- PII
- S0205-96060000616-4-1
- DOI
- 10.7868/S60000616-4-1
- Publication type
- Article
- Status
- Published
- Authors
- Volume/ Edition
- Volume 37 / Issue 2
- Pages
- 233-250
- Abstract
- Famous experiments by Robert A. Millikan to determine the electron charge are often used as an illustration of the method of confi dence intervals in the statistical analysis of experimental data. Yet the lecturers typically pay attention to the already processed data on the measurement of 58 drops, whereas each of these values relies on the results of several successive measurements. For 16 drops, Millikan provided the more detailed primary data, which are analyzed here with the methods of mathematical statistics. It turns out that Millikan's measurements were not statistically stable, which makes the method of confi dence intervals inapplicable. However, the mean value of the electron charge, calculated on the basis of Millikan's primary data, is very close to the modern value, and the narrow confi dence interval includes the latter.
- Keywords
- electron charge, the Millikan experiment, statistical stability, confidence interval, empirical distribution function, normal scale, observational error theory, the Kolmogorov — Smirnov test
- Date of publication
- 01.04.2016
- Year of publication
- 2016
- Number of purchasers
- 1
- Views
- 1355
RAS PresidiumВопросы истории естествознания и техники Voprosy istorii estestvoznaniia i tekhniki
- ISSN (Print) 0205-9606
- ISSN (Online) 2713-041X
THE MILLIKAN EXPERIMENT FROM THE POINT OF VIEW OF MATHEMATICAL STATISTICS
Indexing
Scopus
Crossref
Higher Attestation Commission
At the Ministry of Education and Science of the Russian Federation
Scientific Electronic Library