Questions tagged [log-likelihood]
Only questions related to the implementation and usage of the mathematical function - log-Likelihood should use this tag.
log-likelihood
237
questions
1
vote
1
answer
43
views
Likelihood ratio when the difference in the log-likelihood is a large negative number
Using the Geyer-Thompson algorithm, you can compute the ratio of two likelihoods (needed to do a likelihood ratio test or to compute an information criterion like AIC or BIC). This is useful when ...
- 154
0
votes
1
answer
27
views
implementing an overall Wald test for a glmer model [closed]
I would like to know how to get the overall Wald test and its p-value for a fitted glmer model from the lme4 package. For example:
credec ~ passexp + soctie + recexp + peer + soctie * recexp +
(1 |...
0
votes
1
answer
71
views
Weibull Three Parameters Estimation using Maximum Likelihood and optimization methods
I'm having a problem estimating the Weibull three parameters using ML and optimization methods. My results in some of the methods do not look right. However, when a plot the curve looks fine with the ...
0
votes
0
answers
16
views
Likelihood ratios not distributed as a chi2 distribution with the correct dof (Wilk's theorem)
I perform Bayesian inference on a mixture model such that, μ is the mixture weight for a feature in the mixture
p(x|μ,theta) = μ p_feature(x|theta) + (1-μ) p_nofeature(x|theta).
I calculate T(μ) = \...
1
vote
0
answers
6
views
Is there an R function that minimise a bivariate function f
I need to write a code that using the R function constrOptim, minimise an bivariate function. Please tell me what is wrong in the constrOptim , went i run the code i have this warning message
"...
- 11
1
vote
1
answer
63
views
Post-hoc comparisons of quasi-family glmer models with emmeans
Since "quasi" families cannot be used in glmer, there is an efficient approach to adjust the standard errors of the parameters and the associated statistics post-fitting (https://bbolker....
- 13
0
votes
1
answer
11
views
Likelihoods in both linear regression model and naive Bayesian model
The model in linear regression is
$y = \omega^T x + e$
, where x, y, e represent the feature, the target and the noise, respecively.
p(y|x, omega) is often termed the likelihood function for the ...
- 101
0
votes
0
answers
22
views
Bayesian Information Criterion based on non-negative matrix factorization (NMF)
How to calculate Log-Liklihood (L) and BIC from NMF results.
Shape of W (weights): (65537, 117)
Shape of H (components): (117, 467)
I have used the following to calculate L
var = np.var(residuals, ...
0
votes
0
answers
13
views
Closed form for $w$ that maximizes log likelihood in logistic regression
Given a training set $D=(x_1,y_1) , ... , (x_n, y_n)$ where $x_i \in \mathBB{R} ^d$ and $y_i\in ${$0,1$}
we assume a logistic regression model and aim to learn $w$ that fits $D$.
Is is possible to get ...
- 137
0
votes
0
answers
15
views
function to compute permutation and calculate log likelihood ratio test
Hello i am creating a function to calculate the log likelihood and then to do a permutation
fLLR <- function(outcome, sex, genotype, covariates, L0) {
#outcome <- data[,1]
#sex <- data[...
- 1
0
votes
0
answers
41
views
Implementing a gradient function using numpy
I am having trouble figuring out how to implement a specific gradient function with NumPy. I am sure my math is correct, but I have failed at coding it. I have attached my work and the parts of the ...
- 11
0
votes
1
answer
86
views
Error in EM algorithm: Non-finite Function Value in Likelihood Estimation with Integrals
I am encountering a persistent issue in my R program while performing Monte Carlo simulations for Maximum Likelihood Estimation (MLE). The simulation involves drawing samples from a modified Weibull ...
0
votes
0
answers
25
views
Maximizing the COX likelihood function
What are the best optimization methods to find the parameter values that maximize the likelihood function of COX specifically ?
The likelihood function of COX is:
The likelihood function of COX
How ...
0
votes
0
answers
33
views
Need to understand Variational Gaussian Process in gpflow
When I look at source of Base Likelihood, I saw this:
def variational_expectations(
self, X: TensorType, Fmu: TensorType, Fvar: TensorType, Y: TensorType
) -> tf.Tensor:
r"&...
- 113
0
votes
0
answers
43
views
How to implement Variational Gaussian Process with custom likelihood in gpflow
I have this equation with , y is observation and f is latent. I write this new Likelihood to compute in my model:
class ExpGaussian(likelihoods.ScalarLikelihood):
def Y_given_F(self, F):
mu = ...
- 113