Biocomputational Methodology A n A djunct to Theory and A pplications

Summary The role o/ "methodology", as distinguished /rom "theory" and "application", is discussed and illustrated. It is argued that research in the biomedical sciences is moving towards a degree o/ complexity difJerent in both kind and extent /rom that usually encountered in other disciplines. Certain biocomputational methodology can be viewed as a bridge between the data /orms cornmonly encountered in biomedicine, and the statistical and computational machinery which had previously been developed to deal with physical science in/ormation. Exatszples are given o/ three promising research subareas, all o/ which concern naethods for dealing with highly conlplex /orms o/ health and medical data. 1. lntroduction Biocomputation as is considered in this paper is a blend of several disciplines, the major ones being biology, medicine, computer science and statistics. However, there is no simple distinction between theory and application in the field of biocomputation as there is in the physical sciences. Just what is it about the life sciences that differentiate their intersection with the quantitative disciplines (including computer science) from the interaction of these disciplines with the physical sciences? The following quotation of Dampier (1961) seems an appropriate preliminary to the consideration of the above question:

[1]  R. Ledley.  Use of computers in biology and medicine , 1965 .

[2]  Geoffrey S. Watson,et al.  Density Estimation by Orthogonal Series , 1969 .

[3]  P. Hoel,et al.  Introduction to Mathematical Statistics. Second Edition. , 1955 .

[4]  K. D. Tocher,et al.  The art of simulation , 1967 .

[5]  F. Mosteller.  On Some Useful "Inefficient" Statistics , 1946 .

[6]  H. D. Brunk.  Univariate density estimation by orthogonal series , 1978 .

[7]  R. Kronmal,et al.  The Estimation of Probability Densities and Cumulatives by Fourier Series Methods , 1968 .

[8]  R. Kronmal,et al.  An Introduction to the Implementation and Theory of Nonparametric Density Estimation , 1976 .

[9]  J T Wong,et al.  Interactive editing of biomedical data. , 1976, Computer programs in biomedicine.

[10]  M. Feinleib.  A Method of Analyzing Log-Normally Distributed Survival Data with Incomplete Follow-Up , 1960 .

[11]  Ivor Francis,et al.  A Review of the Manuals for BMDP and SPSS , 1978 .

[12]  Roy H. Wampler.  A Report on the Accuracy of Some Widely Used Least Squares Computer Programs , 1970 .

[13]  L. Breiman,et al.  Variable Kernel Estimates of Multivariate Densities , 1977 .

[14]  R. Kronmal,et al.  On Multivariate Density Estimates Based on Orthogonal Expansions , 1970 .

[15]  K. B. Davis,et al.  Mean Square Error Properties of Density Estimates , 1975 .

[16]  Nonsupervised pattern recognition through the decomposition of probability functions , 1966 .

[17]  S. Raman,et al.  A systematic approach to graphical methods in biometry , 1972 .

[18]  Abraham Silvers,et al.  Implementation and Applications of Bivariate Gaussian Mixture Decomposition , 1975 .

[19]  Michael E. Tarter,et al.  Trigonometric Maximum Likelihood Estimation and Application to the Analysis of Incomplete Survival Information , 1979 .

[20]  R. Plackett,et al.  Introduction to Statistical Analysis. , 1952 .

[21]  Michael E. Tarter,et al.  After the histogram what? a description of new computer methods for estimating the population density , 1967, ACM National Conference.

[22]  W. Fellner.  Heuristic estimation of probability densities , 1974 .

[23]  J Gregor,et al.  An algorithm for the decomposition of a distribution into Gaussian components. , 1969, Biometrics.

[24]  John W. Tukey,et al.  Exploratory data analysis , 1977, Addison-Wesley series in behavioral science : quantitative methods.

[25]  M. Tarter.  Inverse cumulative approximation and applications. , 1968, Biometrika.