Sixteen S ‐squared over D ‐squared: A relation for crude sample size estimates
The DOI matches its Crossref record; 4 of the 4 references it cites were found in a registry or an index.
Abstract
I suggest for memorization an equation for calculating approximate sample size requirements intended only for a specific set of values (80 per cent power for a two‐tailed alpha = 0.05 test) which seems to occur often in biopharmaceutical research. After presenting the formula in terms of variance estimate s 2 and effect size d , I derive a few alternative forms and then discuss the accuracy of the approximation and other properties as well as examples of its use.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Citations
Cites
Statistical Methods for Rates and Proportions
Fleiss, J. L., Levin, B., & Paik, M. C. (2003) · Wiley Series in Probability and Statistics · doi:10.1002/0471445428 · Cited by 18,646
Statistical Methods for Rates and Proportions.
Everitt, B. S., & Fleiss, J. L. (1981) · Biometrics · doi:10.2307/2530193 · Cited by 8,990
Statistical Methods for the Analysis of Biomedical Data
Ziegel, E., & Woolson, R. F. (1989) · Technometrics · doi:10.2307/1268847 · Cited by 583
Statistical Methods for the Analysis of Biomedical Data.
Elton, R. A., & Woolson, R. F. (1988) · Journal of the Royal Statistical Society. Series A (Statistics in Society) · doi:10.2307/2983034 · Cited by 298
Research works printed but not linked: 1
- Snedecor G. W., 1980, Statistical Methods
Cited by
The role and interpretation of pilot studies in clinical research
Leon, A. C., Davis, L. L., & Kraemer, H. C. (2011) · Journal of Psychiatric Research · doi:10.1016/j.jpsychires.2010.10.008 · Cited by 1,917
“(N/group ≈ 16/d2; Lehr, 1992) The clinical interpretation of HAMD change of 1.2 to 3.0 would drive the choice among possible sample sizes in planning a study.”
BackgroundInfluentialExperimental design and analysis and their reporting: new guidance for publication in BJP
Curtis, M. J., Bond, R. A., Spina, D., Ahluwalia, A., Alexander, S. P. A., Giembycz, M. A., Gilchrist, A., Hoyer, D., Insel, P. A., Izzo, A. A., et al. (2015) · British Journal of Pharmacology · doi:10.1111/bph.12856 · Cited by 1,033
“Statistical power analysis to determine the minimum necessary group size is undertaken (Lehr, 1992) when the investigator knows the likely variability (defined for Gaussian distributed data as the variance) of the numerical values and the anticipated magnitude of the difference between groups.”
BackgroundGuidelines for designing and evaluating feasibility pilot studies
Teresi, J. A., Yu, X., Stewart, A. L., & Hays, R. D. (2022) · Medical Care · doi:10.1097/mlr.0000000000001664 · Cited by 734
Campbell, M. J., Julious, S. A., & Altman, D. G. (1995) · BMJ · doi:10.1136/bmj.311.7013.1145 · Cited by 476
Sample size determination for logistic regression revisited
Demidenko, E. (2007) · Statistics in Medicine · doi:10.1002/sim.2771 · Cited by 431
“For a popular choice of = 0.05 and P = 0.8, from (13) we assess the sample size as n = 8V/ 2, Lehr [15].”
BackgroundInfluentialTaylor, M. J., Freemantle, N., Geddes, J. R., & Bhagwagar, Z. (2006) · Archives of General Psychiatry · doi:10.1001/archpsyc.63.11.1217 · Cited by 406
Thanasas, C., Papadimitriou, G., Charalambidis, C., Paraskevopoulos, I., & Papanikolaou, A. (2011) · The American Journal of Sports Medicine · doi:10.1177/0363546511417113 · Cited by 351
Morrow, J. M., Sinclair, C. D. J., Fischmann, A., Machado, P. M., Reilly, M. M., Yousry, T. A., Thornton, J. S., & Hanna, M. G. (2016) · The Lancet Neurology · doi:10.1016/s1474-4422(15)00242-2 · Cited by 342
Lamotrigine reduces painful diabetic neuropathy: A randomized, controlled study
Eisenberg, E., Lurie, Y., Braker, C., Daoud, D., & Ishay, A. (2001) · Neurology · doi:10.1212/wnl.57.3.505 · Cited by 301
Wong, F. K. Y., Ng, A. Y. M., Lee, P. H., Lam, P.-T., Ng, J. S. C., Ng, N. H. Y., & Sham, M. M. K. (2016) · Heart · doi:10.1136/heartjnl-2015-308638 · Cited by 225
Haslam, C., Cruwys, T., Chang, M. X. L., Bentley, S. V., Haslam, S. A., Dingle, G. A., & Jetten, J. (2019) · Journal of Consulting and Clinical Psychology · doi:10.1037/ccp0000427 · Cited by 207
“…al. (2011) meta-analysis were lower: d = -0.367 (range= −4.81 to 0.12) for single group pre-post designs, d=-0.459 (range= -1.88 to 0.11) for non-randomised group GROUPS 4 HEALTH 9 that a minimum of 23 participants would need to be retained in each condition at follow-up for 80% power (Lehr, 1992).”
