C275. The maximum of a bayes factor against "independence" in a contingency table, and generalizations to higher dimensions

1986 ◽  
Vol 26 (3-4) ◽  
pp. 312-316 ◽  
Author(s):  
I.J. Good
2017 ◽  
Vol 6 (2) ◽  
pp. 106 ◽  
Author(s):  
Yuan Yu ◽  
Dhiman Bhadra ◽  
Balgobin Nandram

Fisher's exact test is commonly used for testing the hypothesis of independence between the row and column variables in a $r \times c$ contingency table. It is a ``small-sample'' test since it is used when the sample size is not large enough for the Pearsonian chi-square test to be valid. Fisher's exact test conditions on both margins of a $2 \times 2$ table leading to a hypergeometric distribution of the cell counts under independence. Moreover, it is conservative in the sense that its actual significance level falls short of the nominal level. In this paper, we modify Fisher's exact test by lifting the restriction of fixed margins and allow the margins to be random. In doing so, we propose two new tests - a likelihood ratio test in a frequentist framework and a Bayes factor test in a Bayesian framework, both of which are based on a new multinomial distributional framework. We apply the three tests on data from the Worcester Heart Attack study and compare their power functions in assessing gender difference in the therapeutic management of patients with acute myocardial infarction (AMI).


2014 ◽  
Author(s):  
Sarahanne Field ◽  
Eric-Jan Wagenmakers ◽  
Ben Newell ◽  
Don Van Ravenzwaaij
Keyword(s):  

Astérisque ◽  
2020 ◽  
Vol 416 ◽  
pp. 213-251
Author(s):  
Mikhail LYUBICH ◽  
Remus RADU ◽  
Raluca TANASE
Keyword(s):  

Astérisque ◽  
2020 ◽  
Vol 416 ◽  
pp. 213-251
Author(s):  
Mikhail LYUBICH ◽  
Remus RADU ◽  
Raluca TANASE
Keyword(s):  

2020 ◽  
Author(s):  
Deep Bhattacharjee

Gravity has been leaking in higher dimensions in the bulk. Gravity being a closed string is not attached or does not have any endpoints unlike photons to any Dirichlet (p)-Branes and therefore can travel inter-dimensional without any hindrance. In LHC, CERN, Gravitons are difficult to detect as they last for such a short span of time and in most of the cases invisible as because they can escape to higher spatial dimensions to the maximum of 10, as per 'M'-Theory. Gravity being one of the 4-Fundamental forces is weaker than all 3 (strong and weak nuclear force, electromagnetism) and therefore a famous problem has been made in particle physics called the 'hierarchy problem'. Through comprehensive analysis and research I have come to the conclusion that if dimension is 5 (or 4 if we neglect the temporal dimensions) then an old approach is there for the compactification of the dimensions as per Kaluza-Klein theory and the most important implications of this theory is that an unification of electromagnetism with gravitation occurs in the fifth dimensions, therefore we can conclude that both the charge (electric as well as magnetic and gravity) are dependent of each other in case of Dimensions greater than 4 (5 if time is added). Now, basic principles of electromagnetic theory states that the field-flux density through a closed surface like a T 2 Torus when integrated over the surface area leads to a zero flux. That means there is no flux outside this closed surface integral. However, if the surface is open then the field flux density is not zero and this preserves the concept of magnetic monopoles. However, in a paper in 1931,[1] Dirac approaches monopole theory of magnetism through a different perspectives that, if all the electrical charges of the universe is quantized[2] then there is a suitable (not yet proved though) existence of monopoles; however this are not well understood as of today's scenario. In condensed matter physics, plasma physics and magneto hydrodynamics, there are flux tubes and as the both ends of the flux tubes are independent of each other then the net flux through the cylinder is zero as the amount of field lines entering the tube on one side is equal to the amount of field lines exit from the other end. And in the sides of the cylinder or the flux tube there is no escape of field lines, hence, net flux is conserved. There also exists a type of 'Quasiparticles' that can act as a monopole.[3][4][5] Now, from the perspectives of the Guess law of electromagnetism, if there exists a magnetic monopole then the net charge or flux density over a surface is not zero rather the divergence of the flux density B is 4 [6]and an alternative approach of the 'monopole' can be achieved by increasing the spatial dimensions by a factor of 1 or more. The Gravity has no such poles and therefore can be considered as a unipolar flux density existing throughout the universe and is applicable to the inverse square law of decreasing magnitude via distance as 1/r 2. However, a magnet is always of bipolar with a north and South Pole. If a magnet can be broken then also the broken parts develop the other poles and become bipolar. However, there are tiny domains inside a magnet and if a magnet can be heated to approx. 700℃ then all the poles disappeared and if its cooled quickly, rather very quickly then the tiny domains inside the magnet would not get enough time to rearrange themselves and multipolar magnet is developed therefore to preserve the bipolar properties, the magnet should be cooled slowly allowing the time given to the tiny domains top rearrange themselves. Therefore, even multipole can be achieved quite easily but not the monopoles. So, the equation for a closed surface integral of a flux density without monopole is ∯(S) B dS = 0 or ∇ • B = 0 and that closed surface can be considered as 2 types namely (we will discuss about torus) as because in string theory compactification of higher spatial dimensions occurs in torus.


Sign in / Sign up

Export Citation Format

Share Document