农作物试验设计和统计分析值得注意的7 个问题 - 中国烟草科学.pdf

98 Chinese Tobacco Science 2014-1235 6 7 1,2,3 2 3,4 3,4 1. 266101 2. 410125 3. 100049 4. 365000 S572 1007-5119201406-0098-06 DOI 10.13496/j.issn.1007-5119.2014.06.020 Seven Problematic Areas of Design and Statistical Analysis in Crop Experiments 1,2,3 2 3,4 3,4 ZHANG Jiuquan , SU Yirong , HUANG Yilan , ZHANG Ying (1. Tobacco Research Institute, Chinese Academy of Agricultural Science, Qingdao, 266101, China; 2. Institute of Subtropical Agriculture, Chinese Academy of Sciences, Changsha 410125, China; 3. University of Chinese Academy of Sciences, Beijing 100049, China; 4. Sanming Tobacco Company of Fujian Province, Sanming, Fujian 365000, China) Abstract: Correctness of experimental design and reasonability of statistical analysis influence the correctness of the results when conducting scientific experiments. Currently, statistical issues in crop study have caused much negative influence to scientific and technological innovation in China. We describe the problematic areas which occurred frequently when conducting crop experiments, which includes ignoring experiment design and statistical analysis, lack of study planning, placing importance on study results only when p values are less than .05, indiscriminant application of regression and analysis of variance, issue with repeated measurement data, and improper statistical expression, and suggest some resolu