Partition-adjusted extended inverse Gauss-Poisson analysis with free gamma. Estimates the partition parameter p by minimizing the mean squared error. Note that the observed developmental profile should be available in the working directory (output of spectrum). For a detailed description of the output files, see lnreSgam.
Since there are no closed-form expressions for estimating the parameters of the complete inverse Gauss-Poisson model with free gamma, the program asks the user whether to attempt downhill simplex minimization provide interactive user-guided minimization. In the case downhill simplex minimization is selected, the program calculates E[V(N)] and E[V(1,N)] for the simpler model with gamma = -0.5. The user is offered the choice between using these parameters as starting point for minimization, or to specify another starting point. The program uses cost function C_1 in the simplex subroutine.
In the case of interactive user-guided minimization, the program prompts for Z, b and gamma, and calculates the expected vocabulary size and the expected number of hapax legomena and dis legomena for the specified parameters. The user is offered the option of adjusting the parameter estimates before proceeding to the main analyses.
input
text.spc: the frequency spectrum
text.obs should be available in the working directory
options
-h: display on-line help
-mW: number of frequency ranks m in the fit is set to W (default: 15)
-kX: number of chunks for interpolation is set to X (default: 20)
-KY: number of chunks for extrapolation is set to Y (default: 20)
-EZ: extrapolation sample size is set to Z (default: 2N_0)
-H: input file has no header (default: with header)
output
text_bG.spc: expected frequency spectrum
text_bG.sp2: expected frequency spectrum at 2N_0
text_bG.ev2: V(N_0), E[V(N_0)] and E[V(2N_0)]
text_bG.sum: summary of main statistics, including the specialization parameter p
text_bG.int: interpolation statistics
text_bG.ext: extrapolation statistics
technical details
For technical details, see lnreSgam