#TITLE_ALTERNATIVE#

ABSTRACT: <br /> <br /> <br /> <br /> <br /> In data analysis, to calculate the probability of a random variable X in a point P(X c) or an interval P(a X b), the information of the distribution of X is needed. However, in reality scientists consider that the exact...

Full description

Saved in:
Bibliographic Details
Main Author: Oktari (NIM 10103044), Anggun
Format: Final Project
Language:Indonesia
Online Access:https://digilib.itb.ac.id/gdl/view/5743
Tags: Add Tag
No Tags, Be the first to tag this record!
Institution: Institut Teknologi Bandung
Language: Indonesia
Description
Summary:ABSTRACT: <br /> <br /> <br /> <br /> <br /> In data analysis, to calculate the probability of a random variable X in a point P(X c) or an interval P(a X b), the information of the distribution of X is needed. However, in reality scientists consider that the exact calculation is impractical. They prefer the simple calculation, especially for discrete distribution, even the result is only a bound. This matter will be more useful when there is only a part of the information of the distribution of X is known, such as mean and variance. Inequality can be used to calculate this bound. This final thesis will be discuss about Markovs, Chebyshevs, and Chernoffs inequalities. Chernoffs inequality can give the most accurate bound, near the real value. This inequality also can be prime alternative to give a bound in the probability of an interval, especially in data mining.