摘要
目的本次研究拟验证发表时间顺序与发表偏倚的关系这一假设,将发表时间顺序引入发表偏倚的诊断过程中,利用Meta分析中各独立研究的发表时间顺序和效应尺度信息构建一种新的基于发表时间顺序的发表偏倚诊断方法(简称时序法),通过有偏和无偏Meta分析研究模拟数据及从文献中获得的Meta分析实际数据,对时序法和传统方法的诊断准确度和诊断一致性进行评价,并提出最佳的联合诊断方案。
方法本次研究构建的时序法以效应尺度-发表时间顺序散点图、按发表时间顺序排列的效应尺度序列的游程总数和效应尺度-发表时间顺序回归模型来诊断发表偏倚是否存在。
利用有偏和无偏Meta分析研究模拟数据,依据在保证一定的特异度水平的条件下,灵敏度处于可接受水平的原则,确定游程总数法诊断发表偏倚的参考界值范围；利用有偏和无偏Meta分析研究模拟数据计算时序法和传统方法诊断发表偏倚的灵敏度和特异度,评价时序法的诊断准确度。利用Meta分析研究模拟数据和实际发表的文献数据,采用Kappa指数及其95%可信区间评价时序法与传统方法以及两种时序法之间的诊断一致性。利用Meta分析研究模拟数据,观察时序法和传统方法以及两种时序法之间的联合诊断(并联)发表偏倚的准确度,评价联合诊断的效果并从中选择最佳的时序法和传统方法的联合诊断方案。
使用SAS8.2软件编写时序法和传统方法的宏程序,并应用于Meta分析的实例研究。
本次研究利用Matlab7.0软件产生Meta分析模拟数据,以Monte Carlo法估计灵敏度和特异度,经预模拟研究,确定模拟次数为1000次,不同参数设置条件下的随机种子数不同。假设检验水准设置为0.20。
结果研究发现,时序法(游程总数法和回归模型法)诊断发表偏倚的灵敏度较低,特异度尚可；游程总数法的灵敏度和特异度低于回归模型法；未加权回归模型法的灵敏度高于加权回归模型法,特异度则低于加权回归模型法；时序法的灵敏度普遍低于传统方法(Egger回归法和Begg秩相关法),而两者间的特异度则是互有高低,比较相近；时序法与传统方法的诊断准确度可能与Meta分析研究的总体效应量大小有关,当总体效应量接近于0时,各方法的诊断发表偏倚的灵敏度较低；总体效应量从小到大变化时,各方法诊断发表偏倚的灵敏度呈现先增大后减小的趋势,而特异度基本相等；回归模型法与传统方法的诊断准确度可能与Meta分析研究中子研究的个数有关,子研究个数越多,各方法的灵敏度越大,特异度则越小；时序法和传统方法诊断一致性差,游程总数法和回归模型法对发表偏倚的诊断一致性相对较好,但其一致性程度(Kappa指数)依然处于较低水平；时序法与传统方法间联合诊断(并联)的灵敏度普遍高于传统方法间联合诊断的灵敏度,时序法和传统方法的联合诊断具有较理想的灵敏度和特异度,以加权回归模型法和Begg秩相关法的联合诊断效果最佳；游程总数法和回归模型法的联合诊断效果稍差于时序法和传统方法的联合诊断；应用SAS系统语言编写的包含了时序法和传统方法的发表偏倚诊断宏程序的运行结果与常用软件一致,方便了时序法的推广应用；Meta分析的实例研究发现,对于包含较多子研究个数的Meta分析,回归模型法与传统方法结论基本一致,而子研究个数较少时,回归模型法相对于传统方法更为灵敏。本次Meta分析实例研究的子研究个数较少,而其游程总数都比较大,游程总数法提示可能存在发表偏倚。
结论时序法与传统方法具有相似的诊断准确度,因其具有与传统方法完全不同的理论基础,所以该方法有特殊的应用价值和前景,特别是与传统方法进行发表偏倚的联合诊断。时序法中的加权回归模型法与Begg秩相关法的并联联合诊断方案具有相对较好的灵敏度,且其特异度也处于较高水平,是较理想的一种联合诊断方案。
创新提出了一种新的基于发表时间顺序的发表偏倚诊断方法——时序法；提出了一种产生包含发表时间顺序的无偏和有偏Meta分析模拟数据的方法；提出了时序法(游程总数法和回归模型法)和传统发表偏倚诊断方法(Egger回归法和Begg秩相关法)的联合诊断方案。
Objectives To validate the hypothesis that the publication bias is associated with the sequence of publication date, we used the effect size of substudy in Meta-analysis and the sequence of publication date to construct a new method to detect publication bias, then evaluated the accuracy to detect the publication bias of the new method and the consistency of detecting the publication bias for new and traditional methods and put forward the combined diagnosis project of the new and traditional methods to detect the publication bias. Because the new method to detect publication bias is associated with publication date, so we named this new method "the method based on the sequence of publication date".
