DETERMINATION OF THE GOODNESS OF FIT OF A DISTRIBUTION TO A SET OF EXPERIMENTAL DATA | ||||
The International Conference on Electrical Engineering | ||||
Article 32, Volume 5, 5th International Conference on Electrical Engineering ICEENG 2006, May 2006, Page 1-15 PDF (183.13 K) | ||||
Document Type: Original Article | ||||
DOI: 10.21608/iceeng.2006.33557 | ||||
View on SCiNiTO | ||||
Author | ||||
Ashraf Mamdouh A. Aziz | ||||
Associate Professor, Electrical Eng. Dept., Military Technical College, Cairo, Egypt. | ||||
Abstract | ||||
Abstract Many systems of interest involve phenomena that exhibit unpredictable variation and randomness. For example, communication systems must provide continuous and error free communication over channels that are subject to random noise. Probability models are one of the tools that enable the designer to successfully build systems that are efficient and reliable. Processing of random signals postulates a probability model that is defined by the probability density function of the random signal. In this paper, we propose a method to determine the goodness of fit of a distribution to a set of experimental data. The proposed method depends on the chi-square test. It is applied to different examples of different probability density functions. The proposed method is proved to be efficient. | ||||
Keywords | ||||
Probability density function – Fit of a distribution to data – Probability models – Histogram of random variables | ||||
Statistics Article View: 91 PDF Download: 211 |
||||