Abstract
Experimental stroke researchers take samples from populations (e.g., certain mouse strains) and make inferences about unknown parameters (e.g., infarct sizes, outcomes). They use statistics to describe their data, and they seek formal ways to decide whether their hypotheses are true (“Compound X is a neuroprotectant”). Unfortunately, experimental stroke research at present lacks statistical rigor in designing and analyzing its results, and this may have negative consequences for its predictiveness. This chapter aims at giving a general introduction into the do’s and don’ts of statistical analysis in experimental stroke research. In particular, we will discuss how to design an experimental series and calculate necessary sample sizes, how to describe data with graphics and numbers, and how to apply and interpret formal tests for statistical significance. A surprising conclusion may be that there are no formal ways of deciding whether a hypothesis is correct or not and that we should focus instead on biological (or clinical) significance as measured in the size of an effect and on the implications of this effect for the biological system or organism. “Good evidence” that a hypothesized effect is real comes from replication across multiple studies; it cannot be inferred from the result of a single statistical test!
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsReferences
Bederson JB, Pitts LH, Tsuji M, Nishimura MC, Davis RL, Bartkowski H (1986) Rat middle cerebral artery occlusion: evaluation of the model and development of a neurologic examination. Stroke 17:472–476
Buchan A, Pulsinelli WA (1990) Hypothermia but not the N-methyl-D-aspartate antagonist, MK-801, attenuates neuronal damage in gerbils subjected to transient global ischemia. J Neurosci 10:311–316
Hunt H. Boxplots in Excel. http://staff.unak.is/not/andy/StatisticsTFV0708/Resources/BoxplotsInExcel.pdf. 29 Dec 2015
Harlow LL, Mulaik SA, Steiger JH (eds) (1997) What if there were no significance tests? Lawrence Erlbaum Associates, London
O’Hagan A, Luce R (2003) A primer on Bayesian statistics in health economics and outcomes research. https://www.shef.ac.uk/polopoly_fs/1.80635!/file/primer.pdf. 29 Dec 2015
Sterne JAC, Smith GD (2001) Sifting the evidence – what’s wrong with significance tests? Br Med J 322:226–231
Ziliak ST, McCloskey DN (2008) The Cult of Statistical Significance: How the Standard Error Costs Us Jobs, Justice, and Lives. Univ of Michigan Press, Ann Arbor
Kirk RE (1996) Practical significance: a concept whose time has come. Edu Psychol Meas 56:746–759
Curran-Everett D, Benos DJ (2004) Guidelines for reporting statistics in journals published by the American Physiological Society. Am J Physiol 28(3):85–87
G*Power 3. http://www.gpower.hhu.de/. 29 Dec 2015
Dirnagl U (2006) Bench to bedside: the quest for quality in experimental stroke research. J Cereb Blood Flow Metab 26:1465–1478
Schmidt FL, Hunter JE (1997) Eight common but false objections to the discontinuation of significance testing in the analysis of research data. In: Harlow L, Mulaik SA, Steiger JH (eds) What if there were no significance tests? Lawrence Erlbaum Associates, London, pp 37–64
Mulaik SA, Raju NS, Harshman RA (1997) There is a time and a place for significance testing. In: Harlow L, Mulaik SA, Steiger JH (eds) What if there were no significance tests? Lawrence Erlbaum Associates, London, pp 66–115
Button KS, Ioannidis JP, Mokrysz C, Nosek BA, Flint J, Robinson ES, Munafò MR (2013) Power failure: why small sample size undermines the reliability of neuroscience. Nat Rev Neurosci 14:365–376
Krzywinski M, Altman N (2013) Points of significance: power and sample size. Nat Methods 10:1139–1140
Simonsohn U (2015) Small telescopes: detectability and the evaluation of replication results. Psychol Sci 26:559–569
Ioannidis JP (2005) Why most published research findings are false. PLoS Med 2(8):e124
Oakes M (1986) Statistical inference. Chichester: Wiley
Kimmelman J, Mogil JS, Dirnagl U (2014) Distinguishing between exploratory and confirmatory preclinical research will improve translation. PLoS Biol 12:e1001863
Llovera G, Hofmann K, Roth S, Salas-Pérdomo A, Ferrer-Ferrer M, Perego C, Zanier ER, Mamrak U, Rex A, Party H, Agin V, Fauchon C, Orset C, Haelewyn B, De Simoni MG, Dirnagl U, Grittner U, Planas AM, Plesnila N, Vivien D, Liesz A (2015) Results of a preclinical randomized controlled multicenter trial (pRCT): Anti-CD49d treatment for acute brain ischemia. Sci Transl Med 7:299ra121
Motulsky HJ (2015) Common misconceptions about data analysis and statistics. J Pharmacol Exp Ther 351:200–205
Festing MF, Nevalainen T (2014) The design and statistical analysis of animal experiments: introduction to this issue. ILAR J 55:379–382
Nuzzo R (2014) Scientific method: statistical errors. Nature 506(7487):150–152
Aban IB, George B (2015) Statistical considerations for preclinical studies. Exp Neurol 270:82–87
Dirnagl U. To infinity and beyond. http://dirnagl.com. 29 Dec 2015
Li X, Blizzard KK, Zeng Z, DeVries AC, Hurn PD, McCullough LD (2004) Chronic behavioral testing after focal ischemia in the mouse: functional recovery and the effects of gender. Exp Neurol 187:94–104
Plesnila N, Zinkel S, Le DA, Amin-Hanjani S, Wu Y, Qiu J, Chiarugi A, Thomas SS, Kohane DS, Korsmeyer SJ, Moskowitz MA (2001) BID mediates neuronal cell death after oxygen/glucose deprivation and focal cerebral ischemia. Proc Natl Acad Sci U S A 98:15318–15323
Emerson JD, Moses LE (1985) A note on the Wilcoxon-Mann-Whitney test for 2 x k ordered tables. Biometrics 41:303–309
Cohen J (1988) Statistical power analysis for the behavioral sciences, 2nd edn. Lawrence Erlbaum Associates, Mahwah, NJ
Simon S. Sample size for the Mann-Whitney U test. http://www.pmean.com/00/mann.html. 29 Dec 2015
Head ML, Holman L, Lanfear R, Kahn AT, Jennions MD (2015) The extent and consequences of p-hacking in science. PLoS Biol 13:e1002106
Colquhoun D (2014) An investigation of the false discovery rate and the misinterpretation of p-values. R Soc Open Sci 1:140216
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2016 Springer Science+Business Media New York
About this protocol
Cite this protocol
Dirnagl, U. (2016). Statistics in Experimental Stroke Research: From Sample Size Calculation to Data Description and Significance Testing. In: Dirnagl, U. (eds) Rodent Models of Stroke. Neuromethods, vol 120. Humana Press, New York, NY. https://doi.org/10.1007/978-1-4939-5620-3_19
Download citation
DOI: https://doi.org/10.1007/978-1-4939-5620-3_19
Published:
Publisher Name: Humana Press, New York, NY
Print ISBN: 978-1-4939-5618-0
Online ISBN: 978-1-4939-5620-3
eBook Packages: Springer Protocols