Methods The new method to diagnose publication bias comprises the effect size-the sequence of publication date scatterplot, the total runs of the sequence of effect size sorted by publication date and the effect size-the sequence of publication date linear model.
Using the simulated Meta-analysis data being of publication bias and the simulated Meta-analysis data being of no publication bias, the two-side reference interval of the total runs diagnosing publication bias for the method of the total runs was determined according to the principle that the sensitivity to detect publication bias comes to acceptable level and the specificity to detect publication bias reaches to a high level simultaneously; using the simulated Meta-analysis data being of publication bias and the simulated Meta-analysis data being of no publication bias, the sensitivity and specificity of new method and traditional method to detect publication bias were calculated. Afterward, we compared the accuracy of new method with traditional method; using the simulated and published Meta-analysis data, the consistency of detecting the publication bias for new and traditional methods were examined with the kappa index and its 95% confidence interval (CI); using the simulated meta-analysis data, the accuracy of combined diagnosis project (in parallel) with new methods and traditional methods was discussed. According to the accuracy of combined diagnosis project, then the optimal combined diagnosis project with new method and traditional method was put forward.
The macro of new methods and traditional methods was written with Statistical Analysis System (SAS) language and carried out in one published Meta-analysis. The macro could output the results of new methods and traditional methods in report forms.
The simulated Meta-analysis data were generated by means of Matlab7.0. This study employed the method of Monte Carlo to estimate the accuracy of the new methods and traditional methods to detect publication bias in simulated Meta-analysis for each combination of parameters which was set when generating the simulated Meta-analysis data. According to the pilot simulation study, simulation repeated 1000 times in each different combination of parameters. Simulation was based on different random seed in different combination of parameters. The significant level of hypothesis test was at 0.2.
Results The sensitivity to detect the publication bias of the new method based on the sequence of publication date (the method of the total runs and the method of effect size-the sequence of publication date linear model) was low and the specificity to detect the publication bias of the new method was acceptable; the accuracy of the method of the total runs was less than the accuracy of the method of effect size-the sequence of publication date linear model; the sensitivity of the method of unweighted linear model was more than the sensitivity of the methods of weighted linear model, however, the specificity of the method of unweighted linear model was less than the specificity of the method of weighted linear model; the sensitivity of the new method based on the sequence of publication date was less than the sensitivity of the traditional method (Egger's method and Begg's method), but the specificity of the new methods based on the sequence of publication date was not less than the sensitivity of the traditional method; when the population effect size (SMD or ln(OR)) approximated to zero, then the sensitivity of all methods was low, but when the population effect size increased, the sensitivity of all methods increased early and decreased latter and the specificity of all methods immobilized. That is, the accuracy of all methods might relate to the magnitude of the population effect size; when the number of the substudy of Meta-analysis increased, the sensitivity of all methods, except for the method of the total runs, increased and the specificity decreased. That is, the accuracy of all methods might be associated with the number of substudy of Meta-analysis; the consistency for new method and traditional method based on different theories was low; the consistency for the two new methods was still low (the Kappa index was small), but the consistency for the two new methods was better than the consistency for new method and traditional method; the sensitivity of combined diagnosis with new method and traditional method in parallel was more than the sensitivity of combined diagnosis with two traditional methods (Egger's method and Begg's method) in parallel; when the new method and the traditional method were combined in parallel, the sensitivity of the project of combined diagnosis increased, however, the specificity did not decrease obviously; among all projects of combined diagnosis of new method and traditional method, the project of the method of weighted linear model and the Begg's method was optimal; the sensitivity of the project of combined diagnosis of the two new methods was acceptable, but the specificity was small compared to the project of combined diagnosis of the new method and the traditional method; the macro of the new method and the traditional method was written with SAS language and its output was identical to the output of the software in common use (STATA), therefore, the macro made the new method and the traditional method applied conveniently. When the new method and traditional method to detect publication bias were applied to the published Meta-analysis, we found that the results of the method of the linear model were similar to the results of the traditional method for the Meta-analysis with large number of substudy, however, the sensitivity of the method of the linear model was better than the sensitivity of the traditional method for the Meta-analysis with small number of substudy. Because of the magnitude of the total runs was large when the number of substudy in published Meta-analysis was small, the method of the total runs indicated that there might be the publication bias in this published Meta-analysis.
