[目的/意义] 为解决学科评价中采用不同评价方法评价结果不一致问题,提出一种基于元分析的新的学科发展水平评价方法。[方法/过程] 以JCR光学期刊为例,选取7个文献计量学指标,首先对数据进行标准化,然后采用主成分分析、因子分析、TOPSIS、离散系数、熵权、层次分析进行评价,接着计算评价结果的均值以及前20%优秀期刊的均值,再对各种评价方法的均值进行偏倚检验,最后对所有的均值采用元分析进行整合。[结果/结论] 研究表明,采用元分析对学科发展水平进行评价是一种行之有效的方法,该方法可用于不同学科发展水平之间的比较。认为全部期刊与优秀期刊元分析均值之比可用来衡量同一学科发展水平之差距。
[Purpose/significance] This paper proposes an evaluation method of new disciplines' level of development based on meta-analysis. [Method/process] Taking optical JCR journals as examples and selecting seven indicators of bibliometrics, this paper standardizes the data firstly, and evaluates data by adopting the principal component analysis, factor analysis, TOPSIS, dispersion coefficient, entropy, analytic hierarchy process (AHP). Then, it calculates the mean of evaluation results and that of top 20% of excellent journals and has bias testing for the means of various evaluation methods. Finally, it integrates all means by using meta-analysis. [Result/conclusion] The result shows that adopting meta-analysis to evaluate the development level of subjects is an effective method that can be used for comparing the development levels between different disciplines. The ratio of meta-analysis mean in all journals and excellent journals can be used to measure the gap of the same disciplines' development level.
[1] MICHEL Z,RAHARY S R,COULARD E B.Relativity of citation performance and excellence measures:from cross-field to cross-scale effects of field- normalization[J]. Scientometrics,2005,63 (2) : 373-401.
[2] OPTHOF T, LEYSESDORFF L. Caveats for the journal and field normalizations in the CWTS("leiden")evaluations of research performance[J]. Journal of informetrics, 2010, 4(3): 423-430.
[3] GLANZEL W, THIJS B,SCHUBERT A, et al. Subfield-specific normalized relative indicators and a new generation of relational charts: methodological foundations illustrated on the assessment of institutional research performance[J]. Scientometrics,2009,78(1):165-188.
[4] 赵星,高小强,周春雷.h指数在人文社会学科中的评价表征能力:期刊视角的实证[J]. 情报学报,2010(12):1125-1131.
[5] 汪新红,王国红.学术期刊主要评价指标的学科差异性研究[J]. 科技与出版,2013(2):85-88.
[6] MOED H F,BRUIN R E D E. New bibliometric tools for the assessment of national research performance[J]. Scientometrics,1995,33(3):381-422.
[7] RADICCHIA F, FORTUNATO S, CASTELLANO C. Universality of citation distributions: toward an objective measure of scientific impact[J]. Proceedings of the National Academy of Sciences of the United States of America,2008,105 (45):17268-17272.
[8] BORNMANN L, DANIEL H. Universality of Citation Distributions——a validation of radicchi et al.'s relative indicator cf=c/c0 at the micro level using data from chemistry[J]. Journal of the American Society for Information Science and Technology,2009,60(8):1664-1670.
[9] 金晶,何苗,王孝宁,等. 不同学科领域自然科学论文学术影响力评价与比较的可行性研究[J]. 科技管理研究,2010(14):279-284.
[10] 方永才,吴光豪,陈雷. SCI期刊的学科分布及不同学科论文评价的探讨[J]. 浙江大学学报(农业与生命科学版),2004(1): 114-118.
[11] 俞立平,武夷山. 学术期刊评价中标准分与原始分的比较研究[J]. 情报学报,2011(11):1187-1193.
[12] 邱均平,楼雯. "985"大学世界一流学科建设成效研究[J]. 中国社会科学评价,2015(2):115-125.
[13] 张令伟. 基于"钻石模型"的高校艺术学学科竞争力综合评价模型研究[J]. 西南民族大学学报(社会科学版),2015(6):119-123.
[14] PEARSON K.Report on certain enteric fever inoculation statistics[J].British medicine journal,1904(3):1243-1246.
[15] GLASS G V. Primary,secondary and meta-analysis of research[J].Education research, 1976, 6(5): 38.
[16] EGGER M, SMITH G D, SCHNEIDER M, et al. Bias in meta-analysis detected by a simple, graphical test[J/OL].[2016-01-21].http://www.ncbi.nlm.nih.gov/pubmed/9310563?dopt=Abstract.
[17] BEGG C B, MARUMDAR M. Operating characteristics of a rank correlation test for publication bias[J]. Biometrics,1994, 50(4):1088-1101.
[18] KENDALL M G. A new measure of rank correlation[J]. Biometrika, 1938, 30(1/2): 81-93.
[19] HAYASHINO Y, NOGUCHI Y, FUKUI T. Systematic evaluation and comparison of statistical tests for publication bias[J]. Journal of epidemiol, 2005,15(6):235-243.
[20] HEDGES L V. Distribution theory for Glass's estimator of effect size and relatedestimators[J]. Educational statistics, 1981,6(2): 107- 128.
[21] 俞立平,潘云涛,武夷山. 学术期刊综合评价数据标准化方法研究[J]. 图书情报工作,2009,53(6):136-139.