BackgroundInfluentialCan arterial spin labeling detect white matter perfusion signal?
van Osch, M. J. P., Teeuwisse, W. M., van Walderveen, M. A. A., Hendrikse, J., Kies, D. A., & van Buchem, M. A. (2009) · Magnetic Resonance in Medicine · doi:10.1002/mrm.22002 · Cited by 204
“8, approximation valid when the necessary number of timepoints is large) was determined (19):”
BackgroundMedical Statistics at a Glance
Ludvigsson, J. F. (2003) · Journal of Pediatric Gastroenterology and Nutrition · doi:10.1002/j.1536-4801.2003.tb08042.x · Cited by 197
Sample size calculations: should the emperor's clothes be off the peg or made to measure?
Norman, G., Monteiro, S., & Salama, S. (2012) · BMJ · doi:10.1136/bmj.e5278 · Cited by 187
Statistics in orthopaedic papers
Petrie, A. (2006) · The Journal of Bone and Joint Surgery. British volume · doi:10.1302/0301-620x.88b9.17896 · Cited by 167
Mourisse, J. M. J., Liesveld, J., Verhagen, A. F. T. M., van Rooij, G., van der Heide, S. M., Schuurbiers-Siebers, O. C. J., & van der Heijden, E. H. F. M. (2013) · Anesthesiology · doi:10.1097/aln.0b013e3182834f2d · Cited by 154
Eyck, R. P. T., Tews, M. C., & Ballester, J. M. (2009) · Annals of Emergency Medicine · doi:10.1016/j.annemergmed.2009.03.025 · Cited by 146
Ismail, N. H., Manaf, Z. A., & Azizan, N. Z. (2012) · BMC Dermatology · doi:10.1186/1471-5945-12-13 · Cited by 139
“Based on the formula [14], it was calculated that 35 subjects were required to provide 80% power at a significant level of 5%.”
MethodBerg, S., Tullberg, T., Branth, B., Olerud, C., & Tropp, H. (2009) · European Spine Journal · doi:10.1007/s00586-009-1047-0 · Cited by 133
“The Lehr formula [16] was used to provide crude estimates of sample size.”
MethodEpilepsy Gene Therapy Using an Engineered Potassium Channel
Snowball, A., Chabrol, E., Wykes, R. C., Shekh-Ahmad, T., Cornford, J. H., Lieb, A., Hughes, M. P., Massaro, G., Rahim, A. A., Hashemi, K. S., et al. (2019) · The Journal of Neuroscience · doi:10.1523/jneurosci.1143-18.2019 · Cited by 127
“Given a mean baseline weekly seizure frequency of 5 or above, a modification of Lehr’s formula (Lehr, 1992) for the Poisson distribution suggested that seven to eight animals per group would be sufficient to detect a reduction in seizure frequency from 10 to 6 per week.”
BackgroundMethodComparison of mannitol and hypertonic saline in the treatment of severe brain injuries
Sakellaridis, N., Pavlou, E., Karatzas, S., Chroni, D., Vlachos, K., Chatzopoulos, K., Dimopoulou, E., Kelesis, C., & Karaouli, V. (2010) · Journal of neurosurgery · doi:10.3171/2010.5.jns091685 · Cited by 126
Ekstrand, K. R., Poulsen, J. E., Hede, B., Twetman, S., Qvist, V., & Ellwood, R. P. (2013) · Caries Research · doi:10.1159/000348581 · Cited by 89
“Using Lehr’s formula [Lehr, 1992]: 16/(standardized difference) 2 where the standardized difference in this study is 2/4 = 0.5 gives 64 residents in each of the two groups.”
