摘要
方法变异是由研究方法导致的系统误差。方法变异既可能产生结构层面的影响,也可能产生题目层面的影响;既可能影响单个结构的测量,也可能影响用相同方法研究的多个结构之间的关系,还可能影响用相同方法研究的多个研究之间的关系,进而影响到相关领域的理论建构。在控制方法变异时,可采取过程控制法和统计控制法,最好先用过程控制法。
Method variance refers to variance that is attributable to the measurement method rather than to the construct of interest. Method variance are a problem because they are one of the main sources of measurement error. It may result in many effects： parameter estimation error within measures, common method bias and the threat of common method variance bias to theory building in a research domain. Procedural design and statistical control solutions are provided to minimize method biases in studies. Researchers are encour- aged to consider and address MV when designing their studies,in order that potential bias may be minimized thus increasing the preci- sion of their data analysis.
出处
《心理学探新》
CSSCI
2013年第3期195-199,共5页
Psychological Exploration
基金
广东省普通高校人文社会科学重点研究项目(09JDXMXLX01)
江西省社会科学“十一五”规划项目(10JY46)
江西省教育科学规划一般项目
关键词
方法变异
共同方法变异
共同方法偏差
系统误差
method variance
common method variance
common method bias
systematic measurement error
