The DOI matches its Crossref record; 19 of the 20 references it cites were found in a registry or an index.
Multiple regression of cost data: use of generalised linear models
Abstract
Objective: Choosing an appropriate method for regression analyses of cost data is problematic because it must focus on population means while taking into account the typically skewed distribution of the data. In this paper we illustrate the use of generalised linear models for regression analysis of cost data. Methods: We consider generalised linear models with either an identity link function (providing additive covariate effects) or log link function (providing multiplicative effects), and with gaussian (normal), overdispersed poisson, gamma, or inverse gaussian distributions. These are applied to estimate the treatment effects in two randomised trials adjusted for baseline covariates. Criteria for choosing an appropriate model are presented. Results: In both examples considered, the gaussian model fits poorly and other distributions are to be preferred. When there are variables of prognostic importance in the model, using different distributions can materially affect the estimates obtained; it may also be possible to discriminate between additive and multiplicative covariate effects. Conclusions: Generalised linear models are attractive for the regression of cost data because they provide parametric methods of analysis where a variety of non-normal distributions can be specified and the way covariates act can be altered. Unlike the use of data transformation in ordinary least-squares regression, generalised linear models make inferences about the mean cost directly.
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
“Cost data and QALYs will be analysed using generalised linear models to account for non-normal distributions.83”
From Development, evaluation and implementation of a digital behavioural health treatment for chronic pain: study protocol of the multiphase DAHLIA project (2022) · cites this paper as [83]
Citations
Cites
Model selection and multimodel inference: a practical information-theoretic approach.
Guthery, F. S., Burnham, K. P., & Anderson, D. R. (2003) · The Journal of Wildlife Management · doi:10.2307/3802723 · Cited by 41,495
(2005) · Springer eBooks · doi:10.1007/0-387-27255-0_9 · Cited by 20,333
Longitudinal data analysis using generalized linear models
LIANG, K.-Y., & ZEGER, S. L. (1986) · Biometrika · doi:10.1093/biomet/73.1.13 · Cited by 18,550
Practical Statistics for Medical Research.
Walter, S., & Altman, D. G. (1992) · Biometrics · doi:10.2307/2532320 · Cited by 11,666
Estimating log models: to transform or not to transform?
Manning, W. G., & Mullahy, J. (2001) · Journal of Health Economics · doi:10.1016/s0167-6296(01)00086-8 · Cited by 1,790
A Comparison of Alternative Models for the Demand for Medical Care
Duan, N.-H., Manning, W., Morris, C., & Newhouse, J. (1983) · Journal of Business and Economic Statistics · doi:10.1080/07350015.1983.10509330 · Cited by 1,410
Representing uncertainty: the role of cost‐effectiveness acceptability curves
Fenwick, E. A. L., Claxton, K., & Sculpher, M. J. (2001) · Health Economics · doi:10.1002/hec.635 · Cited by 1,112
Stinnett, A. A., & Mullahy, J. (1998) · Medical Decision Making · doi:10.1177/0272989x98018002s09 · Cited by 1,103
The logged dependent variable, heteroscedasticity, and the retransformation problem.
Manning, W. (1998) · Journal of Health Economics · doi:10.1016/s0167-6296(98)00025-3 · Cited by 959
Much ado about two: reconsidering retransformation and the two-part model in health econometrics.
Mullahy, J. (1998) · Journal of Health Economics · doi:10.1016/s0167-6296(98)00030-7 · Cited by 791
Cited by
Sorted by citations
Items 201–300 of 404
DEEP Study: Modeling Outcomes and Costs of Persistent Orofacial Pain
Durham, J., Breckons, M., Vale, L. D., & Shen, J. (2021) · JDR Clinical & Translational Research · doi:10.1177/23800844211063870 · Cited by 15
“Best practice for managing cost data was followed throughout the analysis (Barber and Thompson 2004; Mihaylova et al. 2011).”
MethodEvaluating Quality Metrics and Cost After Discharge
de Mestral, C., Salata, K., Hussain, M. A., Kayssi, A., Al-Omran, M. A., & Roche‐Nagle, G. (2018) · Annals of Surgery · doi:10.1097/sla.0000000000002767 · Cited by 15
“Generalized linear models with a logarithmic link and gamma distribution, Gamma regression, were used to evaluate associations with 30-day cost given its positively skewed non-normal distribution.(25) Gamma regression provides a ratio of means between levels of a given covariate or, in other words, a percentage increa…”
MethodRamnarayan, P., Evans, R. E. C., Draper, E. S., Seaton, S. E., Wray, J., Stephen Morris, A., & Pagel, C. (2019) · BMJ Open · doi:10.1136/bmjopen-2018-028000 · Cited by 15
HIV Positive Hispanic/Latinos Who Delay HIV Care: Analysis of Multilevel Care Engagement Barriers
Keesee, M. S., Natale, A. P., & Curiel, H. F. (2012) · Social Work in Health Care · doi:10.1080/00981389.2012.662208 · Cited by 15
“00), a nonnegative outcome measurement and a nonconstant variance ( Romeo, Knapp, & Scott, 2006 ; Manning & Mullahy, 2001 ; Barber & Thompson, 2004 ).”
