Simulation, distribution, statistics.

Click For Summary
SUMMARY

This discussion focuses on determining the best-fitting statistical distribution for a dataset consisting of 15 numbers with a mean of 3.206, variance of 2.958195, and skewness of 0.945. The user is exploring various distributions, including Geometric, Poisson, Weibull, Gamma, and PT5, and is seeking methods to estimate parameters such as alpha and beta. Key statistical concepts mentioned include estimators, specifically the Method of Moments and Maximum Likelihood Estimators, which are essential for analyzing the data and conducting the Kolmogorov-Smirnov (KS) test to identify the appropriate distribution.

PREREQUISITES
  • Understanding of statistical concepts such as mean, variance, and skewness.
  • Familiarity with different probability distributions including Geometric, Poisson, Weibull, and Gamma.
  • Knowledge of estimators, specifically Method of Moments and Maximum Likelihood Estimators.
  • Basic proficiency in conducting the Kolmogorov-Smirnov test.
NEXT STEPS
  • Learn how to calculate parameters for Weibull and Gamma distributions.
  • Study the Method of Moments and Maximum Likelihood Estimators in detail.
  • Research the Kolmogorov-Smirnov test and its application in distribution fitting.
  • Explore graphical methods for plotting probability density functions of datasets.
USEFUL FOR

This discussion is beneficial for statisticians, data analysts, and engineering students who are interested in statistical distribution analysis and parameter estimation techniques.

skaterboy1
Messages
13
Reaction score
0
I´m wondering how to find out something about distribution functions after I´ve calculated the scewness. I have 15 numbers, mean is 3.206, highest is 7.028 and lowest is 0.9209. Variance is 2.958195. I calculate the skewness and got 0.945.

I´m wondering which of the following distributions is the best match for the numbers I´ve already calculated. I tried to plot the scors I got but it didn´t seem to make any sense.

These are the possibilities:
DU(i,j)).
Geom(p)).
Poisson(lambda).
Weibull(alpha,beta)).
Gamma(alpha,beta).
PT5(alpha,beta).

I was looking for a way to find alpha, beta, gamma etc
I was thinking if it was something about the Kolmogorov test?
 
Physics news on Phys.org
Hey skaterboy1 and welcome to the forums.

For this kind of problem, we use what is called an estimator.

An estimator is used to get an idea of what a parameter of a distribution might be given a set of data. The estimators that statisticians and scientists used have the properties that they are consistent, unbiased and reliable.

We have different kinds of estimators like Method of Moments and Maximum Likelihood Estimators. These templates can be applied for general distributions if the distribution has certain properties (for example MLE can't be applied to Uniform distributions because it is a constant function which screws up the estimator).

What is your mathematical and statistical background like?
 
Thank you for the reply. Average I guess. Studying engineering.
I red more about this and I have to find probability density function and also plot the numbers i have. I have to do the KS test and find out what type of distribution this is.
I don´t know how to start.
 
Last edited:

Similar threads

  • · Replies 5 ·
Replies
5
Views
2K
Replies
2
Views
2K
  • · Replies 4 ·
Replies
4
Views
5K
  • · Replies 7 ·
Replies
7
Views
3K
  • · Replies 3 ·
Replies
3
Views
12K
  • · Replies 9 ·
Replies
9
Views
2K
Replies
6
Views
2K
  • · Replies 1 ·
Replies
1
Views
1K
  • · Replies 2 ·
Replies
2
Views
2K
  • · Replies 14 ·
Replies
14
Views
2K