Small Sample Inference for Fixed Effects from Restricted Maximum Likelihood
The DOI matches its Crossref record; 23 of the 23 references it cites were found in a registry or an index.
Abstract
Restricted maximum likelihood (REML) is now well established as a method for estimating the parameters of the general Gaussian linear model with a structured covariance matrix, in particular for mixed linear models. Conventionally, estimates of precision and inference for fixed effects are based on their asymptotic distribution, which is known to be inadequate for some small-sample problems. In this paper, we present a scaled Wald statistic, together with an F approximation to its sampling distribution, that is shown to perform well in a range of small sample settings. The statistic uses an adjusted estimator of the covariance matrix that has reduced small sample bias. This approach has the advantage that it reproduces both the statistics and F distributions in those settings where the latter is exact, namely for Hotelling T2 type statistics and for analysis of variance F-ratios. The performance of the modified statistics is assessed through simulation studies of four different REML analyses and the methods are illustrated using three examples.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
In the citing paper
“Accurate model parameter estimations were ensured by use of the residual maximum likelihood approach with the Kenward and Roger, 1997 approximation of degrees of freedom.”
From Longitudinal association between social media use and psychological distress among adolescents (2020) · cites this paper as Kenward and Roger, 1997
In the citing paper
“Not only does the data in the motivating example have different flowering days for each genotype (see for example Fig. 2), but the proposed methodology also accounts for the different strata in the Wald test by approximating the denominator degrees of freedom (Kenward and Roger, 1997).”
From Incorporating environmental covariates to explore genotype × environment × management (G × E × M) interactions: A one-stage predictive model (2023) · cites this paper as Kenward and Roger, 1997
Citations
Cites
Maximum Likelihood from Incomplete Data Via the EM Algorithm
Dempster, A. P., Laird, N. M., & Rubin, D. B. (1977) · Journal of the Royal Statistical Society Series B: Statistical Methodology · doi:10.1111/j.2517-6161.1977.tb01600.x · Cited by 50,444
Random-Effects Models for Longitudinal Data
Laird, N. M., & Ware, J. H. (1982) · Biometrics · doi:10.2307/2529876 · Cited by 8,923
Recovery of inter-block information when block sizes are unequal
PATTERSON, H. D., & THOMPSON, R. (1971) · Biometrika · doi:10.1093/biomet/58.3.545 · Cited by 4,058
Maximum Likelihood Approaches to Variance Component Estimation and to Related Problems
Harville, D. A. (1977) · Journal of the American Statistical Association · doi:10.1080/01621459.1977.10480998 · Cited by 2,667 · cited 1×
“Restricted (or residual) maximum likelihood (REML) has become well established for the estimation of the parameters of Z (Patterson and Thompson, 1971; Harville, 1977; Thompson, 1980; Robinson, 1991) and the corresponding estimator of 3, 3 say, has a generalized least squares form that uses the REML estimate of Z.”
BackgroundThat BLUP is a Good Thing: The Estimation of Random Effects
Robinson, G. K. (1991) · Statistical Science · doi:10.1214/ss/1177011926 · Cited by 1,686
Gilmour, A. R., Thompson, R., & Cullis, B. R. (1995) · Biometrics · doi:10.2307/2533274 · Cited by 915
15 Design and Analysis of Cross-Over Trials
Kenward, M. G., & Jones, B. (2007) · Handbook of Statistics · doi:10.1016/s0169-7161(07)27015-4 · Cited by 871
Self-citationPrinciples of Multivariate Analysis
Ling, R. F. (1990) · Technometrics · doi:10.1080/00401706.1990.10484645 · Cited by 812
Satterthwaite, F. E. (1941) · Psychometrika · doi:10.1007/bf02288586 · Cited by 809
Approximations for Standard Errors of Estimators of Fixed and Random Effects in Mixed Linear Models
Kackar, R. N., & Harville, D. A. (1984) · Journal of the American Statistical Association · doi:10.1080/01621459.1984.10477102 · Cited by 445
Cited by
Items 901–1,000 of 1,051
The impact of chronic environmental stressors on growing pigs, Sus scrofa (Part 2): social behaviour
Parker, M. O., O’Connor, E., McLeman, M. A., Demmers, T. G. M., Lowe, J. C., Owen, R. C., Davey, E. L., Wathes, C. M., & Abeyesinghe, S. M. (2010) · animal · doi:10.1017/s1751731110001084 · Cited by 44
“Degrees of freedom (d.f.) were calculated using the Kenward–Roger method, which is appropriate for unbalanced data with multiple random effects (Kenward and Roger, 1997).”
MethodSubacute ruminal acidosis and total mixed ration preference in lactating dairy cows
Maulfair, D. D., McIntyre, K. K., & Heinrichs, A. J. (2013) · Journal of Dairy Science · doi:10.3168/jds.2013-6771 · Cited by 46
Zebeli, Q., Tafaj, M., Weber, I., Steingaß, H., & Drochner, W. (2007) · Animal Feed Science and Technology · doi:10.1016/j.anifeedsci.2007.04.002 · Cited by 45
“the method of Kenward and Roger (1997). Significance was declared at P≤0.”