InfluentialChorozoglou, M., Mahon, M., Pimperton, H., Worsfold, S., & Kennedy, C. (2018) · BMJ Paediatrics Open · doi:10.1136/bmjpo-2017-000228 · Cited by 15
The economic burden of myalgic encephalomyelitis/chronic fatigue syndrome in Australia
Zhao, T., Cox, I. A., Ahmad, H., Campbell, J. A., Hensher, M., Palmer, A. J., Kelly, R., Rogerson, M. J., Wills, K. E., & de Graaff, B. (2023) · Australian Health Review · doi:10.1071/ah23106 · Cited by 14
Wenig, C. M., Knopf, H. C., & Menn, P. (2011) · BMC Health Services Research · doi:10.1186/1472-6963-11-340 · Cited by 14
“Reducing the analysis to cases with drug intake and therefore positive costs, in a second step, the association of BMI and total costs was analysed using a gamma model with log-link function [40,41].”
MethodReplicating Health Economic Models: Firm Foundations or a House of Cards?
Bermejo, I., Tappenden, P., & Youn, J.-H. (2017) · PharmacoEconomics · doi:10.1007/s40273-017-0553-x · Cited by 14
Tanvejsilp, P., Loeb, M. B., Dushoff, J. G., & Xie, F. (2017) · PharmacoEconomics - Open · doi:10.1007/s41669-017-0057-9 · Cited by 14
“The AICs (Online Appendix Table 4) and graphical analyses (Online Appendix Fig.”
BackgroundMethodInfluentialDoble, B., Wong, W. H. M., Finkelstein, E. A., & on behalf of the COMPASS study team (2021) · Palliative Medicine · doi:10.1177/0269216321999576 · Cited by 14
Aroke, H. A., Buchanan, A. L., Wen, X., Ragosta, P., Koziol, J. A., & Kogut, S. J. (2018) · Journal of Managed Care & Specialty Pharmacy · doi:10.18553/jmcp.2018.24.3.214 · Cited by 14
Icks, A., Haastert, B., Arend, W., Konein, J., Thorand, B., Holle, R., Laxy, M., Schunk, M. V., Neumann, A., Wasem, J., et al. (2018) · Diabetic Medicine · doi:10.1111/dme.13832 · Cited by 14
Depreitere, B., Turner, I., Vandoren, C., & Choi, D. (2019) · World Neurosurgery · doi:10.1016/j.wneu.2019.01.130 · Cited by 14
“A generalized linear model with gamma family and log link were used to account for the skewness of the cost data.(17) Average marginal effects of included covariates were calculated, showing the adjusted impact of each on cost.”
MethodModels of generalist and specialist care in smaller hospitals in England: a mixed-methods study
Vaughan, L., Bardsley, M., Bell, D., Davies, M. S., Goddard, A. F., Imison, C., Melnychuk, M., Stephen Morris, A., & Rafferty, A. M. (2021) · Health Services and Delivery Research · doi:10.3310/hsdr09040 · Cited by 13
McMaughan, D. J., Jones, J. L., Mulcahy, A. C., Tucker, E. C., Beverly, J., & Perez-Patron, M. J. (2022) · Intellectual and developmental disabilities · doi:10.1352/1934-9556-60.6.484 · Cited by 14
McGinley, M., Carlson, J. J., Reihm, J., Plow, M. A., Roser, M., Sisodia, N., Cohen, J. A., Misra‐Hebert, A. D., Lazar, A., & Bove, R. M. (2024) · Contemporary Clinical Trials · doi:10.1016/j.cct.2024.107544 · Cited by 14
Early identification of rheumatoid arthritis: does it induce treatment-related cost savings?
van Mulligen, E., Mölken, M. R., & Mil, A. H. M. V. D. H. (2024) · Annals of the Rheumatic Diseases · doi:10.1136/ard-2024-225746 · Cited by 13
Haas, L., Stargardt, T., Schreyögg, J., Schlösser, R., Hofmann, T., Danzer, G., & Klapp, B. F. (2012) · Journal of Psychosomatic Research · doi:10.1016/j.jpsychores.2012.09.001 · Cited by 13
“] 17% 770 [658–882] 21% 703 [639–767] 17% ] 7% 217 [199–235] 6% 238 [222–253] 6% ] 7% 236 [203–269] 6% 264 [240–288] 6% 1% 23 [17–29] 1% 29 [24–33] 1%”
Intensive Care Unit Admission With Community-Acquired Pneumonia
Vohra, A. S., Meltzer, D. O., Ruhnke, G. W., Tak, H. J., & Shah, M. (2015) · The American Journal of the Medical Sciences · doi:10.1097/maj.0000000000000568 · Cited by 13
“The impact of PSI risk class and comorbidities on cost among ICU patients was estimated based on a generalized linear model with cost as the dependent variable, using a g distribution and a log-link function.(32) Because of”
MethodEarly morbidities following paediatric cardiac surgery: a mixed-methods study
Brown, K., Pagel, C., Ridout, D. A., Wray, J., Tsang, V. T., Anderson, D. R., Banks, V., Barron, D. J., Cassidy, J. V., Chigaru, L., et al. (2020) · Health Services and Delivery Research · doi:10.3310/hsdr08300 · Cited by 15
Warner, G., Durbeej, N., Salari, R., Fängström, K., Lampa, E., Baghdasaryan, Z., Osman, F., Löfving, S. G., Aronsson, A., Feldman, I., et al. (2020) · BMJ Open · doi:10.1136/bmjopen-2019-035459 · Cited by 13
“51 Estimated differences in outcomes will be compared with differences in costs and presented as incremental cost-effectiveness ratios.”
