摘要
提高产品成本估算模型精确度的关键技术是如何进行原始数据的预处理和诊断。对成本原始数据进行了时间价值和学习曲线效应的修正,并采用矩阵的奇异值分解和方差分解比诊断法进行数据的多重共线性诊断,分别采用帽子矩阵法和剔除后的t化残差进行自变量、因变量异常值诊断,用库克距离进行强影响值的诊断,保证了模型所用数据满足要求,提高了模型的精度。
The key technology to improve the precision of the cost cost data.The raw cost data were modified with the value of time estimate model is how to pre-process and diagnose the raw and learning curve effect,and then diagnosed with singular value decomposition and variance decomposition ratio for muhicollinearity.Hat matrix and eliminated t-variance were adopted to distinguish the value out of the ordinary from independent variable and dependent variable respectively.The influential cases were discriminated with Cook＇s distance.The data were guaranteed to fit the demand of the model ,and the precision of this model was improved.
出处
《计算机工程与应用》
CSCD
北大核心
2007年第31期106-108,共3页
Computer Engineering and Applications
关键词
成本估算
数据诊断
多重共线性
异常值
强影响值
cost estimate
data diagnosis
muhicollinearity
value out of the ordinary
influential cases