InfluentialEfficacy of cumulative high-frequency rTMS on freezing of gait in Parkinson’s disease
Kim, M. S., Chang, W. H., Cho, J. W., Youn, J., Kim, Y. K., Kim, S. W., & Kim, Y.-H. (2015) · Restorative Neurology and Neuroscience · doi:10.3233/rnn-140489 · Cited by 109
“Using Lehr’s formula (16/(δ/σ)) (Lehr, 1992) and a 20% dropout rate, we calculated that more than 19 subjects would be needed.”
MethodAssobhi, J. E. H. (2011) · Journal of Orthopaedics and Traumatology · doi:10.1007/s10195-011-0158-7 · Cited by 108
“Lehr’s formula was used for the sample size calculation [15].”
MethodEisenberg, E., Kleiser, A., Dortort, A., Haim, T., & Yarnitsky, D. (1998) · European Journal of Pain · doi:10.1016/s1090-3801(98)90030-1 · Cited by 102
“Using the Lehr formula (Lehr, 1992), the calculated sample size required to detect this difference with a significance level of 0.05 and with 80% power was found to be 10 patients in each group.”
MethodInfluentialPandit, J. J., Bree, S., Dillon, P., Elcock, D., McLaren, I. D., & Crider, B. A. (2000) · Anesthesia & Analgesia · doi:10.1097/00000539-200010000-00004 · Cited by 101
“8, 17 patients in each group were needed (15,16).”
BackgroundOpen and laparoscopic appendectomy are equally safe and acceptable in children
Oka, T., Kurkchubasche, A. G., Bussey, J. G., Wesselhoeft, C., Tracy, T. F., & Luks, F. I. (2003) · Surgical Endoscopy · doi:10.1007/s00464-003-8140-y · Cited by 97
“Sample size was determined according to Lehr’s formula [10]; it provided sufficient power (I–b = 0.”
MethodAnderson, D. J., Seib, C. A., Tjondronegoro, D., Turner, J., Monterosso, L., McGuire, A., Porter‐Steele, J., Song, W., Yates, P. M., King, N. A., et al. (2017) · BMC Cancer · doi:10.1186/s12885-017-3088-9 · Cited by 94
“Habitual dietary intake (including greater detail of alcohol consumption) was monitored through the Food Frequency Questionnaire (FFQ) [27, 28].”
Chang, W. H., Park, C.-H., Kim, D. Y., Shin, Y., Ko, M.-H., Lee, A., Jang, S. Y., & Kim, Y. (2016) · BMC Neurology · doi:10.1186/s12883-016-0553-z · Cited by 81
“Using the Lehr’s formula (16/(δ/σ)) [19] and a 15 % drop-out rate, it was calculated that 70 subjects in all would be needed.”
MethodThe effect of neuromuscular blockade on the efficiency of mask ventilation of the lungs*
Goodwin, M., Pandit, J. J., Hames, K., Popat, M. T., & Yentis, S. M. (2003) · Anaesthesia · doi:10.1046/j.1365-2044.2003.02788_3.x · Cited by 77
Pandit, J. J., Maclachlan, K., Dravid, R. M., & Popat, M. T. (2002) · Anaesthesia · doi:10.1046/j.0003-2409.2001.02401.x · Cited by 73
Validation of MRC Centre MRI calf muscle fat fraction protocol as an outcome measure in CMT1A
Morrow, J. M., Evans, M. R. B., Grider, T., Sinclair, C. D. J., Thedens, D. R., Shah, S., Yousry, T. A., Hanna, M. G., Nopoulos, P., Thornton, J. S., et al. (2018) · Neurology · doi:10.1212/wnl.0000000000006214 · Cited by 69
“For remote-site quality-control qualification, 3 healthy volunteers were scanned with 2 undergoing repeat scanning on a different day to assess test-retest reliability, referenced to similar measurements performed in London.9,10 Statistical analysis was performed using SPSS Statistics 20.0 (IBM Corp., Armonk, NY).”