MethodHealth literacy and age-related health-care utilisation: a multi-dimensional approach
Gerich, J., Moosbrugger, R., & Heigl, C. (2020) · Ageing & Society · doi:10.1017/s0144686x20001609 · Cited by 8
“Similarly, OLS regressions are not appropriate for the analysis of medication costs because these distributions are also typically skewed, which means that heteroskedasticity, non-normal residuals and non-linear relationships could be expected (Barber and Thompson, 2004).”
BackgroundMethodRelative efficiency of chlamydia screening in non-clinical settings in two California counties
Morris, S., Bauer, H. M., Chartier, M., Howard, H., Watson, S., Yokotobi, J., Taylor, A., & BOLAN, G. A. (2009) · International Journal of STD & AIDS · doi:10.1258/ijsa.2009.008474 · Cited by 13
Illou, M. M. A., Haddad, S., Agier, I., & Ridde, V. (2015) · BMC Health Services Research · doi:10.1186/s12913-015-0957-2 · Cited by 18
“The literature suggests a variety of methods for taking into account these distinctive distributions [36–38].”
BackgroundDonovan, M., Khan, A., & Johnston, V. (2016) · Journal of Occupational Rehabilitation · doi:10.1007/s10926-016-9628-3 · Cited by 13
“To analyse effectiveness of the IPP on the adjusted mean cost per claim at P1 and P2, we used generalised linear models which are suitable for analysis of non-normal data [43, 44].”
MethodPanca, M., Christie, D., Cole, T. J., Costa, S., Gregson, J., Holt, R., Hudson, L. D., Kessel, A. S., Kinra, S., Mathiot, A., et al. (2018) · BMJ Open · doi:10.1136/bmjopen-2017-018640 · Cited by 13
“Participants in the clinical trial were well balanced in terms of age, gender and baseline BMI and EQ-5D values, although there were slightly fewer black participants and slightly greater numbers of white and Asian participants in the HELP arm.”
Pevnick, J. M., Li, N., Asch, S. M., Jackevicius, C. A., & Bell, D. S. (2014) · BMC Medical Informatics and Decision Making · doi:10.1186/1472-6947-14-79 · Cited by 12
“Because cost variables often contain a skewed distribution with many outlying data points [17,18], a Box-Cox transformation was used to determine the best way of transforming the patient copayment variable to minimize root mean square error.”
MethodMaheswaran, H., Petrou, S., MacPherson, P., Kumwenda, F., Lalloo, D. G., Corbett, E. L., & Clarke, A. (2017) · JAIDS Journal of Acquired Immune Deficiency Syndromes · doi:10.1097/qai.0000000000001373 · Cited by 12
Direct medical costs of breast cancer in Jordan: cost drivers and predictors
Mousa, R., Hammad, E. A., Melhem, J. M., & Al-Jaghbir, M. T. (2020) · Expert Review of Pharmacoeconomics & Outcomes Research · doi:10.1080/14737167.2021.1859372 · Cited by 12
“Diagnostic tests were used to identify the best fit distribution for the cost data [24].”
MethodSchulz, C., Büchele, G., Peter, R. S., Rothenbacher, D., Brettschneider, C., Liener, U. C., Becker, C., Rapp, K., & König, H. (2021) · The European Journal of Health Economics · doi:10.1007/s10198-021-01295-z · Cited by 13
“Therefore, we applied a generalised linear model with a gamma distribution and a log link function to estimate the mean amount of costs, if occurred [49].”
MethodHow Expensive Are Hospitalizations by COVID-19? Evidence From Colombia
Alvis-Zakzuk, N. J., Flórez-Tanus, Á., Díaz-Jiménez, D. P., Chaparro, P., Castañeda-Orjuela, C. A., de la Hoz, F., Castell, C. R. D., & Alvis‐Guzmán, N. (2022) · Value in Health Regional Issues · doi:10.1016/j.vhri.2022.04.005 · Cited by 12
“The coefficients resulting from the modeling were presented in their exponentiated form, indicating a cost relationship between a category of interest and a reference category for categorical predictors or as the percent increase in the mean cost per unit increase for a continuous predictor.(12) Independent variables…”
MethodDu, X. L., Parikh, R. C., & Lairson, D. R. (2015) · Lung Cancer · doi:10.1016/j.lungcan.2015.09.017 · Cited by 12
Temporal Association between Home Nursing and Hospital Costs at End of Life in Three Provinces
Seow, H. Y., Pataky, R. E., Lawson, B. J., O’Leary, E. M., Sutradhar, R., Fassbender, K., McGrail, K. M., Barbera, L. C., Burge, F., Peacock, S. J., et al. (2016) · Current Oncology · doi:10.3747/co.23.2971 · Cited by 12
Hospitalization Cost Model of Pediatric Surgical Treatment of Chiari Type 1 Malformation.
