholar
  4. 4.
    Escher M, Scavia G, Morabito S et al (2014) A severe foodborne outbreak of diarrhoea linked to a canteen in Italy caused by enteroinvasive Escherichia coli, an uncommon agent. Epidemiol Infect 142(12):2559–2566CrossRefGoogle Scholar
  5. 5.
    Glantz SA (2012) Primer of biostatistics, 7th edn. McGraw-Hill Medical, New YorkGoogle Scholar
  6. 6.
    Tusher VG, Tibshirani R, Chu G (2001) Significance analysis of microarrays applied to the ionizing radiation response. Proc Natl Acad Sci U S A 98(9):5116–5121CrossRefGoogle Scholar
  7. 7.
    von der Heyde S, Sonntag J, Kaschek D et al (2014) RPPanalyzer toolbox: an improved R package for analysis of reverse phase protein array data. Biotechniques 57(3):125–135PubMedGoogle Scholar
  8. 8.
    Cui X, Churchill GA (2003) Statistical tests for differential expression in cDNA microarray experiments. Genome Biol 4(4):210CrossRefGoogle Scholar

Copyright information

© Springer Science+Business Media New York 2016

Authors and Affiliations

  1. 1.Division of Basic Biomedical Sciences, Sanford School of MedicineThe University of South DakotaVermillionUSA

Personalised recommendations