Conclusions The accuracy of the new method based on the sequence of the publication date was similar to the traditional method. Because the theories behind the new method and the traditional method were different, therefore, the new method had the special application value and prospects for planning out the project of combined diagnosis with the traditional method in parallel. In all projects of combined diagnosis of the new method and the traditional method, the sensitivity of the project of combined diagnosis of the method of weighted linear model and the Begg's method was acceptable and the specificity reached to a high level, therefore, this project was regarded as an optimal project.
Innovations A new method based on publication date to diagnose publication bias was advanced; a method to generate simulated Meta-analysis data with the sequence of publication date was put forward; the optimal project of combined diagnosis with the new method (the method of the total runs and the method of effect size-the sequence of publication date linear model) and the traditional method (the Egger's method and Begg's method) was put forward.
引文
1. Fisher R. Statistical Methods for Research Workers.13th ed. New York:Hafner,1958.
2. Beecher HK. The powerful placebo. J Am Med Assoc,1955,159(17):1602-1606.
3. Glass GV. Primary, secondary, and meta-analysis of research. Educational Researcher,1976,5:3-8.
4. Evidence-Based Medicine Working Group. Evidence-based medicine. A new approach to teaching the practice of medicine. JAMA,1992,268 (17):2420-2425.
5. Light RJ, Pillemer DB. Summing Up:The Science of Reviewing Research. Cambridge MA: Harvard University Press,1984.
6. Egger M, Smith GD, Schneider M, et al. Bias in meta-analysis detected by a simple, graphical test. British Medical Journal Journal,1997,315:629-634.
7. Begg CB, Mazumdar M. Operating characteristics of a rank correlation test for publication bias. Biometrics,1994,50:1088-1101.
8. Macaskill P, Walter SD, Irwig L. A comparison of methods to detect publication bias in meta-analysis. Stat Med,2001,20:641-654.
9. Richy F, Reginster JY. A Simple Method For Detecting And Adjusting Meta-Analyses For Publication Bias. The Internet Journal of Epidemiology,2006,3(2).
10.李红颜.Meta分析中识别发表偏倚方法的比较.硕士学位论文.广州：南方医科大学图书馆,2007.
11. Hayashino Y, Noguchi Y, Fukui T. Systematic evaluation and comparison of statistical tests for publication bias. Journal of Epidemiology,2005,15(6):235-243.
12. Zhou XH, Obuchowski NA, McClish DK. Statistical Methods in Diagnostic Medicine. New York: Wiley,2002.
13. Pepe MS. The Statistical Evaluation of Medical Tests for Classification and Prediction. Oxford: Oxford University Press,2003.
14.宋艳艳.临床诊断试验.见赵耐青主编,临床医学研究设计和数据分析.上海：复旦大学出版社,2005.241-254.
15. Kromrey JD, Rendina-Gobioff G. On Knowing What We Do Not Know:An Empirical Compari-son of Methods to Detect Publication Bias in Meta-Analysis. Educational and Psychological Measurement,2006,66:357-373.