MethodInfluentialStrauss, S. Y., Conner, J. K., & Lehtilä, K. (2001) · The American Naturalist · doi:10.1086/323116 · Cited by 71
Burdı́o, F., Güemes, A., Burdio, J. M., Navarro, A., Sousa, R., Castiella, T., Cruz, I., Burzaco, O., & Lozano, R. (2003) · Radiology · doi:10.1148/radiol.2292020978 · Cited by 67
Effect of static stretching of quadriceps and hamstring muscles on knee joint position sense
Larsen, R. F., Lund, H., Christensen, R., Røgind, H., Danneskiold‐Samsøe, B., & Bliddal, H. (2004) · British Journal of Sports Medicine · doi:10.1136/bjsm.2003.011056 · Cited by 65
Sang-Yeun, W. O. N., Kim, H., Kim, M., & Kim, K. (2017) · Journal of Applied Oral Science · doi:10.1590/1678-7757-2016-0462 · Cited by 73
Marfin, A. G., Pandit, J. J., Hames, K., Popat, M. T., & Yentis, S. M. (2003) · Anaesthesia · doi:10.1046/j.1365-2044.2003.03289.x · Cited by 57
Mak, C., Whittingham, K., Cunnington, R., & Boyd, R. N. (2018) · Developmental Medicine & Child Neurology · doi:10.1111/dmcn.13923 · Cited by 72
“80; a sample size of 32 child–parent dyads was needed.(20) To account for attrition (10% was assumed), a total of 36 dyads were required.”
BackgroundEffectively integrating experiments into conservation practice
Ockendon, N., Amano, T., Cadotte, M. W., Downey, H., Hancock, M. H., Thornton, A., Tinsley‐Marshall, P., & Sutherland, W. J. (2021) · Ecological Solutions and Evidence · doi:10.1002/2688-8319.12069 · Cited by 65
“4.1.1 Deciding on a realistic number of replicates The number of replicates needed to detect a specified effect size can be calculated using a power analysis (Lehr, 1992; Crawley, 2015).”
MethodInfluentialImproving the Sensitivity of in Vitro Skin Penetration Experiments
Kasting, G. B., Filloon, T. G., Francis, W. R., & Meredith, M. P. (1994) · Pharmaceutical Research · doi:10.1023/a:1018915416930 · Cited by 54
Hudson, L. E., Fasken, M. B., McDermott, C. D., McBride, S. M., Kuiper, E. G., Guiliano, D. B., Corbett, A. H., & Lamb, T. J. (2014) · PLoS ONE · doi:10.1371/journal.pone.0112660 · Cited by 53
“8416)(2)/(d/s)(2) where d is the smallest meaningful difference in means and s is the standard deviation of the observations in each group, assuming a power of 80% and a significance of 5% [34].”
BackgroundSample size calculations for educational interventions: principles and methods
McConnell, M., Monteiro, S., & Bryson, G. L. (2019) · Canadian Journal of Anesthesia/Journal canadien d anesthésie · doi:10.1007/s12630-019-01405-9 · Cited by 53
Franceschini, M., Mazzoleni, S., Goffredo, M., Pournajaf, S., Galafate, D., Criscuolo, S., Agosti, M., & Posteraro, F. (2019) · Journal of Bodywork and Movement Therapies · doi:10.1016/j.jbmt.2019.03.016 · Cited by 73
Secchi, D., & Seri, R. (2016) · Computational and Mathematical Organization Theory · doi:10.1007/s10588-016-9218-0 · Cited by 67
Carlin, J., & Doyle, L. (2002) · Journal of Paediatrics and Child Health · doi:10.1046/j.1440-1754.2002.00855.x · Cited by 51
The importance of metabolic rate and the folly of body surface area calculations
Gibson, S., & Numa, A. H. (2003) · Anaesthesia · doi:10.1046/j.1365-2044.2003.02788_1.x · Cited by 53
Eyck, R. P. T., Tews, M. C., Ballester, J. M., & Hamilton, G. C. (2010) · Simulation in Healthcare The Journal of the Society for Simulation in Healthcare · doi:10.1097/sih.0b013e3181cca544 · Cited by 46
Danha, R. F., Thompson, J., Popat, M. T., & Pandit, J. J. (2005) · Anaesthesia · doi:10.1111/j.1365-2044.2004.04045.x · Cited by 43
Jain, R., & Xu, W. (2021) · Information Sciences · doi:10.1016/j.ins.2021.06.096 · Cited by 48
Lee, S. C., Rha, D., & Chang, W. H. (2011) · Journal of Back and Musculoskeletal Rehabilitation · doi:10.3233/bmr-2011-0272 · Cited by 42
“formula (16/ (δ/σ)) [19] and 20% of drop-out rate, it”
BackgroundBerg, S., Tropp, H., & Leivseth, G. (2011) · The Spine Journal · doi:10.1016/j.spinee.2011.08.434 · Cited by 41
“The Lehr formula was used to provide crude estimates of sample size [24].”