MethodClimate-induced range overlap among closely related species
Krosby, M., Wilsey, C. B., McGuire, J. L., Duggan, J., Nogeire, T. M., Heinrichs, J. A., Tewksbury, J. J., & Lawler, J. J. (2015) · Nature Climate Change · doi:10.1038/nclimate2699 · Cited by 51
Vepsäläinen, H., Mikkilä, V., Erkkola, M., Broyles, S. T., Chaput, J.-P., Hu, G., Kuriyan, R., Kurpad, A. V., Lambert, E. V., Maher, C. A., et al. (2015) · International Journal of Obesity Supplements · doi:10.1038/ijosup.2015.22 · Cited by 53
Hannam, K. D., Kehila, D., Millard, P., Midwood, A. J., Neilsen, D., Neilsen, G., Forge, T. A., Nichol, C., & Jones, M. D. (2016) · Geoderma · doi:10.1016/j.geoderma.2015.12.015 · Cited by 44
Cowan, J. S., Inglis, D. A., & Miles, C. A. (2013) · HortTechnology · doi:10.21273/horttech.23.6.849 · Cited by 38
Conducting Three-Level Longitudinal Analyses
Peugh, J., & Heck, R. H. (2016) · The Journal of Early Adolescence · doi:10.1177/0272431616642329 · Cited by 56
“The Kenward–Roger procedure has been shown to better maintain Type-1 errors across a number of multilevel dataset conditions (see Peugh, 2014, for additional details).”
MethodBrownell, M. T., Kiely, M. T., Haager, D., Boardman, A., Corbett, N., Algina, J. J., Dingle, M., & Urbach, J. (2016) · Exceptional Children · doi:10.1177/0014402916671517 · Cited by 57
“Kenward-Roger degrees of freedom (Kenward & Roger, 1997) were used for tests of fixed effect.”
MethodThompson, A. L., Thorp, K. R., Conley, M. M., El-Shikha, D. M., French, A. N., Andrade-Sánchez, P., & Pauli, D. (2019) · Remote Sensing · doi:10.3390/rs11060700 · Cited by 44
“Outliers were identified using Studentized deleted residuals with degrees of freedom being calculated using the Kenward and Rogers approximation [32].”
Decadal nitrogen addition alters chemical composition of soil organic matter in a boreal forest
Hasegawa, S., Marshall, J. D., Sparrman, T., & Näsholm, T. (2021) · Geoderma · doi:10.1016/j.geoderma.2020.114906 · Cited by 50
“The response variables in the linear-mixed effects models were transformed (inverse or log e ) to ensure homogeneity of variances and normality of errors prior to the analysis where necessary (Crawley, 2012; Fox and Weisberg, 2011).”
MethodBarnes, S. A., Mallinckrodt, C. H., Lindborg, S. R., & Carter, M. K. (2008) · Pharmaceutical Statistics · doi:10.1002/pst.310 · Cited by 44
“Denominator degrees of freedom were estimated using the Kenward–Roger approximation [24].”
MethodSeeling, K., Lebzien, P., Dänicke, S., Spilke, J., Südekum, K., & Flachowsky, G. (2005) · Journal of Animal Physiology and Animal Nutrition · doi:10.1111/j.1439-0396.2005.00570.x · Cited by 44
Forest fragmentation relaxes natural nest predation in an Afromontane forest
Spanhove, T., Lehouck, V., Boets, P., & Lens, L. (2009) · Animal Conservation · doi:10.1111/j.1469-1795.2009.00249.x · Cited by 45
“Denominator degrees of freedom in models with complex variance structure were computed following Kenward & Roger (1997).”
MethodKnetter, S., Bearson, S. M. D., Huang, T.-H., Kurkiewicz, D., Schroyen, M., Nettleton, D. S., Berman, D., Cohen, V. J., Lunney, J. K., Ramer‐Tait, A. E., et al. (2014) · Innate Immunity · doi:10.1177/1753425914525812 · Cited by 44
Heterosis and Inbreeding Depression in Two Soybean Single Crosses
Burton, J. W., & Brownie, C. (2006) · Crop Science · doi:10.2135/cropsci2006.03.0156 · Cited by 54
“The Kenward option (Kenward and Roger, 1997) was used to compute degrees of freedom.”
MethodTemporal and genomic analysis of additive genetic variance in breeding programmes
Lara, L. A. D. C., Pocrnić, I., Oliveira, T. D. P., Gaynor, R. C., & Gorjanc, G. (2021) · Heredity · doi:10.1038/s41437-021-00485-y · Cited by 46
“There are also frequentist approaches that account for uncertainty of estimating variance components (e.g. Kenward and Roger, 1997).”
BackgroundOtto-Dobos, L. D., Grant, C. V., Lahoud, A. A., Wilcox, O. R., Strehle, L. D., Loman, B. R., Adarkwah Yiadom, S., Seng, M. M., Halloy, N. R., Russart, K. L. G., et al. (2024) · Brain, Behavior, and Immunity · doi:10.1016/j.bbi.2024.05.039 · Cited by 48
From a Somatotopic to a Spatiotopic Frame of Reference for the Localization of Nociceptive Stimuli
De Paepe, A. L., Crombez, G., & Legrain, V. (2015) · PLOS ONE · doi:10.1371/journal.pone.0137120 · Cited by 43
Andersen, L. L., & Zebis, M. K. (2014) · International Journal of Rheumatology · doi:10.1155/2014/761363 · Cited by 53
“The estimation method was restricted maximum likelihood (REML) with degrees of freedom based on the Kenward-Roger approximation [30].”
