Quasi-Distribution for Non-Physicists

  • Context: Undergrad 
  • Thread starter Thread starter consuli
  • Start date Start date
Click For Summary

Discussion Overview

The discussion revolves around the concept of quasi-distribution, particularly in the context of statistical methods used in the R programming language. Participants are exploring the definitions and implications of quasi-distribution and quasi-likelihood, seeking a statistical understanding without delving into physics terminology.

Discussion Character

  • Exploratory, Technical explanation, Conceptual clarification, Debate/contested

Main Points Raised

  • One participant expresses interest in understanding the statistical nature of quasi-distribution and its proper definition, questioning what the density of quasi-distribution references in terms of probability.
  • Another participant provides a link to a Wikipedia article on quasiprobability distribution but refrains from further explanation.
  • A participant seeks a more intuitive and less physics-oriented introduction to the topic, mentioning their current reading of "The Wigner Transform" by Maurice A. de Gosson.
  • There is a clarification regarding the terminology used in R documentation, noting that "quasi-likelihood" is used instead of "quasi-distribution," suggesting that these may be distinct concepts.
  • A participant identifies that Wigner Probability Distribution and Quasi Probability Distribution are considered the same, while emphasizing that Quasi-likelihood is a different concept not initially requested.

Areas of Agreement / Disagreement

Participants appear to have differing views on the relationship between quasi-distribution and quasi-likelihood, with some acknowledging their potential differences while others explore their connections. The discussion remains unresolved regarding the intuitive understanding of these concepts.

Contextual Notes

There is a lack of consensus on the definitions and implications of quasi-distribution and quasi-likelihood, as well as the extent to which they are related. The discussion also reflects varying levels of familiarity with the underlying statistical and physical concepts.

consuli
Messages
62
Reaction score
4
Hello!

I am a statistician interested in physics.

In the glm procedure in the software R, one can choose, quasi-distribution. I have always wondered what that might be.

Could you introduce the statistical nature of quasi-distribution to me, ideally without mentioning any physics terms like Schrödinger-equation and so on.

Quasi-distribution has a proper statistical definition, doesn't it? So for the first: The density of quasi-distribution references the probability of what?

Consuli
 
Physics news on Phys.org
Well, I am looking for a more intuitive and especially less physical but more statistical introduction to this topic.

I am trying"The Wigner Transform", De Gosson, Maurice A, 2017 now. I guess, this isn't easier, but at least more detailed.

Consuli
 
consuli said:
In the glm procedure in the software R, one can choose, quasi-distribution. I have always wondered what that might be.
The R documentation I see online uses the term "quasilikelihood", not "quasidistribution". https://www.rdocumentation.org/packages/stats/versions/3.4.3/topics/glm

A "Quasi-likelihood" may be an entirely different thing than a quasiprobability distribution. (The current Wikipedia treats them in different articles.)

Attempting to develop an intuition about either concept would be an interesting project.
 
Stephen Tashi said:
The R documentation I see online uses the term "quasilikelihood", not "quasidistribution". https://www.rdocumentation.org/packages/stats/versions/3.4.3/topics/glm A "Quasi-likelihood" may be an entirely different thing than a quasiprobability distribution. (The current Wikipedia treats them in different articles.)

Meanwhile I have figured out, that
Wigner Probability Distribution
and
Quasi Probability Distribution
are the same, thus both related to Schrödinger equation (and the ones I asked for)

but
Quasi-likelihood
is another very different thing (I did NOT asked for).

Consuli
 

Similar threads

Undergrad Variable transformation for a multivariate normal distribution
  • · Replies 1 ·
Replies
1
Views
2K
Undergrad Right way to account for non-statistical uncertainties
  • · Replies 16 ·
Replies
16
Views
2K
High School Distribution of particles, given a function
  • · Replies 2 ·
Replies
2
Views
1K
Graduate Negative Poisson-Binomial Distribution
  • · Replies 14 ·
Replies
14
Views
6K
Undergrad Reconciling Lorentz Four-Force Density w/ Spacelike Four-Current (##c = 1##)
  • · Replies 10 ·
Replies
10
Views
3K
Undergrad To rejuvenate the plausibility of stochastic mechanics
  • · Replies 1 ·
Replies
1
Views
2K
Undergrad New Nobel Aspect contradicts himself on action at a distance bel
  • · Replies 2 ·
Replies
2
Views
2K
Graduate AICc and parameter likelihood from repeated fits
  • · Replies 9 ·
Replies
9
Views
3K
Undergrad Why does the Dirac equation lead to spin 1/2?
  • · Replies 8 ·
Replies
8
Views
7K
Undergrad Balloon experiment - Classical Physics vs. Statistical Physics
  • · Replies 16 ·
Replies
16
Views
2K