In-line image projection accelerates task performance in laparoscopic appendectomy
Erfanian, K., Luks, F. I., Kurkchubasche, A. G., Wesselhoeft, C., & Tracy, T. F. (2003) · Journal of Pediatric Surgery · doi:10.1016/s0022-3468(03)00192-1 · Cited by 41
Medrik-Goldberg, T., Lifschitz, D., Pud, D., ADLER, R., & Eisenberg, E. (1999) · Regional Anesthesia & Pain Medicine · doi:10.1016/s1098-7339(99)90045-7 · Cited by 47
SANDERCOCK, G. R. H., Bromley, P. D., & Brodie, D. A. (2004) · Clinical Physiology and Functional Imaging · doi:10.1111/j.1475-097x.2004.00584.x · Cited by 44
“The sample sizes in Table 4 are calculated using the formula provided by Lehr (1992).”
MethodNorris, J. M., Moules, N. J., Pelletier, G., & Culos-Reed, S. N. (2010) · Journal of Pediatric Oncology Nursing · doi:10.1177/1043454209358411 · Cited by 44
“…18 participants per group was necessary to detect a large effect and clinically important difference in mean PedsQL™ HRQL scores of 11.94 (self-report) and 14.28 (parent proxy-report; Varni, Limbers, & Burwinkle, 2007), with power set to 80% and a 2-sided significance level of .05 (Lehr, 1992).”
BackgroundInfluentialColchicine in Cardiac Surgery: The COCS Randomized Clinical Trial
Shvartz, V. A., Le, T. G., Тайсумович, Э. С., Sokolskaya, M. A., Ispiryan, A., Shvartz, E. N., Nudel, D., Araslanova, N., Petrosyan, A. D., Donakanyan, S., et al. (2022) · Journal of Cardiovascular Development and Disease · doi:10.3390/jcdd9100363 · Cited by 45
“Lehr [34], taking into account the data on the incidence of the studied event (POAF) in our sample of patients, the estimated number of observations should have been at least 223 with a given statistical power of 80% and α=0.”
BackgroundStatistical methods in epidemiology. II: A commonsense approach to sample size estimation
Rigby, A. S., & Vail, A. (1998) · Disability and Rehabilitation · doi:10.3109/09638289809166102 · Cited by 38
Economic Rationality under Cognitive Load
Drichoutis, A. C., & Nayga, R. M. (2020) · The Economic Journal · doi:10.1093/ej/ueaa052 · Cited by 42
Nakagawa, S., Lagisz, M., Yang, Y., & Drobniak, S. M. (2024) · PLoS Biology · doi:10.1371/journal.pbio.3002423 · Cited by 43
Implications of clinical trial design on sample size requirements
Leon, A. C. (2007) · Schizophrenia Bulletin · doi:10.1093/schbul/sbn035 · Cited by 35
Shen, A., Bernabé, E., & Sabbah, W. (2019) · PLoS ONE · doi:10.1371/journal.pone.0216227 · Cited by 36
3. Sampling, study size, and power
Cole, T. J. (1997) · Oxford University Press eBooks · doi:10.1093/acprof:oso/9780192627391.003.0003 · Cited by 32
Lee, J. I., Park, J., Koo, J., Son, M.-N., Hwang, J. H., Lee, J. Y., & Chang, W. H. (2022) · Disability and Rehabilitation · doi:10.1080/09638288.2022.2074154 · Cited by 37
Kim, Y. W., Shin, J. C., Yoon, J.-G., Kim, Y.-K., & Lee, S. C. (2013) · Chinese Medical Journal · doi:10.3760/cma.j.issn.0366-6999.20131129 · Cited by 31
“2 calculated from results of a recent article using the Lehr’s formula (16/(2×δ/σ)) and a 20% drop-out rate.(10,16,20) According to these calculations, more than 57 subjects were needed.”