MethodEpistasis causes outbreeding depression in eucalypt hybrids
Silva, J. C. E., Potts, B. M., & Tilyard, P. (2011) · Tree Genetics & Genomes · doi:10.1007/s11295-011-0437-8 · Cited by 50
“For this and the other Wald F-tests (see below) carried out in this study, the computation of the denominator degrees of freedom was based on the approximation proposed by Kenward and Roger (1997).”
MethodPea–oat intercrops to sustain lodging resistance and yield formation in northern European conditions
Kontturi, M., Laine, A., Niskanen, M., Hurme, T., Hyövelä, M., & Peltonen‐Sainio, P. (2011) · Acta Agriculturae Scandinavica Section B - Soil & Plant Science · doi:10.1080/09064710.2010.536780 · Cited by 43
“REML was used as an estimation method and degrees of freedom were calculated according to the Kenward–Roger method for all the models described (Kenward & Roger, 1997 ).”
MethodRäty, M., Ketoja, E., Pitkänen, T. P., Ahola, V., Kananen, K., & Peippo, J. (2011) · Cryobiology · doi:10.1016/j.cryobiol.2011.09.134 · Cited by 44
Detecting the Emergence of Chronic Pain in Sickle Cell Disease
Hollins, M., Stonerock, G. L., Kisaalita, N. R., Jones, S., Orringer, E. P., & Gil, K. M. (2012) · Journal of Pain and Symptom Management · doi:10.1016/j.jpainsymman.2011.06.020 · Cited by 46
Plasticity in behavioural responses and resistance to temperature stress in Musca domestica
Kjærsgaard, A., Blanckenhorn, W. U., Pertoldi, C., Loeschcke, V., Kaufmann, C., Hald, B., Pagès, N., & Bahrndorff, S. (2014) · Animal Behaviour · doi:10.1016/j.anbehav.2014.11.003 · Cited by 43
Developmental family processes and interparental conflict: Patterns of microlevel influences.
Schermerhorn, A. C., Chow, S.-M., & Cummings, E. M. (2010) · Developmental Psychology · doi:10.1037/a0019662 · Cited by 56
“…denominator degrees of freedom for assessing statistical significance of the fixed effects parameters were adjusted using the Kenward-Roger option (Kenward & Roger, 1997; 1Effect size measures for mixed effects models are still an active area of research and there is currently no clear consensus…”
Coombs, C. E. O., Holman, B. W. B., Collins, D., Friend, M. A., & Hopkins, D. L. (2017) · Meat Science · doi:10.1016/j.meatsci.2017.07.017 · Cited by 43
“…and random effects were examined separately in asreml (Butler et al., 2009) in R (R Core Team, 2015), with a Wald-type test with Kenward-Roger adjustment (Kenward & Roger, 1997) and likelihood ratio comparisons used to examine significance of temperature-related and spline components, respectively.”
MethodPauli, D., White, J. W., Andrade-Sánchez, P., Conley, M. M., Heun, J. T., Thorp, K. R., French, A. N., Hunsaker, D. J., Carmo‐Silva, E., Wang, G., et al. (2017) · Frontiers in Plant Science · doi:10.3389/fpls.2017.01405 · Cited by 46
“Sequential tests 347 of fixed effects were conducted with degrees of freedom being calculated with the Kenward and 348 Rogers approximation (Kenward and Roger, 1997) in ASReml-R version 3.”
MethodInfluentialMendoza, S. M., Boyd, R. D., Ferket, P. R., & van Heugten, E. (2017) · Journal of Animal Science · doi:10.2527/jas2017.1905 · Cited by 47
Thiesse, L., Rudzik, F., Spiegel, K., Leproult, R., Pieren, R., Wunderli, J. M., Foraster, M., Héritier, H., Eze, I. C., Meyer, M., et al. (2018) · Environment International · doi:10.1016/j.envint.2018.05.036 · Cited by 53
Pino, F., Mitchell, L. K., Jones, C., & Heinrichs, A. J. (2018) · Journal of Applied Animal Research · doi:10.1080/09712119.2018.1498788 · Cited by 51
SEWAYBRICKER, L. E., Schur, E. A., Melhorn, S. J., de Campos, B. M., Askren, M. K., Nogueira, G. A. S., Zambon, M. P., Antônio, M. Â. R. D. G. M., Cendes, F., Velloso, L. A., et al. (2018) · Pediatric Obesity · doi:10.1111/ijpo.12486 · Cited by 45
“TX, USA) using adjustment for small samples based on Kenward and Roger's method.(24) Statistical significance was determined at P < 0.”
