Questions tagged [convergence]
Convergence generally means that a sequence of a certain sample quantity approaches a constant as the sample size tends to infinity. Convergence is also a property of an iterative algorithm to stabilize on some aim value.
1,201 questions
1 vote
1 answer
49 views
glmmTMB model gives AIC value and coefficient estimates, but no z or p values
I am modeling count data with a non-Poisson distribution and potential zero inflation in glmmTMB. I am using different distributions and zero inflation specifications, including Conway Maxwell Poisson,...
4 votes
3 answers
512 views
Why is the central limit theorem often described as convergence to the normal pdf
In introductory statistics courses, the central limit is often explained in one of several ways. It's often explained with pictures like However, these pictures seem misleading, because they suggest ...
1 vote
0 answers
68 views
SGD convergence when visit basin of attraction infinitely often
Consider a discrete stochastic system with components $(x_k, y_k)$ updated as follows. If all components are strictly positive, i.e. $x_k > 0$, $y_k > 0$, then \begin{aligned} x_{k+1} &= x_k ...
0 votes
0 answers
50 views
The Expectation of the Difference of Sample Quantile and Population Quantile
Suppose a distribution function $F(\cdot)$ is continuous. For some $\tau \in (0, 1)$, the $\tau$th quantile is defined as $$ Q_\tau = \inf \{ x : F(x) \ge \tau \}. $$ For an i.i.d. sample $X_1, \dots, ...
2 votes
0 answers
76 views
Joint model convergence problem: Hessian matrix at convergence is not positive definite
EDIT: adding a bit of context. I'm working with electronic health records, meaning each information per participant or number of measurements per participant is highly different. The event is ...
0 votes
0 answers
65 views
Proving Convergence of Mean and Variance in a Recursive Gaussian Update Process
I'm researching the statistical convergence properties of a recursive system that arises during the training of custom neural network structure. My specific question is: How can I prove convergence of ...
3 votes
1 answer
121 views
MCMC diagnostics by means of quantiles [Reference request]
In short: Could you share any references that explore the assessment of "convergence" and mean-estimate precision in MCMC by means of quantiles (or related quantities), rather than of ...
5 votes
1 answer
146 views
multilevel modeling: singular convergence advice
I am trying to do a multilevel analysis looking at trends in a dichotomous variable over time within multiple clusters. I have 22 years of data for each cluster. [My example data has only 8 clusters, ...
0 votes
0 answers
59 views
Does restricting weight space in Deep Learning models make training faster?
I want to know if the following problem has a name and also I'd like to get some papers to read on the subject. Suppose I have a model to learn, say $A$ and this has a huge numbers of parameters to ...
1 vote
0 answers
47 views
Results and Reference on the Speed of Convergence of MAP Estimator
I am trying to understand the statistical properties of \textbf{Maximum A Posteriori (MAP)} estimators for loss functionals with desirable properties. In my setting, let $n$ denote the number of ...
0 votes
0 answers
112 views
Convergence in distribution of components implies convergence in distribution of vector?
My statistics professor says: Let $X_n \xrightarrow{d} X$, $Y_n \xrightarrow{d} y$, where $y$ is some constant. Suppose for generality that $X \in \mathbb{R}^n$, and $y \in \mathbb{R}^m$. Then $$\...
0 votes
0 answers
230 views
What does the Grenander condition imply about the data-generating process of $(y_i, x_i)$?
Consider a correctly specified linear model $$ y_i = x_i^\top \beta + \varepsilon_i,\quad i=1,\dots,n, $$ where the errors $\varepsilon_i$ are independent with zero mean and finite variance. ...
2 votes
0 answers
71 views
Simple birth process with discrete time - limiting distribution
I previously asked this question at math.stackexhange. Suppose you have a population $X_n$ at integer time $n$ where the probability that each individual independently produces another individual at ...
2 votes
1 answer
191 views
Monotone Convergence Theorem for a Linear Function
According to the monotone convergence theoerem (Beppo Levi), for any monotone increasing sequence with random variable $X_n : \Omega \rightarrow [0,∞]$ with probability space $([0,1], \mathscr B([0,1])...
7 votes
1 answer
270 views
Do Language Model Training Data Satisfy Conditions for Independent Sample Paths and MLE Convergence?
A recent discussion suggests that even when the data generating process (DGP) is non-iid, if we can sample many independent sample paths (or cross-sectional blocks) from the same DGP, we can ...