16. Begg CB, Berlin JA. Publication bias:A problem in interpreting medical data. Journal of the Royal Statistical Society Series A,1988,151(3):419-463.
17. Dickersin K, Scherer R, Lefebvre C. Identifying relevant studies for systematic reviews. British Medical Journal,1994,309(6964):1286-1291.
18. Dickersin K. How important is publication bias? A synthesis of available data. AIDS Educa-tion and Prevention,1997,9(1 Suppl):15-21.
19. Begg CB. Publication bias. In The Handbook of Research Synthesis, Cooper H, Hedges LV (eds). New York:Russell Sage Foundation,1994, Chapter 25.
20. Greenland S. Invited commentary:a critical look at some popular meta-analytic methods. Am J Epidemiol,1994,140:290-296.
21. Kendall MG A New Measure of Rank Correlation. Biometrika,1938,30(1-2):81-93.
22. Shi XQ, Zhou SH, Wang ZX, et al. CYP1A1 and GSTM1 polymorphisms and lung cancer risk in Chinese populations:A meta-analysis. Lung Cancer,2008,59:155-163.
23. Zhuo XG, Melby MK, Watanabe S. Soy Isoflavone Intake Lowers Serum LDL Cholesterol:A Meta-Analysis of 8 Randomized Controlled Trials in Humans. J Nutr,2004,134:2395-2400.
24. Easterbrook PJ, Berlin JA, Gopalan R, et al. Publication bias in clinical research. Lancet,1991, 337:867-872.
25. Sutton AJ, Duval SJ, Tweedie RL, et al. Empirical assessment of effect of publication bias on metaanalyses. BMJ,2000,320:1574-1577.
26. Pharoah PD, Dunning A, Ponder BA,et al. Association studies for finding cancer-susceptibility genetic variants. Nat Rev Cancer,2004,4:850-860.
27. Neumann AS, Sturgis EM, Wei QY. Nucleotide excision repair as a marker for susceptibility to tobacco-related cancers:a review of molecular epidemiological studies. Mol Carcinog,2005,42: 65-92.
28. Freedman ND, Leitzmann MF, Hollenbeck AR, et al. Cigarette smoking and subsequent risk of lung cancer in men and women:analysis of a prospective cohort study. Lancet Oncol,2008,9: 649-656.
29. Bandera EV, Freudenheim JL, Vena JE. Alcohol consumption and lung cancer:a review of the epidemiologic evidence. Cancer Epidemiol Biomarkers Prev,2001,10:813-821.
30. Armstrong B, Hutchinson E, Unwin J, et al. Lung cancer risk after exposure to polycyclic aroma-tic hydrocarbons:A review and meta-analysis. Environmental Health Perspectives,2004,112: 970-978.
31. Moulin JJ, Clavel T, Roy D, et al. Risk of lung cancer in workers producing stainless steel and metallic alloys. Int Arch Occup Environ Health,2000,73:171-180.
32. Vineis P, Husgafvel-Pursiainen K. Air pollution and cancer:biomarker studies in human populations. Carcinogenesis,2005,26:1846-1855.
33. Cleaver JE. Defective repair replication of DNA in xeroderma pigmentosum. Nature,1968,218: 652-656.
34. Caldecott KW, Tucker JD, Stanker LH, et al. Characterization of the XRCC1-DNA ligase Ⅲ complex in vitro and its absence from mutant hamster cells. Nucleic Acids Res,1995,23: 4836-4843.
35. Dianov GL, Prasad R, Wilson SH, et al. Role of DNA polymerase in the excision step of long patch mammalian base excision repair. J Biol Chem,1999,274:13741-13743.
36. Thompson LH, West MG. XRCC1 keeps DNA from getting stranded. Mutat Res,2000,459: 1-18.
37. Lunn RM, Langlois RG, Hsieh LL, et al. XRCC1 polymorphisms:effects on aflatoxin B1-DNA adducts and glycophorin A variant frequency. Cancer Res,1999,59:2557-2561.