MethodMultilevel Models for Communication Sciences and Disorders
Harel, D., & McAllister, T. (2019) · Journal of Speech Language and Hearing Research · doi:10.1044/2018_jslhr-s-18-0075 · Cited by 48
Thiesse, L., Rudzik, F., Kraemer, J. F., Spiegel, K., Leproult, R., Wessel, N., Pieren, R., Héritier, H., Eze, I. C., Foraster, M., et al. (2019) · Environmental Research · doi:10.1016/j.envres.2019.109086 · Cited by 49
Schaller, M. S., Chen, M., Colas, R. A., Sorrentino, T. A., Lazar, A., Grenon, S. M., Dalli, J., & Conte, M. S. (2020) · Journal of the American Heart Association · doi:10.1161/jaha.120.016113 · Cited by 48
“Kenward-Roger denominator degrees of freedom were used to make small sample inference.”
Milosavljević, I., Morgan, D. J., Massie, R. E., & Hoddle, M. S. (2021) · Biological Control · doi:10.1016/j.biocontrol.2021.104627 · Cited by 50
Differences in virulence of Phytophthora capsici isolates from a worldwide collection on host fruits
Granke, L. L., Quesada-Ocampo, L. M., & Hausbeck, M. K. (2011) · European Journal of Plant Pathology · doi:10.1007/s10658-011-9873-4 · Cited by 43
“Due to unequal and sometimes small sample sizes in the various categories, the KENWARDROGER option was specified in the model to calculate appropriate error degrees of freedom (Kenward and Roger 1997).”
MethodEasdale, M. H., & Aguiar, M. R. (2012) · Journal of Arid Environments · doi:10.1016/j.jaridenv.2012.03.002 · Cited by 43
Silva, J. C. E., Hardner, C. M., Tilyard, P., Pires, A. M., & Potts, B. M. (2010) · Annals of Forest Science · doi:10.1051/forest/2010018 · Cited by 44
“Pairwise differences of LSM were then tested using a t-test, and applying the Kenward and Roger (1997) approximation for computing the degrees of freedom associated with the test statistic.”
MethodLow-dose dietary chlorophyll inhibits multi-organ carcinogenesis in the rainbow trout
Simonich, M. T., McQuistan, T. J., Jubert, C., Pereira, C. B., Hendricks, J. D., Schimerlik, M. I., Zhu, B., Dashwood, R. H., Williams, D. E., & Bailey, G. (2007) · Food and Chemical Toxicology · doi:10.1016/j.fct.2007.10.034 · Cited by 43
“The model was fit using the Mixed procedure in SAS version 9.1 with the Kenward-Roger adjustment to account for estimation of multiple variance components (Kenward and Roger, 1997).”
MethodInfluentialOestenstad, R. K., Kimbrough, L. J., & Beasley, T. M. (2007) · Journal of Occupational and Environmental Hygiene · doi:10.1080/15459620701709619 · Cited by 45
“Because there were no group factors (i.e., gender; respirator brand) in these separate models, Kenward and Roger’s(15) adjustments to the dfs were not deemed necessary, and therefore, the default between-within dfs were used.”
MethodInfluentialPiepho, H. (2005) · Theoretical and Applied Genetics · doi:10.1007/s00122-004-1872-9 · Cited by 44
Durán, L., Roseth, C. J., Hoffman, P., & Robertshaw, M. B. (2013) · Bilingual Research Journal · doi:10.1080/15235882.2012.735213 · Cited by 59
“All analyses also employed the Kenward and Roger (1997) method for degrees of freedom and the significance level, α = .05.”
MethodMedina, J., Pineda, J. E. M., Castañeda‐Moya, E., & Rivera‐Monroy, V. H. (2021) · Frontiers in Marine Science · doi:10.3389/fmars.2020.598132 · Cited by 48
“The Kenward-Roger procedure was used to adjust the degrees of freedom of the F-test statistics when the design was unbalanced or when an unequal variance model was significant (Kenward and Roger, 1997; SAS Institute, Cary, North Carolina, United States).”
MethodRanson, M. K., Sinha, T., Chatterjee, M., Gandhi, F., Jayswal, R., Patel, F., Morris, S. S., & MILLS, A. J. (2007) · BMJ · doi:10.1136/bmj.39192.719583.ae · Cited by 52
“where TIME is a dummy variable coded 0=baseline, 1=postintervention. This equation is a simplified representation, as three indicator variables rather than just one represented the different intervention groups (in each case contrasted with the standard scheme group), and three interactions with time captured the net…”
MethodPenn, D. L., Uzenoff, S. R., Perkins, D., Mueser, K. T., Hamer, R., Waldheter, E., Saade, S., & Cook, L. (2011) · Schizophrenia Research · doi:10.1016/j.schres.2010.08.006 · Cited by 42
O’Connor, E., Parker, M. O., Davey, E. L., Grist, H., Owen, R. C., Szladovits, B., Demmers, T. G. M., Wathes, C. M., & Abeyesinghe, S. M. (2011) · British Poultry Science · doi:10.1080/00071668.2011.639342 · Cited by 42
Audet, K. N., & Mare, L. L. (2010) · International Journal of Behavioral Development · doi:10.1177/0165025410373313 · Cited by 55
“Degrees of freedom were calculated in SAS using the Kenward Roger method (see Kenward & Roger, 1997).”