Lam, S., Mayer, R., Luerssen, T., & Pan, W.-T. (2016) · Jornal de Pediatria · doi:10.1016/j.jpeds.2016.08.074 · Cited by 10
Berger, A. J., Friedlander, D. F., Herzog, P., Ortega, G., O’Leary, M. P., Kathrins, M. N., & Trinh, Q. (2019) · The Journal of Sexual Medicine · doi:10.1016/j.jsxm.2019.07.004 · Cited by 12
Jung, B., Kim, J., Ha, I., & Lee, J. (2020) · BMJ Open · doi:10.1136/bmjopen-2019-033159 · Cited by 12
Health care utilization and excess costs after pelvic fractures among older people in Germany
Andrich, S., Haastert, B., Neuhaus, E., Frommholz, K., Arend, W., Ohmann, C., Grebe, J., Vogt, A., Brunoni, C., Jungbluth, P., et al. (2021) · Osteoporosis International · doi:10.1007/s00198-021-05935-1 · Cited by 12
“In the second part, a gamma model with log-link was fitted on the subpopulation with positive costs estimating CRs for unit changes of independent variables [29].”
MethodGroff, M., Latimer, E., Joober, R., Iyer, S. N., Schmitz, N., Abadi, S., Abdel-Baki, A., Casacalenda, N., Margolese, H. C., Jarvis, G. E., et al. (2021) · Schizophrenia Bulletin · doi:10.1093/schbul/sbaa130 · Cited by 13
Hersh, A. R., Mischkot, B. F., Greiner, K. S., Garg, B., & Caughey, A. B. (2021) · The Journal of Maternal-Fetal & Neonatal Medicine · doi:10.1080/14767058.2020.1849096 · Cited by 11
“As a sensitivity analysis, we compared mean costs using generalized linear regression models (GLM) as this is the most commonly employed method to analyze costs since the distribution of costs tends to be right-skewed [14].”
MethodChapter 11: Positive Continuous Data: Gamma and Inverse Gaussian GLMs
Dunn, P. K., & Smyth, G. K. (2018) · Springer texts in statistics · doi:10.1007/978-1-4419-0118-7_11 · Cited by 11
Sweeney, S., Vassall, A., Guinness, L., Siapka, M., Chimbindi, N., Mudzengi, D. L., & Gomez, G. B. (2020) · PharmacoEconomics · doi:10.1007/s40273-020-00898-3 · Cited by 11
Costs of Depression from Claims Data for Medicare Recipients in A Population-Based Sample
Alexandre, P. K., Hwang, S., Roth, K. B., Gallo, J. J., & Eaton, W. W. (2016) · Journal of Health and Human Services Administration · doi:10.1177/107937391603900105 · Cited by 10
“( Barber & Thompson, 2004) Models were adjusted for differences in demographic, socioeconomic, and clinical variables that could confound the relationship between depression and medical costs.”
Andrén, P., de la Cruz, L. F., Isomura, K., Lenhard, F., Hall, C. L., Davies, E. B., Murphy, T. L., Hollis, C. P., Sampaio, F., Feldman, I., et al. (2021) · Trials · doi:10.1186/s13063-021-05592-z · Cited by 12
Dorling, A., Rebollo‐Mesa, I., Hilton, R. M., Peacock, J. L., Vaughan, R., Gardner, L. M., Danzi, G., Baker, R. J., Clark, B., Thuraisingham, R. C., et al. (2014) · Trials · doi:10.1186/1745-6215-15-30 · Cited by 11
“Nonnormality in errors will be allowed for by using generalised linear models with an appropriate error structure (for example, a gamma distribution [12]).”