38. Duell EJ, Wiencke JK, Cheng TJ, et al. Polymorphisms in the DNA repair genes XRCC1 and ERCC2 and biomarkers of DNA damage in human blood mononuclear cells. Carcinogenesis, 2000,21:965-971.
39. Matullo G, Guarrera S, Carturan S, et al. DNA repair gene polymorphisms, bulky DNA adducts in white blood cells and bladder cancer in a case-control study. Int J Cancer,2001,92:562-567.
40. Lei YC, Hwang SJ, Chang CC, et al. Effects on sister chromatid exchange frequency of polymorphisms in DNA repair gene XRCC1 in smokers. Mutat Res,2002,519:93-101.
41. Hsieh LL, Chien HT, Chen IH, et al. The XRCC1 399Gln polymorphism and the frequency of p53 mutations in Taiwanese oral squamous cell carcinomas. Cancer Epidemiol Biomarkers Prev, 2003,12:439-443.
42. Hu JJ, Smith TR, Miller MS, et al. Amino acid substitution variants of APE1 and XRCC1 genes associated with ionizing radiation sensitivity. Carcinogenesis,2001,22:917-922.
43. Taylor RM, Thistlethwaite A, Caldecott KW. Central role for the XRCC1 BRCT I domain in mammalian DNA single-strand break repair. Mol Cell Biol,2002,22:2556-2563.
44. Pastorelli R, Cerri A, Mezzetti M, et al. Effect of DNA repair gene poly-morphisms on BPDE-DNA adducts in human lymphocytes. Int J Cancer,2002,100:9-13.
45. Gao WM, Romkes M, Day RD, et al. Association of the DNA repair gene XPD Asp312Asn polymorphism with p53 gene mutations in tobacco-related non-small cell lung cancer. Carcinogenesis,2003,24:1671-1676.
46. Hou SM, Ryk C, Kannio A, et al. Influence of common XPD and XRCC1 variant alleles on p53 mutations in lung tumors. Environ Mol Mutagen,2003,41:37-42.
47. Wang Y, Spitz MR, Zhu Y, et al. From genotype to phenotype:correlating XRCC1 polymorphisms with mutagen sensitivity. DNA Repair,2003,2:901-908.
48. Berwick M, Vineis P. Markers of DNA repair and susceptibility to cancer in humans:an epidemiologic review. J Natl Cancer Inst,2000,92:874-897.
49. Lippman SM, Spitz MR. Lung cancer chemoprevention:an integrated approa-ch. J Clin Oncol, 2001,19:S74-82.
50. Wei Q, Cheng L, Amos CI, et al. Repair of tobacco carcinogen-induced DNA adducts and lung cancer risk:a molecular epidemiologic study. J Natl Cancer Inst,2000,92:1764-1772.
51. Wei Q, Cheng L, Hong WK, et al. Reduced DNA repair capacity in lung cancer patients. Cancer Res,1996,56:4103-4107.
52. Rajaee-Behbahani N, Schmezer P, Risch A, et al. Altered DNA repair capacity and bleomycin sensitivity as risk markers for non-small cell lung cancer. Int J Cancer,2001,95:86-91.
53. Kiyohara C, Takayama K, Nakanishi Y. Association of genetic polymorphisms in the base excision repair pathway with lung cancer risk:a meta-analysis. Lung Cancer,2006,54:267-283.
54. Chen S, Tang D, Xue K, et al. DNA repair gene XRCC1 and XPD poly-morphisms and risk of lung cancer in a Chinese population. Carcinogenesis,2002,23:1321-1325.
55.宋雅辉,尹立红,浦跃补,等.南京市人群DNA修复基因XRCC1多态性与肺癌易感性的关系.环境与职业医学,2004,21(1)：18-21.
56.李家伟,穆丽娜,卫国荣,等.DNA修复基因XRCC1多态性与肺癌易感性的关系.中国癌症杂志,2005,15(4)：335-338.
57.张文娟吴拥军吴逸明.XRCC1基因G28152A多态与肺癌风险的研究.癌变.畸变.突变,2005,17(2)：76-78.