MethodLaurent, D., Riek, J., Sinclair, C. D. J., Houston, P., Roubenoff, R., Papanicolaou, D. A., Nagy, A., Pieper, S., Yousry, T. A., Hanna, M. G., et al. (2022) · Neurology · doi:10.1212/wnl.0000000000200776 · Cited by 33
“Irrespective of these considerations, our data would support the use of TMV, fat volume (IMAT or T2%-IMAT), MTR, and muscle inflammation (T2 relaxation time), with absolute group mean SRM values ranging from 0.65 to 1.50, as the most responsive measures for a primary end point in clinical trials, allowing a significan…”
BackgroundInfluentialEstudos clínicos de não-inferioridade: fundamentos e controvérsias
Pinto, V. F. (2010) · Jornal Vascular Brasileiro · doi:10.1590/s1677-54492010000300009 · Cited by 48
The veil of experimental currency units in second price auctions
Drichoutis, A. C., Lusk, J. L., & Nayga, R. M. (2015) · Journal of the Economic Science Association · doi:10.1007/s40881-015-0014-2 · Cited by 35
“The formula then collapses to n 1⁄4 16 D(2) (with D 1⁄4 l0 l1 r ), which is known as Lehr’s (1992) equation [see also Chapter 2 in van Belle (2008)].”
BackgroundO’Daly, B., Ridgway, P. F., Keenan, N., Sweeney, K., Brophy, D. P., Hill, A. D. K., Evoy, D., O’Higgins, N. J., & McDermott, E. W. M. (2009) · PubMed Central · Cited by 29
Statistics for clinicians: 7: Sample size
Carlin, J. B., & Doyle, L. W. (2002) · Journal of Paediatrics and Child Health · Cited by 28
Voon, P. T., Ng, T. K. W., Lee, V. K. M., & Nesaretnam, K. (2015) · European Journal of Clinical Nutrition · doi:10.1038/ejcn.2015.26 · Cited by 26
Griffin, X. L., Achten, J., Parsons, N., Boardman, F., Griffiths, F. E., & Costa, M. L. (2012) · Bone and Joint Research · doi:10.1302/2046-3758.111.2000127 · Cited by 28
Comparing Two Imaging Methods for Follow-Up of Lung Cancer Treatment: A Randomized Pilot Study
Gambazzi, F., Frey, L. D., Bruehlmeier, M., Janthur, W.-D., Graber, S. M., Heuberger, J., Springer, O., Zweifel, R., Boerner, B., Tini, G. M., et al. (2018) · The Annals of Thoracic Surgery · doi:10.1016/j.athoracsur.2018.08.015 · Cited by 26
Enhancing clinical trial design of interventions for posttraumatic stress disorder
Leon, A. C., & Davis, L. L. (2009) · Journal of Traumatic Stress · doi:10.1002/jts.20466 · Cited by 26
“Alternatively, a quick approximation for estimating the required sample size per group (N) for 80% power with a t test is calculated as follows (adapting Lehr, 1992): N = 16/d2.”
MethodWitkamp, F. E., van Zuylen, L., van der Maas, P. J., van Dijk, H., van der Rijt, C. C. D., & van der Heide, A. (2013) · BMC Health Services Research · doi:10.1186/1472-6963-13-115 · Cited by 25
“5) = 100) [46].”
Asthma in an Urban Population in Portugal: A prevalence study
de Sousa, J. C., Santo, M. E., Colaço, T., Lobo, F. A., & Yaphe, J. (2011) · BMC Public Health · doi:10.1186/1471-2458-11-347 · Cited by 26
“Lehr R: Sixteen S-squared over D-squared: a relation for crude sample size estimates.”
MethodAutomated and distributed statistical analysis of economic agent-based models
Vandin, A., Giachini, D., Lamperti, F., & Chiaromonte, F. (2022) · Journal of Economic Dynamics and Control · doi:10.1016/j.jedc.2022.104458 · Cited by 42
HDSI: High dimensional selection with interactions algorithm on feature selection and testing
Jain, R., & Xu, W. (2021) · PLoS ONE · doi:10.1371/journal.pone.0246159 · Cited by 28
“Since it is a one-sample case, the sample size of the coefficient values for a feature could be estimated from following Lehr’s equation, L = 8/ Δ 2 [27].”
