Loading...
Please wait, while we are loading the content...
Similar Documents
The numerical evaluation of maximum-likelihood estimates of the parameters for a mixture of normal distributions from partially identified samples
| Content Provider | NASA Technical Reports Server (NTRS) |
|---|---|
| Author | Walker, H. F. |
| Copyright Year | 1976 |
| Description | Likelihood equations determined by the two types of samples which are necessary conditions for a maximum-likelihood estimate are considered. These equations, suggest certain successive-approximations iterative procedures for obtaining maximum-likelihood estimates. These are generalized steepest ascent (deflected gradient) procedures. It is shown that, with probability 1 as N sub 0 approaches infinity (regardless of the relative sizes of N sub 0 and N sub 1, i=1,...,m), these procedures converge locally to the strongly consistent maximum-likelihood estimates whenever the step size is between 0 and 2. Furthermore, the value of the step size which yields optimal local convergence rates is bounded from below by a number which always lies between 1 and 2. |
| File Size | 3081982 |
| Page Count | 18 |
| File Format | |
| Alternate Webpage(s) | http://archive.org/details/NASA_NTRS_Archive_19760023803 |
| Archival Resource Key | ark:/13960/t4wh7bz9t |
| Language | English |
| Publisher Date | 1976-06-01 |
| Access Restriction | Open |
| Subject Keyword | Statistics And Probability Normal Density Functions Theorems Approximation Probability Theory Iteration Maximum Likelihood Estimates Matrices Mathematics Convergence Ntrs Nasa Technical Reports Server (ntrs) Nasa Technical Reports Server Aerodynamics Aircraft Aerospace Engineering Aerospace Aeronautic Space Science |
| Content Type | Text |
| Resource Type | Technical Report |