MethodViner, R., Kinra, S., Christie, D., Cole, T. J., Costa, S., Croker, H. A., Fry, T., Hsia, Y., Hudson, L. D., Kessel, A. S., et al. (2020) · Programme Grants for Applied Research · doi:10.3310/pgfar08030 · Cited by 12
The socioeconomic burden of facioscapulohumeral muscular dystrophy
Blokhuis, A. M., Deenen, J. C. W., Voermans, N. C., van Engelen, B. G. M., Kievit, W., & Groothuis, J. T. (2021) · Journal of Neurology · doi:10.1007/s00415-021-10591-w · Cited by 10
“A generalized linear model with an identity link function and gamma distribution was fitted to the data to investigate whether the mean per-patient annual costs of illness varied among the three mobility classes (walking without mobility aid, walking with mobility aid, unable to walk) and to predict costs for these gr…”
MethodTsiachristas, A., & Mölken, M. R. (2014) · Applied Economics · doi:10.1080/00036846.2013.864044 · Cited by 10
“GLMMswere also selected because they overcome limitations of OLS and two-stage models by avoiding with ad-hoc adjustments for skewed data and accommodating zero observations for costs simultaneously (Manning and Mullahy, 2001; Barber and Thompson, 2004; Buntin and Zaslavsky, 2004; Gilleskie and Mroz, 2004; Gilmer et a…”
BackgroundMethodShaw, E., Addy, I., Stoddart, M., Vank, C., Grier, S., Wiegand, I., Leibovici, L., Eliakim‐Raz, N., Vallejo‐Torres, L., Stephen Morris, A., et al. (2016) · BMJ Open · doi:10.1136/bmjopen-2016-011500 · Cited by 10
Berkovich, R., Fox, E., Okai, A. F., Ding, Y., Gorritz, M., Bartolome, L., Wade, R. L., Su, W. W., Johnson, K. M., & Russo, P. A. (2020) · Journal of Medical Economics · doi:10.1080/13696998.2020.1857257 · Cited by 10
Excess healthcare spending associated with fractures among adults with cerebral palsy
Whitney, D. G., Caird, M. S., Jepsen, K. J., Hurvitz, E. A., & Hirth, R. A. (2022) · Disability and health journal · doi:10.1016/j.dhjo.2022.101315 · Cited by 10
For the Protease Inhibitor monotherapy Versus Ongoing Triple therapy (PIVOT) Trial Team, Oddershede, L., Walker, S., Stöhr, W., Dunn, D. T., Arenas‐Pinto, A., Paton, N. I., & Sculpher, M. J. (2016) · PharmacoEconomics · doi:10.1007/s40273-016-0396-x · Cited by 10
“Generalised linear regression models (GLMs) were used to obtain the incremental estimates of costs and QALYs whilst adjusting for any imbalances in baseline characteristics (with the latter selected a priori) [21].”
MethodMcGillion, M. H., Henry, S., Busse, J. W., Ouellette, C., Katz, J. D., Choinière, M., Lamy, A. L., Whitlock, R. P., Pettit, S. M., Hare, J., et al. (2019) · BMJ Open · doi:10.1136/bmjopen-2018-022995 · Cited by 12
Brinkman‐Stoppelenburg, A., Polinder, S., Olij, B. F., den Berg, B., Gunnink-Boonstra, N., Hendriks, M. P., van der Linden, Y. M., Nieboer, D., van der Padt‐Pruijsten, A., Peters, L., et al. (2019) · European Journal of Cancer Care · doi:10.1111/ecc.13198 · Cited by 10
“A gamma regression model was used due to the expected skewed distribution of costs (Barber & Thompson, 2004).”
MethodIsayama, T., O’Reilly, D. J., Beyene, J., Shah, P. S., Lee, S. K., & McDonald, S. D. (2020) · The Journal of Pediatrics · doi:10.1016/j.jpeds.2020.06.060 · Cited by 10
Palliative Care Consultation in the Intensive Care Unit Reduces Hospital Costs: A Cost-Analysis
Chung, T. H., Nguyen, L. K., Lal, L. S., Swint, J. M., Le, Y. L., Hanley, K., Siller, E., & Chanaud, C. M. (2022) · Journal of Palliative Care · doi:10.1177/08258597221095986 · Cited by 12
Tylee, A. T., Barley, E. A., Walters, P., Achilla, E., Borschmann, R., Leese, M., McCrone, P., Palacios, J. E., Smith, A., Simmonds, R., et al. (2016) · Programme Grants for Applied Research · doi:10.3310/pgfar04080 · Cited by 12
“30 months: everyone No depression (n= 498), mean, £ (SD) Depression (n= 100), mean, £ (SD) Difference, mean, £ (95% CI) A&E attendances 10 (42) 14 (35) 4 (–5 to 13) Day hospital attendances 57 (636) 46 (161) –11 (–137 to 115) Inpatient stays 449 (2247) 1237 (5372) 788 (143 to 1434) Outpatient visits 268 (553) 434 (137…”
Trends in Eye Injuries and Associated Medical Costs among Children in the United States, 2002–2014
Luo, H., Shrestha, S. S., Zhang, X., SAADDINE, J. B., Zeng, X., & Reeder, T. J. (2018) · Ophthalmic Epidemiology · doi:10.1080/09286586.2018.1441425 · Cited by 10
“with log link and gamma distribution to estimate the average costs examined in this study because expenditure data were highly skewed and right-tailed.(29) We compared the predicted expenditures between the first and other later periods using t test with unequal variance.”
MethodTanvejsilp, P., Loeb, M. B., Dushoff, J. G., & Xie, F. (2017) · PharmacoEconomics - Open · doi:10.1007/s41669-017-0053-0 · Cited by 9
“Smaller AIC values indicate better-fitting models; differences of ten or more in AIC indicate that the better-fitting model should be strongly preferred [14].”
