Software Effort Prediction Models Using Maximum Likelihood Methods Require Multivariate Normality of the Software Metrics Data Sample: Can Such a Sample Be Made Multivariate Normal?
Victor K. Y. ChanPublished in: COMPSAC (2004)
Keyphrases
- maximum likelihood
- data analysis
- raw data
- multivariate normal
- historical data
- neural network
- statistical methods
- software effort
- genetic algorithm
- multiple linear regression
- training data
- prediction model
- object oriented
- methods require
- artificial neural networks
- relational databases
- training set
- feature selection
- machine learning
- data mining