MethodGenetic Analysis of 16 NMR‐Lipoprotein Fractions in Humans, the GOLDN Study
Kraja, A. T., Borecki, I. B., Tsai, M. Y., Ordovas, J. M., Hopkins, P. N., Lai, C., Frazier‐Wood, A. C., Straka, R. J., Hixson, J. E., Province, M. A., et al. (2013) · Lipids · doi:10.1007/s11745-012-3740-8 · Cited by 42
“Because of unequal variances the Kenward–Roger approximation for degrees of freedom for the reference distribution was used by defining the option ddfm=KR in the SAS MIXED procedure [20].”
MethodUsing the linear mixed model to analyze nonnormal data distributions in longitudinal designs
Arnau, J., Bono, R., Blanca, M. J., & Bendayan, R. (2012) · Behavior Research Methods · doi:10.3758/s13428-012-0196-y · Cited by 45
“One way of controlling this bias is to apply the procedure developed by Kenward and Roger (1997; henceforth, the KR method) to correct the degrees of freedom. Studies by Kowalchuk, Keselman, Algina, and Wolfinger (2004) and Vallejo and Ato (2006) showed that with an adequate covariance structure, the KR method is able…”
MethodSelonen, V., Sulkava, P. O., Sulkava, R., Sulkava, S., & Korpimäki, E. (2010) · Animal Conservation · doi:10.1111/j.1469-1795.2010.00379.x · Cited by 42
“Based on the repeated measure, the degrees of freedom were adjusted with the Kenward–Roger method of determination of error degrees of freedom (procedure GLIMMIX; Kenward & Roger, 1997).”
MethodAn analytic method for the placebo‐based pattern‐mixture model
Lu, K. (2013) · Statistics in Medicine · doi:10.1002/sim.6008 · Cited by 49
Differential Group Delay of the Frequency Following Response Measured Vertically and Horizontally
King, A., Hopkins, K., & Plack, C. J. (2016) · Journal of the Association for Research in Otolaryngology · doi:10.1007/s10162-016-0556-x · Cited by 42
“An adjustment to the degrees of freedom was made to account for the small sample size (Kenward and Roger 1997).”
MethodChristie, J. D., Vaslef, S. N., Chang, P. K., May, A. K., Gunn, S. R., Yang, S., Hardes, K., Kahl, L. P., Powley, W. M., Lipson, D. A., et al. (2015) · Critical Care Medicine · doi:10.1097/ccm.0000000000001132 · Cited by 42
“The Kenward-Roger method (35) was used to adjust the degrees of freedom (Models fitted using PC SAS v9.”
MethodLight therapy with boxes or glasses to counteract effects of acute sleep deprivation
Comtet, H., Geoffroy, P. A., Frisk, M. K., Hubbard, J. T., Robin-Choteau, L., Calvel, L. Y., Hugueny, L., Viola, A., & Bourgin, P. (2019) · Scientific Reports · doi:10.1038/s41598-019-54311-x · Cited by 53
Changes in EEG permutation entropy in the evening and in the transition from wake to sleep
Hou, F., Zhang, L., Qin, B., Gaggioni, G., Liu, X., & Vandewalle, G. (2020) · SLEEP · doi:10.1093/sleep/zsaa226 · Cited by 46
Moritz, S., & Jelinek, L. (2011) · Depression and Anxiety · doi:10.1002/da.20843 · Cited by 42
“Hereby, we used the adjustment to the standard errors and degrees of freedom derived by Kenward and Roger.[42] This gives more accurate standard errors when the sample size is small, and corrects the default estimate of the degrees of freedom.”
MethodSalonen, J., Hyvönen, T., Kaseva, J., & Jalli, H. (2012) · Weed Research · doi:10.1111/wre.12004 · Cited by 42
A wild bootstrap approach for nonparametric repeated measurements
Friedrich, S., Konietschke, F., & Pauly, M. (2017) · Computational Statistics & Data Analysis · doi:10.1016/j.csda.2016.06.016 · Cited by 41
“…more general mean-based analysis in various repeated measures designs have been proposed, see Huynh and Feldt (1976), Huynh (1978), Lecoutre (1991), Kenward and Roger (1997), Keselman et al. (2000), Pesarin (2001), Vallejo and Ato (2006), Xu and Cui (2008), Kenward and Roger (2009), Arnau et al.…”
Waters, T. P., Kim, S. Y., Sharma, A. J., Schnellinger, P., Bobo, J. K., Woodruff, R. T., Cubbins, L. A., Haghiac, M., Minium, J., Presley, L. H., et al. (2019) · Diabetologia · doi:10.1007/s00125-019-05051-0 · Cited by 45
Balestrieri, A., Winkler, A., Scribano, G., Gazzola, A., Lastrico, G., Grioni, A., Pellitteri‐Rosa, D., & Tremolada, P. (2022) · Environmental Pollution · doi:10.1016/j.envpol.2022.119137 · Cited by 40
The folded exponential transformation for proportions
Piepho, H. (2003) · Journal of the Royal Statistical Society Series D (The Statistician) · doi:10.1046/j.0039-0526.2003.00509.x · Cited by 41
“tMeans for transformed data in a group followed by the same capital letter are not significantly different by an approximate t-test based on restricted ML (Kenward and Roger, 1997).”
