Using propensity score with Receiver Operating Characteristics (ROC) and bootstrap to evaluate effect size in observational studies

Górkiewicz, M.

Artykuł - szczegóły

Tytuł artykułu

Using propensity score with Receiver Operating Characteristics (ROC) and bootstrap to evaluate effect size in observational studies

Autorzy

Górkiewicz M.

Wybrane pełne teksty z tego czasopisma

Identyfikatory

Warianty tytułu

Języki publikacji

Abstrakty

In non-randomised studies, prioritisation of patients who are most likely to benefit from more expensive and more effective treatments usually take place and/or patients select themselves to treatments. Propensity score methods have been considered as means to reduce the effect of selection bias. In this study it was shown that use of receiver operating characteristics (ROC) and area under ROC (AUC) provides an additional insight into analysis of non-randomised studies. The estimates of mean effect obtained with five different techniques were compared and nonparametric bootstrap was recommended as superior tool for propensity score analyses.

Słowa kluczowe

effect size non-randomised study propensity score bootstrap online calculator

wielkość efektu ładowanie początkowe kalkulator on-line

Wydawca

Nałęcz Institute of Biocybernetics and Biomedical Engineering of the Polish Academy of Sciences
Elsevier

Czasopismo

Biocybernetics and Biomedical Engineering

Rocznik

2009

Tom

Vol. 29, no. 4

Strony

41--61

Opis fizyczny

Bibliogr. 49 poz., tab.

Twórcy

autor

Górkiewicz M.

Jagiellonian University in Krakow, Health Sciences Faculty, Departament of Epidemiology and Population Research, ul. Grzegórzecka 20, 31-531 Kraków, Poland, gorkiewicz@poczta.fm

