HIERARCHY OF TECHNIQUES TO CONSTRUCT A BIVARIAT DISTRIBUTION ON DISCRETE DATA WITH IMPLICATION OF DEPENDENCE
Discrete data is empirical data as realizations of either discrete or continuous random variables. When two types of discrete data, it is interesting that want knowm, that kind of dependency that occurs and the second probability <br /> <br /> data can occur simultaneously. To determine...
Saved in:
| Main Author: | |
|---|---|
| Format: | Theses |
| Language: | Indonesia |
| Online Access: | https://digilib.itb.ac.id/gdl/view/25497 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Institution: | Institut Teknologi Bandung |
| Language: | Indonesia |
| Summary: | Discrete data is empirical data as realizations of either discrete or continuous random variables. When two types of discrete data, it is interesting that want knowm, that kind of dependency that occurs and the second probability <br />
<br />
data can occur simultaneously. To determine the type of dependence that occurs used Pearson correlation dan Kendall's tau. Meanwhile, in order to identify probability it needs to be constructed with a bivariat distribution, <br />
<br />
either probability function or distribution function. <br />
<br />
The results obtained in this thesis is hierarchy of techniques to construct a bivariat distribution on discrete data with implication of the dependence. Beginning with frequency technique that construction fully relies on empirical data, afterwards distribution and/or Copula Archimedean techniques that construction using marginal distribution. We provide examples of simulated data to <br />
<br />
illustrate such construction. |
|---|