MethodSenthamizhchelvan, S., Hobbs, R. F., Song, H., Frey, E. C., Zhang, Z., Armour, E., Wahl, R. L., Loeb, D. M., & Sgouros, G. (2012) · Journal of Nuclear Medicine · doi:10.2967/jnumed.111.096677 · Cited by 41
“The Kenward–Roger approximation was used to assess the degrees of freedom (20).”
MethodHofmockel, K., Gallet‐Budynek, A., McCarthy, H. R., Currie, W. S., Jackson, R. B., & Finzi, A. C. (2011) · Global Change Biology · doi:10.1111/j.1365-2486.2011.02465.x · Cited by 44
“…variation in plant biomass, NPP and pools of N, the effect of elevated CO2 on N content and biomass were tested using repeated measures analysis (Kenward & Roger, 1997; Littell, 2002) with the 1996 pretreatment data as covariates, using Proc Mixed in SAS (Schlesinger & Lichter, 2001; Finzi et…”
MethodPaskett, E. D., Dudley, D., Young, G. S., Bernardo, B. M., Wells, K. J., Calhoun, E. A., Fiscella, K., Patierno, S. R., Warren-Mears, V., Battaglia, T. A., et al. (2016) · Journal of Women's Health · doi:10.1089/jwh.2014.5094 · Cited by 40
Dugas, M. B., Wamelink, C. N., Killius, A. M., & Richards‐Zawacki, C. L. (2015) · Behavioral Ecology · doi:10.1093/beheco/arv173 · Cited by 41
“Degrees-of-freedom for fixed effects in this and all analyses described below were calculated with the Kenward–Roger approximation (Kenward and Roger 1997).”
MethodPlotz, R. D., Grecian, W. J., Kerley, G. I. H., & Linklater, W. L. (2016) · PLoS ONE · doi:10.1371/journal.pone.0150571 · Cited by 41
Difford, G. F., Lassen, J., & Løvendahl, P. (2016) · Computers and Electronics in Agriculture · doi:10.1016/j.compag.2016.04.010 · Cited by 40
“A Kenward–Roger correction was utilised for computing the correct denominator degrees of freedom of fixed effects in the presence of repeated measures (Kenward and Roger, 1997).”
MethodBarletta, R. V., Gandra, J. R., Bettero, V. P., Araújo, C. E., Valle, T. A. D., de Almeida, G. F., de Jesus, E. F., Mingoti, R. D., Benevento, B. C., Júnior, J. E. D. F., et al. (2016) · Animal Feed Science and Technology · doi:10.1016/j.anifeedsci.2016.06.011 · Cited by 51
Wein, A., Bauhus, J., Bilodeau‐Gauthier, S., Scherer‐Lorenzen, M., Nock, C. A., & Staab, M. (2016) · PLoS ONE · doi:10.1371/journal.pone.0168751 · Cited by 46
Behm, M. O., Yee, K. L., Liu, R., Levine, V., Panebianco, D. L., & Fackler, P. H. (2017) · Clinical Drug Investigation · doi:10.1007/s40261-017-0512-5 · Cited by 41
Virus interferes with host-seeking behaviour of mosquito
Vogels, C. B. F., Fros, J. J., Pijlman, G. P., van Loon, J. J. A., Gort, G., & Koenraadt, C. J. M. (2017) · Journal of Experimental Biology · doi:10.1242/jeb.164186 · Cited by 44
“Degrees of freedom were calculated according to the method of Kenward and Roger (1997).”
MethodMeta‐analysis of Gaussian individual patient data: Two‐stage or not two‐stage?
Morris, T. P., Fisher, D. J., Kenward, M. G., & Carpenter, J. R. (2018) · Statistics in Medicine · doi:10.1002/sim.7589 · Cited by 46
Self-citationWilliamson, T. J., Thomas, K. S., Eisenberger, N. I., & Stanton, A. L. (2018) · International Journal of Behavioral Medicine · doi:10.1007/s12529-018-9720-5 · Cited by 41
“Significance testing for coefficients was conducted using z-scores, and results were identical when coefficients were tested using t tests with the Kenward-Roger method to estimate degrees of freedom, which uses an adjustment for estimating the covariance matrix that reduces bias from small sample sizes [52].”
MethodSpeech Planning at Turn Transitions in Dialog Is Associated With Increased Processing Load
Barthel, M., & Sauppe, S. (2019) · Cognitive Science · doi:10.1111/cogs.12768 · Cited by 42
“Their statistical significance was assessed using F -tests with Kenward-Roger approximations of degrees of freedom (Fox &Weisberg, 2011; Halekoh & Hojsgaard, 2014; Kenward & Roger, 1997).”
MethodLongobardi, C., Ferrigno, S., Gullotta, G., Jungert, T., Thornberg, R., & Marengo, D. (2021) · European Journal of Psychology of Education · doi:10.1007/s10212-021-00535-3 · Cited by 75
“The model was estimated using an RSPL estimator, and denominator degrees of freedom were calculated using the Satterthwaite (1941) method, with the Kenward–Roger adjustment (Kenward & Roger 1997).”