58. Shen M, Berndt SI, Rothman N, et al. Polymorphisms in the DNA base exci-sion repair genes APEX1 and XRCC1 and lung cancer risk in Xuan Wei, China. Anticancer Res,2005,25: 537-542.
59.余红平,曾小云,仇小强,等.DNA修复基因XRCC1单核苷酸多态性与肺癌易感性.广西医科大学学报,2006,23(3)：355-358.
60. Yin JY, Vogel U, Ma YG, et al. The DNA repair gene XRCC1 and genetic susceptibility of lung cancer in a northeastern Chinese population. Lung Cancer,2007,56:153-160.
61. Li MC, Yin ZH, Guan P, et al. XRCC1 polymorphisms, cooking oil fume and lung cancer in Chinese women nonsmokers. Lung Cancer,2008,62(2):145-151. Epub 2008 Apr 14.
62. Hung RJ, Hall J, Brennan P, et al. Genetic polymorphisms in the base excision repair pathway and cancer risk:a HuGE review. Am J Epidemiol,2005,162:925-942.
63. Hu ZB, Ma HX, Chen F, et al. XRCC1 polymorphisms and cancer risk:a meta-analysis of 38 case-control studies. Cancer Epidemiol Biomarkers Prev,2005,14:1810-1818.
64. Ratnasinghe D, Yao SX, Tangrea JA, et al. Polymorphisms of the DNA repair gene XRCC1 and lung cancer risk. Cancer Epidemiol Biomarkers Prev,2001,10:119-123.
65. David-Beabes GL, London SJ. Genetic polymorphism of XRCC1 and lung cancer risk among African-Americans and Caucasians. Lung Cancer,2001,34:333-339.
1. Last JM, editor. A Dictionary of Epidemiology. Oxford:Oxford University Press,1983.12.
2. Smith MB. Editorial. J Abnorm Social Psychol,1956,52:1-4.
3. Sterling T. Publication decisions and their possible effects on inferences drawn from tests of significance-or vice versa. Am Stat Assoc J,1959,54:30-34.
4. Rosenthal R. The "file drawer problem" and tolerance for null results.Psychol Bull,1979,86: 638-641.
5. Smart RG The importance of negative results in psychological research. Can Psychol,1964,5: 225-232.
6. Chalmers I. Underreporting research is scientific misconduct. JAMA,1990,263:1405-1408.
7. Easterbrook PJ, Berlin JA, Gopalan R, et al. Publication bias inclinical research. Lancet,1991,337: 867-872.
8. Dwan K, Altman DG, Arnaiz JA, et al. Systematic review of the empirical evidence of study publication bias and outcome reporting bias. PLoS One,2008,28,3(8):e3081.
9. Tweedie RL, Scott DJ, Biggerstaff BJ, et al. Bayesian meta-analysis, with application to studies of ETS and lung cancer.Lung Cancer,1996,14(suppl.1):S171-194.
10. Decullier E, Lheritier V, Chapuis F. Fate of biomedical research protocols and publication bias in France:retrospective cohort study. BMJ,2005,331:19.
11. Dickersin K, Min YI. Publication bias:the problem that won't go away. Ann NY Acad Sci, 1993,703:135-146 [discussion 146-148].
12. Egger M, Smith GD. Misleading meta-analysis. BMJ,1995,310:752-754.
13. Rothstein HR. Publication bias as a threat to the validity of meta-analytic results J Exp Criminol,2008,4:61-81.
14.张博恒,赵耐青.Meta分析中的统计方法.见王吉耀主编.循证医学与临床实践(第二版).北京：科学出版社,2002.89-117.
15. Egger M, Davey Smith G, Altman DG Systematic reviews in health care:Meta-analysis incontext. London:BMJ Books,2000.
16. Hall R, de Antueno C, Webber A. Publication bias in the medical literature:a review by a Cana-dian Research Ethics Board. Can J Anaesth,2007,54(5):380-388.
17.史红,李静,包务业.医学研究中的发表偏倚问题.中华医学杂志,2001,81(14)：892-894.