BackgroundBurdı́o, F., Morlana, P. T., Quesada, R., BERJANO, E. J., Navarro, A., Poves, I., & Grande, L. (2011) · American Journal of Roentgenology · doi:10.2214/ajr.10.5202 · Cited by 25
“The sample size of the study was previously calculated in each group by the formula proposed by Lehr [19]: n = 16 / SMD2, where SMD is the standardized mean difference between the two means being compared.”
MethodWong, A. W. K., Hon, E. K. L., & Zee, B. C.-Y. (2008) · International Journal of Dermatology · doi:10.1111/j.1365-4632.2008.03414.x · Cited by 26
Rahardi, F., & Dartanto, T. (2021) · Heliyon · doi:10.1016/j.heliyon.2021.e06681 · Cited by 39
Saraswathy, T., Nalliah, S., Manaf, R. A., Ramasamy, S., Jalina, K., Shahar, H. K., & Amin-Nordin, S. (2021) · BMC Medical Education · doi:10.1186/s12909-021-02907-1 · Cited by 29
Heart rate variability reproducibility during exercise
McNarry, M. A., & Lewis, M. J. (2012) · Physiological Measurement · doi:10.1088/0967-3334/33/7/1123 · Cited by 31
“As the reliability of measurements influences the sample size required for an experiment, we estimated the sample size required to detect a relevant change in the mean of the HRV parameters after a treatment (test–retest design) (Lehr 1992).”
MethodReal-world evidence on the economic implications of CGRP-mAbs as preventive treatment of migraine
Siersbæk, N., Kilsdal, L., Jervelund, C., Antić, S., & Bendtsen, L. (2023) · BMC Neurology · doi:10.1186/s12883-023-03302-7 · Cited by 26
Visual analogue scales for interstitial lung disease: a prospective validation study
Yates, H., Adamali, H. I., Maskell, N. A., Barratt, S. L., & Sharp, C. (2018) · QJM · doi:10.1093/qjmed/hcy102 · Cited by 28
All that glisters… How to assess the ‘value’ of a scientific paper
Pandit, J. J., & Yentis, S. M. (2005) · Anaesthesia · doi:10.1111/j.1365-2044.2005.04151.x · Cited by 23
Rohani, M., Mozaffar, H., Mesri, M., Shokri, M., Delaney, D., & Karimy, M. (2022) · Eastern Mediterranean Health Journal · doi:10.26719/emhj.22.064 · Cited by 22
Chen, P., Shih, Y., Chu, H.-C., Chang, W., Hsieh, T., & Chao, Y. (2008) · The American Journal of Gastroenterology · doi:10.1111/j.1572-0241.2008.01812.x · Cited by 21
“ing Lehr’s formula (15) for unpaired t-testd and by assuming a standard deviation (SD) of 6.”
BackgroundQuantum Leak: Timing Side-Channel Attacks on Cloud-Based Quantum Services
Lu, C., Telang, E., Aysu, A., & Basu, K. (2025) · ACM Great Lakes Symposium on VLSI (GLSVLSI) · doi:10.1145/3716368.3735264 · Cited by 46
Cai, X.-Z., Yan, S., Wu, H., He, R.-X., Dai, X.-S., Chen, H., Yan, R., & Zhao, X. (2007) · Antimicrobial Agents and Chemotherapy · doi:10.1128/aac.01465-06 · Cited by 20
“Based upon Lehr’s formula (12), the optimal sample size for each group in the PK and PD studies was determined to be eight.”