Bibliografia

1. Rosenbaum P.R., Rubin D.B.: The central role of the propensity score in observational studies for causal effects. Biometrika 1983, 70, 1, 41–55.
2. Tannen R.L., Weiner M.G., Xie D.: Use of primary care electronic medical record database in drug efficacy research on cardiovascular outcomes: comparison of database and randomised controlled trial findings. BMJ 2009;338:b81, [Accessed 2009, Jul 14].
3. Furlan A.D., Tomlinson G., Jadad A.A., Bombardier C.: Methodological quality and homogeneity influenced agreement between randomised trials and nonrandomized studies of the same intervention for back pain. J. Clin. Epidemiol. 2008, 61(3), 209–231.
4. Senn S., Graf E., Caputo A.: Stratification for the propensity score compared with linear regression techniques to assess the effect of treatment or exposure. Statistics in Medicine 2007, 26, 30, 5529–5544.
5. Kurth T., Walker A.M., Glynn R.J., Chan K.A., Gaziano J.M., Berger K., Robins J.M.: Results of Multivariate Logistic Regression, Propensity matching, Propensity Adjustment, and Propensity-based Weighting under Conditions of Nonuniform Effect. Am. J. Epidemiol. 2006, 163, 262–270.
6. Shrier I., Bolvin J.F., Steele R.J., Platt R.W., Furian A., Kakuma R., Brophy J., Rossignol M.: Should Meta-Analyses of Interventions Include Observational Studies in Addition to Randomized Controlled Trials? A Critical Examination of Underlying Principles. Am. J. of Epidemiol. 2007, 166, 1203–1209.
7. West S.G., Duan N., Pequegnat W., Gaist P., Jarlais C., Holtgrave D., Szapocznik J., Fishbein M., Rapkin B., Clatts M., Mullen P.D.: Alternatives to Randomized Controlled Trials. Am. J. Public Helth 2008, 98, 8, 1359–1366.
8. Parker R.I.: Increased Reliability for Single-Case Research Results: Is the Bootstrap the Answer? Behavior Therapy 2006, 17, 326–338.
9. Kelley K.: The Effects of Nonnormal Distributions on Confidence Intervals Around the Standarized Mean Difference: Bootstrapping as an Alternative to Parametric Confidence Intervals. Educational and Psychological Measurement 2005, 65, 51–69.
10. Tu W., Zhou X.H: A Bootstrap Confidence Interval Procedure for the Treatment Effect Using Propensity Score Subclassification. Health Services & Outcomes Research Methodology 2002, 3,135–147.
11. Stürmer T., Joshi M., Glynn R.J., Avorn J., Rothmann K.J., Schneeweiss S.: A review of the application of propensity score methods yielded increasing use, advantages in specific settings, but not substantially different estimates compared with conventional multivariate methods. J. Clinical Epidemiol. 2006, 59, 5, 437–461.
12. Kunz R., Vist G., Oxman A.D.: Randomisation to protect against selection bias in healthcare trials. BMC Med. Res Methodol. 2005, 2, 5(1),10.
13. Deeks J.J., Dinnes J., D’Amico R.A., Sowden A.J., Sakarovitch C., Song F., Petticrew M., Altman D.G.: Evaluating non-randomised intervention studies. Health Technol Assess 2003;7:1–173. [Medline], full text available online: URL_http://www.hta.ac.uk/1117 [Accessed 2009, Jul 14].
14. Brookhart M.A., Schneeweiss S., Rothman K.J., Glynn R.J., Avorn J., Stürmer T.: Variable Selection for Propensity Score Models. Am. J. Epidemiol. 2006, 163, 1149–1156.
15. Redelmeier D.A.: The Cognitive Psychology of Missed Diagnoses. Annals of Internal Medicine 2005, 142(2), 115–120.
16. Roberts R., Goodwin P.: Weight approximations in multi-attribute decision models. J of Multi-Criteria Decision Analysis 2002, 11(6), 292–303.
17. Reid M.C., Lane D.A., Feinstein A.R.: Academic Calculations versus Clinical Judgments: Practicing Physicians’ Use of Quantitative Measures of Test Accuracy. Am. J. Medicine 1996, 104(4), 374–380.
18. Stürmer T., Schneeweiss S., Rothmann K.J., Avorn J, Glynn R.J.: Performance of Propensity Score Calibration – A Simulation Study. Am. J. Epidemiol. 2007, 165, 1110–1118.
19. Zou G.: Quantifying responsiveness of quality of life measures without an external criterion. Quality of Life Research 2005, 14(6), 1545–1552.
20. Zhou X.H., Castellucio P., Zhou C.: Nonparametric Estimation of ROC Curves in the Absence of a Gold Standard. Biometrics 2005, 6, 600–609.
21. Górkiewicz M., Ciszek E., Szczygieł A.: Selecting experts and classifying features with procedure of repeated arrangements to classes of similarity, In: J. Wywiał (Ed.), Metoda Reprezentacyjna w Badaniach Ekonomiczno-Społecznych, University of Economics in Katowice 2004, 195–215 [in Polish].
22. Goldstone R.L., Medin D.L., Halberstadt J.: Similarity in Context. 2003, On-line: http:// cognitrn. psych.indiana.edu/rgoldsto/context/context.html [Accessed 2009, Jul 14].
23. Szczygieł A., Ciszek E., Górkiewicz M.: Visual inspection of the osteoporosis functional disability using rescaled standard anatomical pictures. Annales Academiae Medicae Bialostocensis 2005, 50 (Suppl.2), 75–77 URL_ http://www.advms.pl/node/84 [Accessed 2009, Jul 14, by menu options: Supplements / Supplement 2, Vol. 50].