MethodHolden, K. G., Gangloff, E. J., Gomez-Mancillas, E., Hagerty, K., & Bronikowski, A. M. (2021) · General and Comparative Endocrinology · doi:10.1016/j.ygcen.2021.113758 · Cited by 48
Regular Caffeine Intake Delays REM Sleep Promotion and Attenuates Sleep Quality in Healthy Men
Weibel, J., Lin, Y.-S., Landolt, H., Berthomier, C., Brandewinder, M., Kistler, J., Rehm, S., Rentsch, K., Meyer, M., Borgwardt, S., et al. (2021) · Journal of Biological Rhythms · doi:10.1177/07487304211013995 · Cited by 56
“The degrees of freedom were based on the approximation of Kenward and Roger reported in Kenward and Roger (1997).”
MethodMusil, J., Horký, P., Slavík, O., Zbořil, A., & Horká, P. (2012) · Ecological Indicators · doi:10.1016/j.ecolind.2012.05.018 · Cited by 49
“The degrees of freedom were calculated using the Kenward–Roger method (Kenward and Roger, 1997).”
MethodInterpersonal Psychotherapy-Adolescent Skills Training: Effects on School and Social Functioning
Young, J. F., Kranzler, A., Gallop, R., & Mufson, L. H. (2012) · School Mental Health · doi:10.1007/s12310-012-9078-9 · Cited by 50
“The degrees of freedom were estimated with the Kenward-Roger’s approximation (Kenward & Roger, 1997), which accommodates small sample inferences, and effect sizes (Cohen’s d) were derived as specified by Verbeke and Molenberghs (2000).”
Brown, K. R., Anderson, G. A., Son, K., Rentfrow, G. K., Bush, L. P., Klotz, J. L., Strickland, J. R., Boling, J. A., & Matthews, J. C. (2008) · Journal of Animal Science · doi:10.2527/jas.2008-1108 · Cited by 55
Lamandé, M., Wildenschild, D., Berisso, F. E., Garbout, A., Marsh, M., Møldrup, P., Keller, T., Hansen, S. B., de Jonge, L. W., & Schjønning, P. (2013) · Soil Science · doi:10.1097/ss.0b013e3182a79e1a · Cited by 43
Sarvary, M. A., Bloem, K. A., Bloem, S., Carpenter, J. E., Hight, S. D., & Dorn, S. (2008) · Journal of Economic Entomology · doi:10.1603/0022-0493(2008)101[314:dfpafp]2.0.co;2 · Cited by 41
Dorn, L. D., Beal, S. J., Kalkwarf, H. J., Pabst, S., Noll, J. G., & Susman, E. J. (2013) · Journal of Adolescent Health · doi:10.1016/j.jadohealth.2012.10.005 · Cited by 40
Fenofibrate and metabolic syndrome
T. Kraja, A., A. Province, M., J. Straka, R., M. Ordovas, J., B. Borecki, I., & K. Arnett, D. (2010) · Endocrine, Metabolic & Immune Disorders - Drug Targets · doi:10.2174/187153010791213047 · Cited by 40
Movement in a confined space: Estimating path tortuosity
Miller, C. P., Christman, M. C., & Estévez, I. (2011) · Applied Animal Behaviour Science · doi:10.1016/j.applanim.2011.09.002 · Cited by 48
Puberty, statural growth, and growth hormone release in children with cerebral palsy
Kuperminc, M. N., Gurka, M. J., Houlihan, C. M., Henderson, R. C., Roemmich, J. N., Rogol, A. D., & Stevenson, R. D. (2009) · Journal of Pediatric Rehabilitation Medicine · doi:10.3233/prm-2009-0072 · Cited by 46
“To account for potential discrepancies in nutritional adequacy, all models also included baseline triceps skinfold z-scores for each child, as calculated using reference values from Frisancho [25] The Kenward-Roger approximation of the degrees of freedom was used to compute p-values from the overall tests[26].”
Foraging Location and Site Fidelity of the Double-crested Cormorant on Oneida Lake, New York
Coleman, J., Richmond, M., Rudstam, L., & Mattison, P. M. (2005) · Waterbirds · doi:10.1675/1524-4695(2005)28[498:flasfo]2.0.co;2 · Cited by 39
“Denominator degrees of freedom for the type three tests of fixed effects were calculated according to the method detailed by Kenward and Roger (1997) in order to minimize risk of Type I error (Schaalje et al. 2001).”
MethodCunningham, R. B., Lindenmayer, D. B., Barton, P. S., Ikin, K., Crane, M. J., Michael, D., Okada, S., Gibbons, P., & Stein, J. (2014) · Ecological Applications · doi:10.1890/13-0872.1 · Cited by 42
Sun Protection at Elementary Schools: A Cluster Randomized Trial
Hunter, S., Love-Jackson, K. M., Abdulla, R. A., Zhu, W., Lee, J., Wells, K. J., & Roetzheim, R. G. (2010) · JNCI Journal of the National Cancer Institute · doi:10.1093/jnci/djq010 · Cited by 41
Wilson, B. E., Showler, A. T., Reagan, T. E., & Beuzelin, J. M. (2012) · Journal of Economic Entomology · doi:10.1603/ec11271 · Cited by 40
“For all models, the KenwardÐRoger method (Kenward and Roger 1997) was used to compute denominator degrees of freedom for the test of Þxed effects for all variables, and TukeyÕs honestly signiÞcant difference (HSD) test (Tukey 1953) was used for mean separation.”