BackgroundMethodInfluentialTriggering Factors of Primary Care Costs in the Years Following Type 2 Diabetes Diagnosis in Mexico
Castro‐Ríos, A., Nevárez-Sida, A., Tiro-Sánchez, M. T., & Wacher, N. H. (2014) · Archives of Medical Research · doi:10.1016/j.arcmed.2014.05.002 · Cited by 9
Sari, A. A., Rezaei, S., Arab, M., Matin, B. K., & Majdzadeh, R. (2017) · Medical Journal of the Islamic Republic of Iran · doi:10.14196/mjiri.31.63 · Cited by 9
Hunter, R. M., Anderson, R., Kirkpatrick, T., Lennox, C., Warren, F. C., Taylor, R. S., Shaw, J. J., Haddad, M., Stirzaker, A., Maguire, M., et al. (2021) · The European Journal of Health Economics · doi:10.1007/s10198-021-01360-7 · Cited by 9
Wolf, D. C., Jaganathan, S., Burudpakdee, C., Seetasith, A., Low, R., Lee, E. W., Gucky, J., Yassine, M., & Schwartz, D. A. (2018) · Patient Preference and Adherence · doi:10.2147/ppa.s148777 · Cited by 9
Saluja, R., Jiao, T., Koshy, L., Cheung, M. C., & Chan, K. (2021) · Current Oncology · doi:10.3390/curroncol28010060 · Cited by 9
“Generalized linear regression models with Gamma distribution and log link were used to examine the changes in ICERs over time from 2012 to 2018, as costs have non-negative values and are right-skewed [14,15].”
MethodRihal, C. S., Kamath, C. C., Holmes, D. R., Reller, M. K., Anderson, S. S., McMurtry, E. K., & Long, K. H. (2006) · PubMed · Cited by 9
Curry, N. S., Davenport, R. A., Thomas, H., Fox, E. E., Lucas, J., Evans, A. L., Massou, E., Sharma, R., Shanmugaranjan, S., Rourke, C., et al. (2024) · Health Technology Assessment · doi:10.3310/jytr6938 · Cited by 8
Wan, Y., Sun, S. X., Corman, S. L., Huang, X., Gao, X., & Shorr, A. F. (2015) · International Journal of COPD · doi:10.2147/copd.s80106 · Cited by 8
“Wilcoxon rank-sum tests were used to compare the HCRU and cost data between study groups because they usually have a skewed distribution.(10) The differences between baseline and postindex exacerbation rates (PPPM), monthly HCRU, and monthly costs were calculated for each patient, and difference-in-difference (DID) li…”
Cost of illness of spinal muscular atrophy (SMA) in Italy
Marcellusi, A., Bini, C., Casiraghi, J. L., D’Ambrosio, F., Rotundo, M. A., Pallara, A., & Mennini, F. S. (2019) · Global & Regional Health Technology Assessment · doi:10.1177/2284240319867662 · Cited by 8
Esposti, L. D., Saragoni, S., Buda, S., & Esposti, E. D. (2014) · ClinicoEconomics and Outcomes Research · doi:10.2147/ceor.s63666 · Cited by 8
“A generalized linear model with an identity link function and a gamma distribution was used to estimate the association between health care costs and the type of OHD treatment.(20) Two-tailed P-values ,0.”
Economic Evaluation of the Protecting Teeth @ 3 Randomized Controlled Trial
Anopa, Y., Macpherson, L. M. D., McMahon, A. D., Wright, W., Conway, D. I., & McIntosh, E. (2022) · JDR Clinical & Translational Research · doi:10.1177/23800844221090444 · Cited by 8
“Differences in cost and QALYs between the intervention and control groups were estimated using generalized linear models (Barber and Thompson 2004).”
MethodMoore, P., Bennett, K., & Normand, C. E. M. (2014) · Applied Health Economics and Health Policy · doi:10.1007/s40258-014-0121-x · Cited by 8
Chow, B. J. W., Green, R. E., Coyle, D., Laine, M., Hänninen, H., Leskinen, H., Rajda, M., Larose, É., Hartikainen, J. E. K., Hedman, M., et al. (2013) · Trials · doi:10.1186/1745-6215-14-443 · Cited by 8
“The modified Parks test can be used to determine the appropriate family while the novel technique of extended estimating equations has been developed, which allows identification of both the link function and family [18-20].”
BackgroundMethodMedical Costs of Chronic Musculoskeletal Pain in Italy
Garattini, L., Koleva, D., Motterlini, N., & Cornago, D. (2007) · Clinical Drug Investigation · doi:10.2165/00044011-200727020-00007 · Cited by 8
Konnopka, C., Büchele, G., Jaensch, A., Rothenbacher, D., Becker, C., Rapp, K., Henken, E., & König, H. (2023) · Osteoporosis International · doi:10.1007/s00198-023-06965-7 · Cited by 7
“Therefore, weighted generalized linear models with a gamma distribution and a log link function were applied to estimate the amount of costs [52].”
MethodSun, S., Jönsson, H., Salén, K.-G., Anden, M., Beckman, L., & Fransson, P. (2022) · The European Journal of Health Economics · doi:10.1007/s10198-022-01467-5 · Cited by 7
“In cost analysis, the Generalized linear models (GLM) assuming gamma distribution with log and identity links were commonly applied [22, 23].”
MethodTunthanathip, T., Sae-heng, S., Oearsakul, T., Kaewborisutsakul, A., Inkate, S., Madteng, S., & Tanvejsilp, P. (2022) · Journal of Neurosciences in Rural Practice · doi:10.25259/jnrp-2022-3-45 · Cited by 7
“The influence of disease severity and baseline characteristics on patient expenditures [Table 5] demonstrated results of GLM analyses for patient expenditures.”