24. Cook A.: Using video to include the experiences of people with dementia in research. Research Policy and Planning 2003 21, 23–32.
25. Walewska E., Ścisło L., Górkiewicz M., Czupryna A., Kłęk S., Szczepanik A.M., Kulig J.: Usefulness of guidelines for nutrition screening at patients with gastric cancer. Ann. Univ. Mariae Curie-Sklodowska, Sect. D, Med. 2005, suppl. 16 (6), 152–156, [in Polish].
26. Pezzullo J.C., Sullivan K.M.: Logistic Regression. available online: URL_ http://statpages.org/logistic. html [Accessed 2009, Jul 14].
27. Filippone M., Camastra F., Masulli F., Rovetta S.: A survey of kernel and spectral methods for clustering. Pattern Recognition 2008, 41(1), 176–190.
28. Mak T.K.: Estimating variances for all sample sizes by the bootstrap. Computational Statistics and Data Analysis 2004, 46, 459–467.
29. Bartkowiak A.: Robust Mahalanobis Distances Obtained Using the ‘Multout’ and ‘Fast-med’ Methods. Biocybernetics and Biomedical Engineering 2005, 25(1), 7–21.
30. Hutson A.D.: A semiparametric bootstrap approach to correlated data analysis problems. Computer Methods and Programs in Biomedicine 2004, 73, 129–134.
31. Górkiewicz M.: Multivariable ROCs: for separating planes, voting rules and decision trees. In: L. Bobrowski, J. Doroszewski, C. Kulikowski, N. Victor (Eds.), Statistics and Clinical Practice, Lecture Notes of ICB Seminars, vol. 70: Warsaw 2005, 95–102.
32. Rossa A.: The goodnes-of-fit tests for ROC curves, In: L. Bobrowski, J. Doroszewski, C. Kulikowski, N. Victor (Eds.), Statistics and Clinical Practice, Lecture Notes of ICB Seminars, vol. 70: Warsaw 2005 , 42–47.
33. Hanley J.A., McNeil B.J: The meaning and use of the area under a receiver operating characteristic (ROC) curve. Radiology 1982, 143, 29–36.
34. Hall P., Hyndman R.J., Fan Y.: Nonparametric confidence intervals for receiver operating characteristic curves. Biometrika 2004, 91 (3), 743–750.
35. Mossman D.: Resampling techniques in the analysis of non-normal ROC data. Medical Decision Making 1995, 15, 358–366.
36. Galea S., Tracy M.: Participation Rates in Epidemiologic Studies. Ann. Epidemiol. 2007, 17, 643–653.
37. Owen A.: The ethics of two- and one-sided hypothesis tests for clinical trials. Clinical Ethics 2007, 2(2), 100–102.
38. von Elm E., Altman D.G., Egger M., Pocock S.J., Gotzsche P.C., Vandenbroucke J.P.: The Strengthening the Reporting of Observational Studies in Epidemiology (STROBE) Statement: Guidelines for Reporting Observational Studies. PLoS Med. 4 (10), 2007, e296 URL_http://medicine.plosjournals. org/perlserv/ URL_http://www.strobe-statement.org/ [Accessed 2009, Jul 14].
39. Górkiewicz M.: Observational studies: using propensity score with receiver operating characteristics and bootstrap., in: Balcerar-Nicolau H, Bobrowski L, Doroszewski J, Kulikowski C. (eds). Lecture Notes of the VII-th ICB Seminar: Statistics and Clinical Practice, Warszawa 2008: 68–74.
40. Chmiel I., Czupryna A., Górkiewicz M., Brzostek T.: The causes of acute pancreatitis and the range of psychoeducational intervention for convalescens. Studia Medyczne, 2008, 11, 51–56 [in Polish].
41. Basu A.: How to Conduct a Meta-Analysis, 2005, Available On-line: URL_http://www.pitt.edu/~-super1/lecture/lec1171/008.htm.
42. Chang A: Meta-analysis using Mean Difference, 2000. Available On-line: URL_http://department. obg.cuhk.edu.hk/researchsupport/MetaMeans.asp [Accessed 2009, Jul 14, by menu options: Stats toolbox / Statistical tests / Meta-Analysis].
43. Wood M.: The Role of Simulation Approaches in Statistics. J. of Statistics Education 2005, 13, 3 available on-line URL_www.amstat.org/publications/jse/v13n3/wood.html [Accessed 2009, Jul 14].
44. Aksenov S: Confidence Intervals by Bootstrap. Wolfram Research Inc. 2002, available on-line: URL_http://library.wolfram.com/infocenter/MathSource/4272/ [Accessed 2009, Jul 14].
45. Siniksaran R.: BootStrapPackage: A Package of Bootstrap Algorithms for Mean, Simple Linear Regression Models, and Correlation Coefficient. Wolfram Research Inc. 2001, URL_http://library. wolfram.com/infocenter/MathSource/815/ [Accessed 2009, Jul 14.
46. Glasziou P., Chalmers I., Rawlins M., McCulloch P.: When are randomised trials unnecessary? Picking signal from noise. BMJ, 2007 334(7589), 349–351.
47. Chan C.W.: Psychoeducational intervention, a critical review of systematic analyses. Clinical Effectiveness in Nursing, 2005, 9, 101–111.
48. Rosochacka W., Górkiewicz M.: Forgotten duties: universities should be anxious for students’ learning styles. Annales Academiae Medicae Bialostocensis 2005, 50 (Suppl.2), 59–60 URL_ http://www.advms.pl/node/84 [Accessed 2009, Jul 14, by menu options: Supplements / Supplement 2, Vol. 50].
49. Eldridge S., Ashby D., Bennett C., Wakelin M., Feder G.: Internal and external validity of cluster randomised trials: systematic review of recent trials. BMJ, 2008, 336(7649), 876–880.

Typ dokumentu

Bibliografia

Identyfikator YADDA

bwmeta1.element.baztech-article-BPZ1-0059-0003