Adequate sample size for developing prediction models is not simply related to events per variable

Journal of Clinical Epidemiology

Volumn 76, Issue , 2016, Pages 175-182

  Ogundimu, Emmanuel O ^a   Altman, Douglas G ^a   Collins, Gary S ^a  

^a UNIVERSITY OF OXFORD   (United Kingdom)

Author keywords

Cox model; Events per variable; External validation; Predictive modeling; Resampling study; Sample size

Indexed keywords

ACCURACY; ADULT; ARTICLE; CLINICAL PRACTICE; EVENTS PER VARIABLE; EXTERNAL VALIDITY; FEMALE; GENERAL PRACTICE; HEURISTICS; HUMAN; MAJOR CLINICAL STUDY; MALE; MEDICAL RECORD; MIDDLE AGED; MONTE CARLO METHOD; PREDICTION; PREVALENCE; PRIORITY JOURNAL; PROPORTIONAL HAZARDS MODEL; SAMPLE SIZE; STATISTICAL MODEL; BAYES THEOREM; FORECASTING; MEDICAL RESEARCH; METHODOLOGY; PATIENT SELECTION; PROCEDURES; REGRESSION ANALYSIS; STATISTICS AND NUMERICAL DATA;

ADULT; BAYES THEOREM; BIOMEDICAL RESEARCH; FEMALE; FORECASTING; HUMANS; LOGISTIC MODELS; MALE; MIDDLE AGED; PATIENT SELECTION; PROPORTIONAL HAZARDS MODELS; REGRESSION ANALYSIS; RESEARCH DESIGN; SAMPLE SIZE;

EID: 84962074698     PISSN: 08954356     EISSN: 18785921     Source Type: Journal    
DOI: 10.1016/j.jclinepi.2016.02.031     Document Type: Article

References (18)

1. [1] Concato, J., Peduzzi, P., Holford, T., Feinstein, A., The importance of events per independent variable in proportional hazards regression analysis: I. Background, goals and general strategy. J Clin Epidemiol 48 (1995), 1495–1501.
2. [2] Harrell, F., Lee, K., Matchar, D., Reichert, T., Regression models for prognostic prediction: advantages, problems, and suggested solutions. Cancer Treat Rep 69 (1985), 1071–1077.
3. [3] Peduzzi, P., Concato, J., Feinstein, A., Holford, T., The importance of events per independent variable in proportional hazards regression analysis: II. Accuracy and precision of regression estimates. J Clin Epidemiol 48 (1995), 1503–1510.
4. [4] Peduzzi, P., Concato, J., Kemper, E., Holford, T.R., Feinstein, A., A simulation study on the number of events per variable in logistic regression analysis. J Clin Epidemiol 49 (1996), 1373–1379.
5. [5] Vittinghoff, E., McCulloch, C.E., Relaxing the rule of ten events per variable in logistic and Cox regression. Am J Epidemiol 165 (2007), 710–718.
6. [6] Courvoisier, D.S., Combescure, C., Agoritsas, T., Gayet-Ageron, A., Perneger, T.V., Performance of logistic regression modeling: beyond the number of events per variable, the role of data structure. J Clin Epidemiol 64 (2011), 993–1000.
7. [7] Steyerberg, E.W., Schemper, M., Harrell, F.E., Logistic regression modeling and the number of events per variable: selection bias dominates. J Clin Epidemiol 64 (2011), 1463–1469.
8. [8] Steyerberg, E.W., Eijkemans, M.J.C., Habbema, J.F., Stepwise selection in small data sets: a simulation study of bias in logistic regression analysis. J Clin Epidemiol 52 (1999), 935–942.
9. [9] Albert, A., Anderson, J.A., On the existence of maximum likelihood estimates in logistic regression. Biometrika 71 (1984), 1–10.
10. [10] Heinze, G., Schemper, M., A solution to the problem of separation in logistic regression. Stat Med 21 (2002), 2409–2419.
11. [11] Heinze, G., Schempe, M., A solution to problem of monotone likelihood in Cox regression. Biometrics 57 (2001), 114–119.
12. [12] Firth, D., Bias reduction of maximum likelihood estimates. Biometrika 80 (1993), 27–38.
13. [13] Burton, A., Altman, D.G., Royston, P., Holder, R.L., The design of simulation studies in medical statistics. Stat Med 25 (2006), 4279–4292.
14. [14] Royston, P., Sauerbrei, W., A new measure of prognostic separation in survival data. Stat Med 23 (2004), 723–748.
15. [15] O'Quigley, J., Xu, R., Stare, J., Explained randomness in proportional hazards models. Stat Med 24 (2005), 479–489.
16. [16] Ambler, G., Seaman, S., Omar, R.Z., An evaluation of penalised survival methods for developing prognostic models with rare events. Stat Med 31 (2012), 1150–1161.
17. [17] Lin, I.F., Chang, W.P., Liao, Y.N., Shrinkage methods enhanced the accuracy of parameter estimation using Cox models with small number of events. J Clin Epidemiol 66 (2013), 743–751.
18. [18] Heinze, G., Letter to the editor: a comparative study of the bias corrected estimates in logistic regression. Stat Methods Med Res 21 (2012), 660–661.