18. Angell M. Negative studies. N Engl J Med,1989,321:464-466.
19. Felson DT. Bias in meta-analytic research. J Clin Epidemiol,1992,45:885-892.
20. Chalmers TC, Berrier J, Sacks HS, et al. Meta-analysis of clinical trials as a scientific discipline. I:Control of bias and comparison with large co-operative trials. Stat Med,1987,6:315-328.
21. Dickersin K. The existence of publication bias and risk factors for its occurrence. JAMA,1990, 263:1385-1389.
22. Kleijnen J, Knipschild P. Review articles and publication bias. Arzneimittel-forschung,1992,42: 587-91.
23. Minerva. Re publication bias. BMJ,1992,304:264.
24. Begg CB, Berlin JA. Publication bias:a problem in interpreting medical data. J R Stat Soc A, 1988,151:419-463.
25. Light RJ. Accumulating evidence from independent studies:what we can win and what we can lose. Stat Med,1987,6:221-231.
26. Begg CB. A measure to aid in the interpretation of published clinical trials. Stat Med,1985,4: 1-9.
27. Bulpitt CJ. Meta-analysis. Lancet,1988, ⅱ:93-94.
28. Pocock SJ, Hughes MD, Lee RJ. Statistical problems in the reportingof clinical trials:a survey of three medical journals. N Engl J Med,1987,317:426-432.
29. Lee PN. Problems in interpreting epidemiological data. In:Mohr U, Bates DV, Dungworth DL, et al, editors. Assessment of Inhalation Hazards. Berlin:Springer-Verlag,1989.49-50.
30. Newcombe RG Towards a reduction in publication bias. BMJ,1987,295:656-659.
31. LeVois ME, Layard MW. Publication bias in the environmental tobacco smoke/coronary heart disease epidemiologic literature. Regul Toxicol Pharmacol,1995,21:184-191.
32. Dickersin K, Min YI, Meinert CL.Factors influencing publication of research results. Follow-up of applications submitted to two institutional review boards. JAMA,1992,267(3):374-378.
33. Koren G, Shear H, Graham K, et al. Bias against the null hypothesis:the reproductive hazards of cocaine. Lancet,1989, ii:1440-1442.
34. Squitieri L, Petruska E, Chung KC. Publication Bias in Kienbock's Disease:Systematic Review.J Hand Surg Am,2010,5(3):359-367.
35. Charlton B. Think negative:science needs its failures. New Scientist,1987,29:72.
36. Mahoney MJ. Publication prejudices:an experimental study of confirmatory bias in the peer review system. Cog Ther Res,1977,1:161-175.
37. Moher D, Cook DJ, Eastwood S, et al. Improving the quality of reports of meta-analyses of randomised controlled trials:the QUOROM statement. Quality of Reporting of Meta-analyses.Lancet,1999,354(9193):1896-1900.
38.夏愔愔,詹思延.如何撰写高质量的流行病学研究论文第七讲随机对照试验Meta分析的 报告规范——QUOROM介绍.中华流行病学杂志,2007,28(6)：618-620.
39. Light RJ, Pillemer DB. Summing Up:The Science of Reviewing Research. Cambridge MA: Harvard University Press,1984.
40. LeVois ME, Layard MW. Publication bias in the environmental tobacco smoke/coronary heart disease epidemiologic literature. Regul Toxicol Pharmacol,1995,21:184-191.
41. Greenland S. Invited commentary:a critical look at some popular meta-analytic methods. Am J Epidemiol,1994,140:290-296.
42. Gregoire G, Derderian F, Le Lorier J. Selecting the language of the publications included in a meta-analysis:is there a Tower of Babel bias? J Clin Epidemiol,1995,48(1):159-163.
43. Egger M, Zellweger-Zahner T, Schneider M, et al. Language bias in randomised controlled trials published in English and German. Lancet,1997,350(9074):326-329.
44. Schulz KF, Chalmers I, Hayes RJ, et al. Empirical evidence of bias. Dimensions of methodology-cal quality associated with estimates of treatment effects in controlled trials. JAMA,1995,273 (5):408-412.
