Logistic Regression: From Art to Science

Logistic Regression: From Art to Science

A high quality logistic regression model contains various desirable properties: predictive power, interpretability, significance, robustness to error in data and sparsity, among others. To achieve these competing goals, modelers incorporate these properties iteratively as they hone in on a final model. In the period 1991–2015, algorithmic advances in MixedInteger Linear Optimization (MILO) coup...

cumulative logistic regression vs ordinary logistic regression

The common practice of collapsing inherently continuous or ordinal variables into two categories causes information loss that may potentially weaken power to detect effects of explanatory variables and result in Type II errors in statistical inference. The purpose of this investigation was to illustrate, using a substantive example, the potential increase in power gained from an ordinal instead...

Information System Architectures: From Art to Science

The presentation claims that architectural design plays a crucial role in system development as a first step in a process that turns a requirements specification into a working software and hardware system. As such, architectural design should follow a rigorous methodology – a science – rather than intuition – an art. Our basic premise is that requirements in information systems follow a servic...

Quantitative fluorescence microscopy: from art to science.

A substantial number of elegant experimental approaches have been developed to image the distribution and dynamics of DNA, mRNA, proteins, organelles, metabolites, and ions in living plant cells. Although the human brain can rapidly assimilate visual information, particularly when presented as animations and movies, it is much more challenging to condense the phenomenal amount of data present i...

Diagnostic imaging: from art to science?