Questions tagged [mathematica]
Mathematica is a software package for symbolic mathematical computations.
16 questions with no upvoted or accepted answers
3
votes
0
answers
532
views
How do I calculate the Bayes error of a multivariate normal Bayesian classifier?
I have a 4 dimensional feature and each of them are independent normal distributions. I want to calculate the bayesian error associated with this classifier. The covariance matrix and the mean have ...
- 131
2
votes
0
answers
108
views
Maximum Uncertainty in Normal Distribution
While reading Goodfellow's Deep Learning Book, I came across the below fact about Normal Distribution. I am not sure I have understood what led to this conclusion, Can someone help with it?
"Out ...
- 51
2
votes
1
answer
518
views
2
votes
0
answers
1k
views
How can I compute the lower and upper bounds of a confidence interval in a linear regression problem?
I am completing a university statistics assignment on the Mathematica program, and this is the initial question:
"The Medical Research Council wanted to evaluate the
effects of different dosages of a ...
- 21
2
votes
1
answer
295
views
Frequency of a wavelet filter
Assume that I have decomposed a data set using Symlet Wavelet with six levels. How can I estimate the approximate frequency interval of each level?
That would be great if you consider your answer in ...
- 505
1
vote
0
answers
84
views
What mathematical background do I need to do research in field of deep learning
I am familiar with few deep learning models and I understand how (little bit why) CNN/RNN works. But I still cannot make sense of new research papers. I want to dive deeper into field of deep learning ...
1
vote
1
answer
132
views
Is there any relationship between two normalized gamma distributions?
Consider two normalized gamma distribution functions $\frac{\Gamma(x,y)}{\Gamma(x)}$ and $\frac{\Gamma(nx,ny)}{\Gamma(nx)}$ where $n$ is a positive integer value. Is there any relationship between the ...
- 11
1
vote
0
answers
105
views
How can I incrementally calculate the 4 central moments in statistics (mean, standard deviation, skewness and curtosis) when a value is removed?
I'm incrementally calculating the 4 central moments. When a value x is added and n, M1, M2, M3 and M4 are some predefined values, I'm using the following algorithm:
...
- 11
1
vote
0
answers
53
views
Measuring Autocorrelation in Tail Events
I have a single time series of financial data (stock index returns) and would like to study the autocorrelation among (log-)returns that are classified as "extreme", for example via exceedance of a ...
- 111
1
vote
0
answers
36
views
Visualising n vectors of length n in a periodic fashion
I'm currently working on a specific problem in a periodic structure, for which I obtain a set of eigenvectors that I would like to plot. It is probably easiest if I give you an explicit example, then ...
- 211
0
votes
0
answers
5
views
how to distinguish negative shock or positive shock in TGARCH model?
IN the picture, how to know whether the yellow highlighted part exists or not?
because the return of day 1000 drop from 0.02 to 0.01, so there was a negative shock, so l should keep the yellow ...
- 1
0
votes
0
answers
54
views
Are these data points decaying exponentially or as a power law?
0
I have a set of data points. The first coordinate is time and the second coordinate is energy. I am trying to figure out how the energy is decaying over time. Particularly, I have to find if it is ...
0
votes
1
answer
61
views
Would I use a one-tailed paired-sample t- test on this?
I am doing an assignment that tests whether acceptance and commitment therapy is beneficial for social anxiety disorder.
With an experimental and controlled group.
I just need to know what test I ...
0
votes
0
answers
483
views
How can Hinge loss be upper bound of the 0-1 loss?
I just have a question and I did not find clear explanation, hinge loss is upper bound of 0-1 loss, so does this mean upper bound regard to a single point loss such as 0 or 1 ?!. So, for example the 0-...
- 109
0
votes
0
answers
33
views
Why fitting does not find the true best point
I fitting an expression of the form:
$s(t)=\frac{1}{1+\exp[a+\sum_k b_k x_k(t)]}$
Where $a$ and $b_k$ are fitting parameters and $x_k(t)$ an input time series. I have $k=1,...,N$ different types of ...
- 161
0
votes
0
answers
96
views
How can I fix a poor nonlinear curve fit?
I was trying calculating Fourier transform of some rings. as follow:
By directly calculating of model as several rings, the result showed different from the the experimental ones. So I tried to get ...
- 1