45. Moher D, Pham B, Jones A, et al. Does quality of reports of randomised trials affect estimates of intervention efficacy reported in meta-analyses? Lancet,1998,352(9128):609-613.
46. Stuck AE, Rubenstein LZ, Wieland D.Bias in meta-analysis detected by a simple, graphical test. Asymmetry detected in funnel plot was probably due to true heterogeneity. BMJ,1998,316(7129): 469.
47. Egger M, Davey Smith G, Schneider M, et al. Bias in meta-analysis detected by a simple, graphi-cal test. BMJ,1997,315(7109):629-634.
48. Begg CB, Mazumdar M. Operating characteristics of a rank correlation test for publication bias. Biometrics,1994,50:1088-1101.
49. Macaskill P, Walter SD, Irwig L. A comparison of methods to detect publication bias in meta-analysis. Stat Med,2001,20:641-654.
50.李红颜.Meta分析中识别发表偏倚方法的比较.硕士学位论文.广州：南方医科大学图书馆,2007.
51. Irwig L, Macaskill P, Berry G, et al. Bias in meta-analysis detected by a simple, graphical test. Graphical test is itself biased (Letter). British Medical Journal,1998,316(7129):470.
52. Draper NR, Smith H. Applied Regression Analysis,2nd edn. New York:Wiley,1981.
53. Agresti A. Categorical Data Analysis. New York:Wiley,1990.
54. Kendall MG A New Measure of Rank Correlation. Biometrika,1938,30(1-2):81-93.
55. Hayashino Y, Noguchi Y, Fukui T. Systematic evaluation and comparison of statistical tests for publication bias. Journal of Epidemiology,2005,15(6):235-243.
56. Persaud R. Misleading meta-analysis. "Fail safe N" is a useful mathematical measure of the stability of results. BMJ,1996,312(7023):125.
57. Evans S. Statistician's comment. BMJ,1996,312:125.
58.杨书,杨晓虹,刘新.发表性偏倚产生与识别方法的可行性论证.成都医学院学报,2008,3(2)：132-135.
59. Duval S, Tweedie R. A Nonparametric "Trim and Fill" Method of Accounting for Publication Bias in Meta-Analysis. Journal of the American Statistical Association,2000,95(449):89-98.
60. Duval S, Tweedie R. Trim and fill:A simple funnel-plot-based method of testing and adjusting for publication bias in meta-analysis. Biometrics,2000,56(2):455-463.
61. Richy F, Reginster JY. A Simple Method For Detecting And Adjusting Meta-Analyses For Publication Bias. The Internet Journal of Epidemiology,2006,3(2).
62. Dear KBG, Begg CB. An Approach for Assessing Publication Bias Prior to Performing a Meta-Analysis. Statistical Science,1992,7(2):237-245.
63. Gleser LJ, Olkin I. Models for estimating the number of unpublished studies. Stat Med,1996, 15(23):2493-2507.
64. Givens GH, Smith DD, Tweedie RL. Publication Bias in Meta-Analysis:A Bayesian Data-Augmentation Approach to Account for Issues Exemplified in the Passive Smoking Debate. Statistical Science,1997,12(4):221-240.
65. Spoor P, Airey M, Bennett C, et al. Use of the capture-recapture technique to evaluate the completeness of systematic literature searches. BMJ,1996,313:342-343.
66. Bennett DA, Latham NK, Stretton C, et al. Capture-recapture is a potentially useful method for assessing publication bias. J Clin Epidemiol,2004,57(4):349-357.
67. Begg CB. Publication bias. In:Cooper H, Hedges LV, editors. The Handbook of Research Synthesis. New York:Russell Sage Foundation,1994.399-409.
68. Hackshaw AK, Law MR, Wald NJ. The accumulated evidence on lung cancer and environmental tobacco smoke. BMJ,1997,315(7114):980-988.
69. Sugita M, Kanamori M, Izuno T, et al. Estimating a summarized odds ratio whilst eliminating publication bias in meta-analysis. Jpn J Clin Oncol,1992,22(5):354-358.