Thresholds of Confidence
An Analysis of Statistical Methods for Composition: Part 2: Applications
Bibliographic Data
| ID | 20486171 |
|---|---|
| Authors | Charles Ames (corresponding author) |
| Year | 1996 |
| Volume | 6 |
| Pages | 21 |
| Publication date | 1996-01-01 |
| Open Access | No |
| Type | ARTICLE |
| Venue | Leonardo Music Journal (JOURNAL) |
| Journal identifiers | ISSN: 0961-1215 • E-ISSN: 1531-4812 |
| Publisher | JSTOR (PUBLISHER) |
| DOI | 10.2307/1513300 |
| OpenAlex | W2335779881 |
| Language | EN |
| References cited | 3 |
This is Part 2 of a two-part analysis of serialism, randomness and statistical feedback. Part 1 developed the theoretical basis, which the present article applies to seven compositional scenarios. Scenarios 1-3 cover discrete distributions in static contexts and deem methods effective when they are able to utilize the least-weighted state at least once. Scenarios 4 and 5 cover continuous distributions, again in static contexts. These scenarios measure effectiveness by comparing the expected mean and variance with the statistics obtained from populations. Scenario 6 covers discrete distributions with evolving weights, with effectiveness being gauged through the number of samples required to establish a trend. Scenario 7 covers conditional distributions through the paradigm of the Markov chain. Here a realization is deemed effective if it represents the least-weighted transition at least once
Art · Confidence interval · Literature · Statistical analysis · Statistics · Bayesian Methods and Mixture Models · Computer Science · Mathematics · Stochastic processes and statistical mechanics · Theoretical and Computational Physics
| Highly cited | No |
|---|