BackgroundWaterstraat, G., Teleńczuk, B., Burghoff, M., Fedele, T., Scheer, H.-J., & Curio, G. (2012) · Clinical Neurophysiology · doi:10.1016/j.clinph.2012.03.013 · Cited by 22
“Power values and the required sample size to reach a desired statistical power can now be calculated with standard techniques such as presented in Lehr (1992): 1 b 1⁄4 cdf 0:5 logðSNRS þ 1Þ ffiffiffiffiffiffi kN p ppf 1 a”
Pang, N. T. P., Tio, V. C. S., Bhupendar Singh, A. S., Tseu, M. W. L., Shoesmith, W. D., Abd Rahim, M. A., & Mohd Kassim, M. A. (2022) · Trends in Psychiatry and Psychotherapy · doi:10.47626/2237-6089-2020-0172 · Cited by 17
Li, Z., Fei, Y., Li, Z., Wei, T., Zhu, J., & Su, A. (2021) · Endocrine · doi:10.1007/s12020-021-02921-9 · Cited by 21
McAlinden, C., Moore, J. E., McGilligan, V., & Moore, T. (2010) · Graefe s Archive for Clinical and Experimental Ophthalmology · doi:10.1007/s00417-010-1476-9 · Cited by 18
“used on the same set of patients, the number of subjects was determined to be 20 [10, 11].”
Hames, K., Pandit, J. J., Marfin, A. G., Popat, M. T., & Yentis, S. M. (2003) · Anaesthesia · doi:10.1046/j.1365-2044.2003.03288.x · Cited by 17
Kurebayashi, Y., Mori, K., & Otaki, J. (2021) · Perspectives In Psychiatric Care · doi:10.1111/ppc.12896 · Cited by 22
Goodall, E. A., Moore, J. E., & Moore, T. (2009) · Eye · doi:10.1038/eye.2009.105 · Cited by 17
Moses, A. M., Golos, D. B., & Bennett, C. M. (2015) · Early Childhood Education Journal · doi:10.1007/s10643-015-0690-9 · Cited by 20
“According to calculations (32/effect size2) provided by Lehr (1992), a sample size between approximately 50 and 89 participants is adequate for detecting an effect size between 0.6 and 0.8 (i.e., ‘‘large’’ effect size).”
InfluentialQuesada, R., Poves, I., BERJANO, E. J., Vilaplana, C., Andaluz, A., Moll, X., Dorcaratto, D., Grande, L., & Burdı́o, F. (2016) · International Journal of Hyperthermia · doi:10.1080/02656736.2016.1231938 · Cited by 16
“The sample size of the study in each group was calculated by means of the formula proposed by Lehr [22]: N1⁄4 16/ SMD(2), where SMD is the standardised mean difference between the two means being compared.”
MethodLamb, T. J., Graham, A. L., & Petrie, A. (2008) · Immunity · doi:10.1016/j.immuni.2008.02.003 · Cited by 16
“In addition, Lehr (Lehr, 1992) devised simple formulae (provided in Box S3) specifically for a 5% significance level and an 80% or 90% power.”
MethodНиколаев, Н. А., Skirdenko, Y. P., Balabanova, A. A., Gorbenko, A. V., Andreev, K. A., Fedorin, M. M., Livzan, M. A., Владимирович, Ч. Е., & Михайлович, У. Г. (2022) · Rational Pharmacotherapy in Cardiology · doi:10.20996/1819-6446-2021-12-12 · Cited by 15
“Lehr at a confidence level of 95% [14].”
Background
Metadata
- Authors
- Lehr, R.
- Corresponding author
- Lehr, Robert
- Venue
- Statistics in Medicine
- Publisher
- Wiley
- Published
- 1992-01
- Volume
- 11
- Issue
- 8
- Pages
- 1099-1102
- ISSN
- 0277-6715 (ISSN-L)
- 1097-0258
- OpenAlex
- W2029233919
- Cited by
- 253
- References
- 4
- Citations by year
- 2026: 14 · 2025: 14 · 2024: 22 · 2023: 15 · 2022: 11 · 2021: 15 · 2020: 9 · 2019: 10 · 2018: 9 · 2017: 6 · 2016: 6 · 2015: 16 · 2014: 6 · 2013: 8 · 2012: 12
- FWCI
- 1.00
- Type
- journal article
- Language
- en
- Open access
- closed
- Locations
- Statistics in Medicine (publishedVersion)
- Topics
- Physical Sciences › Mathematics › Statistics and Probability › Statistical Methods in Clinical Trials
- Physical Sciences › Mathematics › Statistics and Probability › Statistical Methods in Epidemiology
- Social Sciences › Decision Sciences › Statistics, Probability and Uncertainty › Meta-analysis and systematic reviews
- Keywords
- sample size determination, effect size, variance estimation, statistical power, biopharmaceutical research, two-tailed tests, approximation accuracy
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.