BackgroundMethodA re-randomisation design for clinical trials
Kahan, B. C., Forbes, A. B., Doré, C. J., & Morris, T. P. (2015) · BMC Medical Research Methodology · doi:10.1186/s12874-015-0082-2 · Cited by 43
“However, it has been previously noted that GEEs and mixed-effects models have led to increased error rates in small sample situations [19, 20].”
BackgroundHorncastle, V. J., Hellgren, E. C., Mayer, P. M., Engle, D. M., & Leslie, D. M. (2004) · The American Midland Naturalist · doi:10.1674/0003-0031(2004)152[0255:dcoerc]2.0.co;2 · Cited by 40
The Effect of Cariprazine on Hostility Associated With Schizophrenia
Citrome, L., Durgam, S., Lu, K., FERGUSON, P. W., & Laszlovszky, I. (2016) · The Journal of Clinical Psychiatry · doi:10.4088/jcp.15m10192 · Cited by 40
Reay‐Jones, F. P. F., Bessin, R. T., Brewer, M. J., Buntin, D. G., Catchot, A. L., Cook, D. R., Flanders, K. L., Kerns, D. L., Porter, R. P., Reisig, D., et al. (2016) · Journal of Economic Entomology · doi:10.1093/jee/tow109 · Cited by 41
“The Kenward–Roger method (Kenward and Roger 1997) was used to compute denominator degrees of freedom for the test of fixed effects for all variables.”
MethodHuang, Y., Park, E., Edirisinghe, I., & Burton‐Freeman, B. M. (2016) · Food & Function · doi:10.1039/c6fo00995f · Cited by 41
Blond, M. B., Rosenkilde, M., Gram, A. S., Tindborg, M., Christensen, A. N., Quist, J. S., & Stallknecht, B. M. (2019) · British Journal of Sports Medicine · doi:10.1136/bjsports-2018-100036 · Cited by 40
Quint, T., Brunner, P. M., Sinz, C., Steiner, I., Ristl, R., Vigl, K., Kimeswenger, S., Neubauer, K., Pirkhammer, D., Zikeli, M., et al. (2020) · Journal of Clinical Medicine · doi:10.3390/jcm9041241 · Cited by 42
“Degrees of freedom were calculated using the method by Kenward and Roger [17].”
MethodReischenböck, V., Marks, M., Herren, D. B., & Schindele, S. F. (2020) · Journal of Hand Surgery (European Volume) · doi:10.1177/1753193420977244 · Cited by 40
“Due to missing data for follow-up time points in some patients, parameters were estimated with restricted maximum likelihood using the method of Kenward and Roger (1997).”
MethodStauffer, V. L., Song, G., Kinon, B. J., Ascher‐Svanum, H., Chen, L., Feldman, P. D., & Conley, R. R. (2011) · Schizophrenia Research · doi:10.1016/j.schres.2011.09.028 · Cited by 48
“To approximate inference for fixed effects, Kenward– Roger approximation (Kenward and Roger, 1997) was used for estimation of denominator degrees of freedom.”
Method
Metadata
- Authors
- Kenward, M. G., & Roger, J. H.
- Affiliations
- University of Kent (GB)
- Venue
- Biometrics
- Publisher
- JSTOR
- Published
- 1997-09
- Volume
- 53
- Issue
- 3
- Pages
- 983
- ISSN
- 0006-341X (ISSN-L)
- OpenAlex
- W1981747359
- Cited by
- 4,552
- References
- 23
- Citations by year
- 2026: 217 · 2025: 196 · 2024: 216 · 2023: 213 · 2022: 261 · 2021: 299 · 2020: 287 · 2019: 270 · 2018: 247 · 2017: 240 · 2016: 286 · 2015: 256 · 2014: 217 · 2013: 189 · 2012: 218
- FWCI
- 7.02
- Type
- journal article
- Language
- en
- Open access
- closed
- Locations
- Biometrics (publishedVersion)
- PubMed (publishedVersion)
- Rothamsted Repository (Rothamsted Repository) (submittedVersion)
- Kent Academic Repository (University of Kent) (submittedVersion)
- Topics
- Physical Sciences › Mathematics › Statistics and Probability › Statistical Methods and Bayesian Inference
- Physical Sciences › Mathematics › Statistics and Probability › Advanced Statistical Methods and Models
- Physical Sciences › Mathematics › Applied Mathematics › Statistical and numerical algorithms
- Keywords
- restricted maximum likelihood, small sample inference, fixed effects, Wald statistic, covariance matrix estimation, small sample bias, Hotelling's T2 statistic, linear mixed models, linear Gaussian models
- MeSH terms
- Analysis of Variance, Biometry, Clinical Trials as Topic, Humans, Intermittent Claudication, Nitrogen Fixation, Plants, Probability, Regression Analysis, Research Design, Rhizobium, Soil Microbiology, Reproducibility of Results, Models, Statistical, Bias, Randomized Controlled Trials as Topic, Cross-Over Studies
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.