FORTRAN Computer Programs (Source Codes)
We provide here Fortran source codes for Biologically Inspired Global Optimization methods such as the Repulsive Particle Swarm (RPS), Host-Parasite or Cuckoo-Host Coevolution (HPC/CHC) metaheuristics, the Genetic Algorithms (GAs) and the Differential Evolution (DE). We also provide programs for econometric analysis such as Non-linear Least Squares, Robust Regression, Robust Two-Stage Least Squares, Ordinal Canonical Correlation, Ordinal Principal Component Analysis, Hybridization of canonical correlation and principal component analysis, fitting origin-displaced logarithmic spiral to data, solving the nearest correlation matrix problem, completing the correlation matrix, construction of composite indices by linear aggregation, etc. some of which are based on global optimization. Some Fortran Source Code Libraries on the Web have also been linked.
These programs (source codes) may be compiled by a suitable FORTRAN compiler (e.g. Microsoft Fortran Compiler or Force Compiler or FORCE Fortran 77 compiler; note that FORCE Compilers are free downloadable), which, after compilation will yield executable programs to be run for solving the problems. Some programs may use higher versions of Fortran (e.g Fortran 95). Compilers (e.g. Silverfrost FTN95) for those versions are also free downloadable.
"The Mecca of the economist lies in economic biology rather than in economic dynamics. But biological conceptions are more complex than those of mechanics." Alfred Marshall, Principles of Economics (Preface 8 Ed), Macmillan,1920.
- A Fortran-77 computer program to minimize a multimodal (nonconvex) objective function by Host-Parasite (or Cuckoo-Host) Co-Evolutionary algorithm of Global Optimization.
- A Fortran-77 computer program to minimize a multimodal (nonconvex) objective function by Repulsive Particle Swarm method of Global Optimization.
- A Fortran-77 computer program to minimize a multimodal (nonconvex) objective function by Differential Evolution method of Global Optimization.
- A Fortran general purpose program for Real Coded Genetic Algorithms from High Altitude Observatory.
- Xie, J.C., Mishra, S.K., Kar, T. & Xie, R.H. (2014). "Generalized Interatomic Pair-Potential Function", Chemical Physics Letters. 605-606 (June 17, 2014): 137-146.
has been fitted (by minimization of cost - hybrid least squared plus least absolute deviation cost function) for the following cases (that serve as examples) :
1. CASE 1: H2 (Strongly covalent bonding) - Code : PairPotCodeH2.for; Input: potInPutH2.dat; Output: (i) potOutputH2.dat and (ii) vibOutputH2.dat
2. CASE 2: Ar2 (Weakly bonding) - Code : PairPotCodeAr2.for; Input: potInPutAr2.dat; Output: (i) potOutputAr2.dat and (ii) vibOutputAr2.dat
These Codes (Fortran) for H2 and Ar2, input files (potInPutH2.dat and potInPutAr2.dat) and output files (potOutputH2.dat, vibOutputH2.dat; potOutputAr2.dat, vibOutputAr2.dat) may be downloaded from here (download Code, Input data and output for H2 and Ar2).
- A Fortran-77 computer program for Construction of a Composite Index by Optimization of Shapley Value Shares of the Constituent Variables. Download (Fortran source codes).
- A Fortran-77 computer program for Shapley value regression for resolution of multicollinearity (Fortran source codes).
- A Fortran-77 computer program for Nonlinear Least Squares by Differential Evolution and Repulsive Particle Swarm methods of Global Optimization.
- A Fortran-77 computer program to compute the estimators of (linear mulltiple) regression parameters by a family of Maximum Entropy Leuven Estimators to ameliorate the multicollinearity problem.
- A Fortran-77 computer program to compute Robust Regression coefficients in presence of outliers
- A Fortran-77 computer program to compute Robust Regression coefficients in presence of outliers (P.J. Rousseeuw and A.M. Leroy (1987): Robust Regression and Outlier Detection, Wiley, New York). Also see some more information.
- A Fortran-77 computer program for Construction of Composite Indices: Alternatives to the Principal Component Analysis.
- A Fortran-77 computer program for non-Perarsonian correlation-based principal component analysis - NPPCA (Note: In any PCA obtaining Z=XA, where A contains the (scaled) eigenvectors of R, the component scores, Z, are sub-optimal if R is a non-Pearsonian, say S (such as Spearman's rank, Kendall's Tau, Signum, Shevlyakov, Brownian, Bradley's absolute, etc) correlation matrix. However, if X is suitable transformed to H = f(X) such that the inner product < f(X),f(X) > is H'H = S (non-Pearsonian correlation matrix), the Principal Component scores U = HB (where B is the scaled eigenvectors of H), gives U = HB = XA = Z). [Base Paper], (Fortran Code).
- A Fortran-77 computer program to compute the structural coefficients of a multi-equation linear econometric model (in presence of outliers in the dataset) by Robust 2-Stage Least Squares.
- A Fortran-77 computer program to obtain the most representative composite rank ordering of multi-attribute objects.
- A Fortran-77 computer program to obtain Ordinal Canonical Correlation between two sets of ranking scores.
- A Fortran-77 computer program to obtain representation-constrained canonical correlation (hybridization of canonical correlation and principal component analyses).
- A Fortran-77 computer program for fitting an Origin-Displaced Logarithmic Spiral to empirical data.
- A Fortran-77 computer program for solving the Nearest Correlation Matrix Problem (using Differential Evolution, Particle Swarm and Neumann-Dykstra iteration).
- A Fortran-77 computer program for Completing the given Incomplete Correlation Matrices of Arbitrary Order.
- A Fortran-77 computer program for Construction of Pena's DP2 Synthetic Indicator (or Composite Index).
|Fortran Program Libraries|