| 洪志恒,王苹,曹卫华.慢性病观察性研究论文统计学应用评价[J].Chinese journal of Epidemiology,2012,33(9):964-968 |
| 慢性病观察性研究论文统计学应用评价 |
| Application of statistics on chronic-diseases-relating observational research papers |
| Received:April 17, 2012 |
| DOI：10.3760/cma.j.issn.0254-6450.2012.09.020 |
| KeyWord: 观察性研究 统计学 应用评价 |
| English Key Word: Observational study Statistics Application evaluation |
| FundProject: |
| Author Name | Affiliation | E-mail | | Hong Zhi-heng | Key Laboratory of Epidemiology, Ministry of Education, Department of Epidemiology and Biostatistics, School of Public Health, Peking University, Beijing 100191, China | | | Wang Ping | Key Laboratory of Epidemiology, Ministry of Education, Department of Epidemiology and Biostatistics, School of Public Health, Peking University, Beijing 100191, China | | | Cao Wei-hua | Key Laboratory of Epidemiology, Ministry of Education, Department of Epidemiology and Biostatistics, School of Public Health, Peking University, Beijing 100191, China | caoweihua60@163.com |
|
| Hits: 3711 |
| Download times: 1193 |
| Abstract: |
| 目的 评价中华医学会影响因子在0．5以上的核心期刊中慢性病观察性研究论文的统计学应用情况。方法 选择近5年影响因子在0．5以上的中华医学会系列杂志，采用自行设计的调查表，对是否有研究设计类型、样本量估计、变量及赋值描述，以及统计描述、推断及解释等进行调查，分析慢性病观察性研究论文统计学应用情况。结果 共有《中华流行病学杂志》、《中华预防医学杂志》、《中华心血管病杂志》、《中华内分泌代谢杂志》、《中华内科杂志》和《中华肿瘤杂志》6种期刊中的352篇慢性病观察性论著人选。明确说明研究同的、目标对象、抽样对象、对象入选标准和变量定义率的分别为99.43%、98.57%、95.43%、92.86%和96.87%；计量资料和分类变量描述正确率分别为90.94%、91.46%；计量资料、分娄变量及模型推断正确表达率分别为100%、95．32%和87.19%；研究结论正确回应研究目的的占89.49%。没有明示研究设计类型的占69.60%，需要进一步说明人选对象排除标准而没有说明的占11.14%，仅有5.16%论著提及了样本量估计情况，变量赋值说明率为24.21%。介绍了数据序建立方法的为24.15%，18.75%论著统计推断方法介绍不全。进行率标准化的论著约有1/4使用不当，对统计检验前提条件进行验证和说明的仅占24.12%，有9.94%论著需要做推断分析而未做。结论 目前中华医学会系列杂志发表的慢性病观察性研究论史统计学应用总体良好，但没计类型表述、样本量估计、变量赋值说明不充分；统计方法介绍不够明确；应加强了解统计推断使用的前提条件。 |
| English Abstract: |
| Objective To study the application of statistics on Chronic-diseases-relating observational research papers which were recently published in the Chinese Medical Association Magazines, with influential index above 0.5. Methods Using a self-developed criterion, two investigators individually participated in assessing the application of statistics On Chinese Medical Association Magazines, with influential indcx above 0.5. Different opinions reached an agreement through discussion. Results A total number of 352 papers from 6 magazines, inciuding the Chinese Journal of Epidemiology, Chinese Journal of Oncology, Chinese Journal of Preventive Medwine, Chinese Joturnal of Cardiology, Chinese Journal of Internal Medicine and Chinese Journal of Endoerinology and Metabolism, were reviewed. The rate of clear statement on the following contents as: research objectives, ttarget audience, sample issues, objective inclusion criteria and variablc definitions were 99.43%, 98.57%, 95.43%, 92.86% and 96.87%. The correct rates of description on quantitative and qualitative data were 90.94% and 91.46%, respectively. The rates on correctly expressing the results, on statistical inference methods related to quantitative, qualitative data and modeling were 100%, 95.32% and 87.19%, respectively 89.49% of the conclusions could directly response to the research objectives. However, 69.60% of the Papers did not mention the exact names of the study design, statistically, that the papers were using, 11.14% of the Papers were in lack of further statement on the exclusion criteria. Percentage of the papers that could clearly explain the sample size estimation only taking up as 5.16%. Only 24.21% of the papers clearly described the variable value assignment. Regarding the introduction on statistical conduction and on database methods, the rate was only 24.15%, 18.75%of the papers did not express the statistical inference methods sufficiently. A quarter of the papers did not use‘standardization’appropriately. As for the aspect of statistical inference, the rate of description on statistical testing prerequisite was only 24.12% while 9.94% papers did not even employ the statistical inferential method that should be used. Conclusion The main deficiencics on the application of Staffsties used ln papers related to Chronic-diseases-related observational research were as follows; lack of sample-size determination, variable value assignment description not suffhcient, methods on statisties were not introduced clearly or properly, 1ack of consideration for pre-requisition regarding the use of stalistical inferenecs. |
|
View Fulltext
Html FullText
View/Add Comment Download reader |
| Close |
|
|
|