MethodInfluentialBoye, K. S., Bae, J. P., Thieu, V. T., & Lage, M. J. (2023) · Diabetes Therapy · doi:10.1007/s13300-023-01507-0 · Cited by 7
“Specifically, given the skewed nature of cost data, generalized linear models (GLM) with gamma distribution and log link [15] were used to examine all-cause total costs, outpatient costs, and drug costs, while all-cause acute care costs were examined using a two-part model.”
Using statistical models to assess medical cost of hepatitis C virus.
Vahedi, M., Pourhoseingholi, A., Ashtari, S., Pourhoseingholi, M. A., Karkhane, M., Moghimi-Dehkordi, B., Safaee, A., Kimiia, Z., & Alavian, S. M. (2012) · Gastroenterology and hepatology from bed to bench. · Cited by 7
Mau, L., Preussler, J. M., Burns, L. J., Leppke, S. N., Majhail, N. S., Meyer, C. L., Mupfudze, T. G., Saber, W., Steinert, P., & Vanness, D. J. (2020) · PharmacoEconomics · doi:10.1007/s40273-020-00891-w · Cited by 7
Lu, S., Rakovitch, E., Hannon, B. L., Zimmermann, C., Dharmarajan, K. V., Yan, M., de Almeida, J. R., Yao, C. M. K. L., Gillespie, E. F., Chino, F. L., et al. (2024) · JCO Oncology Practice · doi:10.1200/op.23.00576 · Cited by 7
“The generalized linear model 44 with gamma distribution and log link is commonly used to model cross-sectional cost data 45 as this model can handle the positively skewed distribution in cost data and make inferences on mean cost directly.”
Hunter, R. M., Huynh, J., Lüchtenborg, M., Armes, J., Plugge, E., Taylor, R. M., Visser, R., & Davies, E. (2024) · EClinicalMedicine · doi:10.1016/j.eclinm.2024.102575 · Cited by 7
Gardner, C., Rankin, J. M., Geelhoed, E. A., Nguyen, M., Newman, M. A. J., Cutlip, D. E., Knuiman, M. W., Briffa, T. G., Hobbs, M., & Sanfilippo, F. M. (2014) · BMJ Open · doi:10.1136/bmjopen-2014-006337 · Cited by 7
Isaranuwatchai, W., de Oliveira, C., Mittmann, N., Evans, W. K., Peter, A., Truscott, R., & Chan, K. (2019) · BMJ Open · doi:10.1136/bmjopen-2018-026022 · Cited by 7
“literature has called for more up-to-date and precise health care cost estimates of smoking.(9, 32)”
BackgroundOwusu‐Edusei, K., Marks, S. M., Miramontes, R., Stockbridge, E. L., & Winston, C. A. (2017) · The International Journal of Tuberculosis and Lung Disease · doi:10.5588/ijtld.16.0587 · Cited by 7
“16,17 19 To reduce the potential problem of high multi-collinearity, which can affect the magnitude and therefore the interpretation of the estimated coefficients of the control variables, 20 we checked the variance inflation factor (VIF < 10) and condition number (<15) based on Belsley et al.’s…”
Monfared, A. A. T., Han, D., Sheehy, O., Bexton, B., & LeLorier, J. (2005) · Current Medical Research and Opinion · doi:10.1185/030079906x80314 · Cited by 7
Stuttard, L., Hewitt, C. E., Fairhurst, C. M., Weatherly, H. L. A., Walker, S., Longo, F., Maddison, J., Boyle, P., & Beresford, B. (2020) · JMIR Research Protocols · doi:10.2196/15452 · Cited by 6
“A regression analysis will be undertaken to account for any baseline differences in study participants between the trial arms using appropriate techniques to account for non-normality of outcomes and costs data [45].”
MethodWassonguema, B., N’Diaye, D. S., Michel, M., Ngabirano, L., Frison, S., Ba, M., Siroma, F., Brizuela, A. V., Audibert, M., & Chevreul, K. (2024) · Nutrients · doi:10.3390/nu16142192 · Cited by 6
The Cost-Effectiveness of the SMART Work & Life Intervention for Reducing Sitting Time
Cox, E., Walker, S., Edwardson, C. L., Biddle, S., Clarke-Cornwell, A. M., Clemes, S. A., Davies, M. J., Dunstan, D. W., Eborall, H., Granat, M. H., et al. (2022) · International Journal of Environmental Research and Public Health · doi:10.3390/ijerph192214861 · Cited by 6
“Costing and absenteeism regressions used a log-link transformation and gamma family form to account for the bounded right-skewed nature of the dependant variable [37].”
MethodMohiuddin, S., Hollingworth, W., Glynn, J., Jones, T., Johnson, L., Potter, S., Brighter Study Group, Holcombe, C., O’Donoghue, J. M., Browne, J. P., et al. (2023) · British journal of surgery · doi:10.1093/bjs/znad149 · Cited by 6
Ngo, L., Denman, R. A., Hay, K. E., Kaambwa, B., Ganesan, A. N., & Ranasinghe, I. (2023) · Journal of the American Heart Association · doi:10.1161/jaha.123.030236 · Cited by 6
Publication Patterns of Cancer Cost-Effectiveness Studies Presented at Major Conferences
Chan, K., Siu, E., Mozessohn, L., & Cheung, M. C. (2013) · Current Oncology · doi:10.3747/co.20.1438 · Cited by 6
John‐Baptiste, A., Li, L., Isaranuwatchai, W., Osuch, E. A., & Anderson, K. K. (2019) · Early Intervention in Psychiatry · doi:10.1111/eip.12790 · Cited by 6
“We tested the identity and log links, to determine the relationship between the mean cost and the cost distribution (Barber & Thompson, 2004).”
MethodCross‐sectional study of electrocardiographic pattern in healthy children resident at high altitude
Huicho, L., & Niermeyer, S. (2007) · American Journal of Physical Anthropology · doi:10.1002/ajpa.20563 · Cited by 6
O'Sullivan, C. (2011) · UCL Discovery (University College London) · Cited by 6
Cost-effectiveness of patient observation on cranial CT use with minor head trauma
Singh, S., Hearps, S. J. C., Nishijima, D. K., Cheek, J. A., Borland, M. L., Dalziel, S. R., Holmes, J. F., Kuppermann, N., Babl, F. E., & Hoch, J. S. (2022) · Archives of Disease in Childhood · doi:10.1136/archdischild-2021-323701 · Cited by 5
Baric, V. B., Yngve, M., Holmefur, M., Feldman, I., Wilder, J., Johansen, K., Klang, N., Lidström, H., & Borgestig, M. (2023) · BMC Public Health · doi:10.1186/s12889-023-17053-0 · Cited by 10
“QALYs will be analysed with general regression model (GLM) [48], which allows for the control of confounders and adjustments to baseline.”
MethodSun, C., Jia, Y., Li, H., Qiao, X., Tang, M., Geng, M., Jones, E., Pike, J., Unsworth, M., & Hu, M. (2024) · Scientific Reports · doi:10.1038/s41598-024-64713-1 · Cited by 6
“Generalized linear models (GLMs) with log link and gamma distribution 20 were used to model the association between current EDSS score and costs adjusting for age and sex.”
Davies, E., Lüchtenborg, M., Hunter, R. M., Visser, R., Huynh, J., Pow, R., Plugge, E., Taylor, R. M., & Armes, J. (2025) · Health and Social Care Delivery Research · doi:10.3310/hyrt9622 · Cited by 5
Oncology Patients Are High Cost Outliers in Total Joint Replacement Bundled Payment Systems
Woelber, E., Gundle, K. R., Geddes, J., Schabel, K., Hayden, J. B., Hasan, S. R., Raymond, L. M., & Doung, Y.-C. (2019) · The Journal of Arthroplasty · doi:10.1016/j.arth.2019.08.030 · Cited by 5
Costs of postoperative morbidity following paediatric cardiac surgery: observational study
Hudson, E., Brown, K., Pagel, C., Wray, J., Barron, D. J., Rodrigues, W., Stoica, S. C., Tibby, S. M., Tsang, V. T., Ridout, D. A., et al. (2020) · Archives of Disease in Childhood · doi:10.1136/archdischild-2019-318499 · Cited by 5
Pal, S. S., Paul, S., & Dey, R. (2022) · IJARCCE · doi:10.17148/ijarcce.2022.11340 · Cited by 5
Metadata
- Authors
- Barber, J., & Thompson, S.
- Affiliations
- University College London (GB)
- MRC Biostatistics Unit (GB)
- Venue
- Journal of Health Services Research & Policy
- Publisher
- SAGE Publications
- Published
- 2004-10-02
- Volume
- 9
- Issue
- 4
- Pages
- 197-204
- ISSN
- 1355-8196 (ISSN-L)
- 1758-1060
- OpenAlex
- W1996146145
- Cited by
- 404
- References
- 20
- Citations by year
- 2026: 11 · 2025: 11 · 2024: 17 · 2023: 18 · 2022: 27 · 2021: 29 · 2020: 32 · 2019: 29 · 2018: 32 · 2017: 28 · 2016: 28 · 2015: 23 · 2014: 22 · 2013: 17 · 2012: 20
- FWCI
- 7.09
- Type
- journal article
- Language
- en
- Open access
- closed
- Locations
- Journal of Health Services Research & Policy (publishedVersion)
- PubMed (publishedVersion)
- UCL Discovery (University College London) (submittedVersion)
- Topics
- Physical Sciences › Mathematics › Statistics and Probability › Statistical Methods and Bayesian Inference
- Social Sciences › Economics, Econometrics and Finance › Economics and Econometrics › Health Systems, Economic Evaluations, Quality of Life
- Physical Sciences › Mathematics › Statistics and Probability › Statistical Methods in Clinical Trials
- Keywords
- cost data, generalized linear models, skewed distributions, gamma distribution, inverse Gaussian distribution, log link function, treatment effects, baseline covariate adjustment, model selection criteria
- MeSH terms
- Costs and Cost Analysis, United Kingdom, Health Services Research, Normal Distribution, Linear Models
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