All Questions

Filter by
Sorted by
Tagged with
0
votes
0answers
2 views

How to initialize an encoder-decoder type of neural network that is used in image segmentation?

In this example: https://github.com/qubvel/segmentation_models.pytorch/blob/dcd19d676bdfbf73fc140d5b98d780f449b0a2f8/segmentation_models_pytorch/base/initialization.py It only initializes the decoder ...
0
votes
0answers
5 views

Does increasing the value of C in svm.LinearSVC leads to overfitting?

I have made an svm.LinearSVC model to classify images. Firstly, the features of the images are extracted by SIFT and then based on them the LinearSVC is trained. I have the following Python snippet: <...
0
votes
0answers
14 views

Why am I getting NAs in this calculation in R? [migrated]

While working on an Rcpp program, I used the sample() function, which gave me the following error: "NAs not allowed in probability." I traced this issue to the fact that the probability ...
0
votes
0answers
7 views

Implication of gaussian model with strictly positive data [closed]

On this site there are many messages underlining that a gaussian model is not the best choice to fit data that can assume just positive values such as count data, because it allows predictions to ...
0
votes
0answers
4 views

How do we define the kernel to calculate the acceptance ratio for Metropolis-Hastings Markov Chain Monte Carlo?

I am having a lot of difficulty understanding how to apply the algorithm to a real scenario. The part that confuses me is that we are looking for a target distribution (the real distribution of our ...
0
votes
0answers
7 views

How to generate several scenarios of ARIMA(p,d,q) Gaussian time series

I am wondering how it is possible to generate several scenarios of an ARIMA(p,d,q) time series with Gaussian noise and with an initial value for the start of the time series. Are there any packages to ...
1
vote
0answers
7 views

If a distribution contains a non-trivial unbiased statistic of zero, then this distribution does not have a complete statistic?

If a distribution contains a non-trivial unbiased statistic of zero, then this distribution does not have a complete statistic? Here is what it means Suppose we have a family of distribution $\...
0
votes
0answers
3 views

Select data points that follow a symmetric unknown distribution and also satisfies other restrictions

I have the same set of data points plotted on the figures below: the first figure is a histogram and the second one shows the data distribution over a grid/map. I want to select the data points from ...
-2
votes
0answers
6 views

uniform to exponential MATLAB implementation [duplicate]

first of all im not a native english speaker :) I am working on a project and I have countered with a problem. Based on the following function I want to have a function in matlab that does the ...
0
votes
0answers
4 views

How are the Cochran's test for inlying variance results interpreted?

I'm running several hypothesis tests to check whether I can assume homocedasticity in some independent data series. The R package outliers [1] offers the function <...
0
votes
0answers
3 views

Why models often benefit from reducing the learning rate during training

In Keras official documentation for ReduceLROnPlateau class (https://keras.io/api/callbacks/reduce_lr_on_plateau/) they mention that Models often benefit from reducing the learning rate Why is that ...
0
votes
0answers
7 views

Exposure or Independent Variable in count models?

I am fitting count models to test hypotheses and compute association strength (not interested in predictions). Each observation is a small hexagon part of a geographic tessellation of some country of ...
1
vote
0answers
5 views

Credit risk book reference

Credit risk is a beautiful field that relies on basic notions of statistics and stochastic processes. I have been studying it, and now I am trying to understand the market models such as KMV, ...
1
vote
1answer
24 views

If $X, Y$ are random vectors, is it true that $E[g(X,Y)] = E[E[g(X,Y)| \{Y: AY \geq b\}]]$?

Suppose $Y \in \mathbb{R}^n$ and $X \in \mathbb{R}^n$ are random vectors. By the law of iterated expectation, does the following hold? $$E[g(X,Y)] = E[E[g(X,Y)| \{Y: AY \geq b\}]],$$ where $g(\cdot, \...
1
vote
0answers
12 views

Simple point processes and the expected value

When considering simple point processes, how is $$P(t_{n+1} \in [t;t+dt]) = E[N([t;t+dt])]$$, where $N(A)$ is the number of points in interval $A$ and $dt$ is the length of an infinitesimal interval. ...
0
votes
0answers
13 views

Please verify my RNN/LSTM multilingual multi class text classifier approach

Can you please verify my approach for a multilingual multi class text classifier using RNN/LSTM? The dataset consists of authors (labels, response) and their letters (input data). The letters can be ...
0
votes
0answers
13 views

Kernel PCA stopping rule / criterion

I have been comparing dimensionality reduction methods, while performing KPCA, I didn't know what number of PCs I should retain, how many to take and decide : "there it is, this is the new ...
0
votes
0answers
12 views

False cross validation points

So I have a practice test I am attending on K-folds and it asks me to select the false statements regarding K-fold cross validation: ...
0
votes
0answers
12 views

What is the significance of missing value correlations?

Suppose, I have a missing value correlated matrix. Some features have high correlation. What does this imply? How this insight can help me decide to handle missing value in a dataset?
-1
votes
0answers
9 views

How to calculate eigen values from a 4x4 matrix without any software? [closed]

How to calculate eigen values from a 4x4 matrix without any software? The matrix is given below, A[1,]= 19 30 2 12 A[2,]= 30 57 5 23 A[3,]= 2 5 38 47 A[4,]= 12 23 47 68
0
votes
0answers
6 views

Testing for a linear relationship between a treatment value and outcome

Suppose there are five treatment groups, $D = 1, 2, ..., 5$, and also a control group $D = 0$. We are interested in the effect of the treatment $D$ on some outcome variable $Y$; and to this end, have ...
0
votes
1answer
22 views

2nd derivative of $\sigma^2$ in normal MLE

Many times I differentiated the MLE of the normal distribution, but when it came to $\sigma$ I always stopped at the first derivative, showing that indeed: $$\hat\sigma^2 = \frac{\sum(y_i-\bar y)^2}{n}...
0
votes
0answers
3 views

Data lineage/traceability in pipelines

I want to collect information about: 1) from which single data signals a feature is composed in a ML pipeline and 2) what data preprocessing operations are/were executed on a data signal. Does anyone ...
0
votes
0answers
14 views

Using Gaussian Process For Predicting with Confidence

I have a dataset of [(cluster of points, real location point)], which contains clusters of points (x,y) and for each cluster a real location point. My goal is given a cluster of points, predict where ...
0
votes
0answers
6 views

How to conduct a mixed ANOVA with group means only?

I recently came upon 2 questions about mixed ANOVA (1 within IV and 1 between IV). Having been working on it for a few hours without a clue brings me here to ask if anyone knows the solution. ...
0
votes
0answers
5 views

Is it acceptable to use Boostrap/Jackknife to estimate the variance of an MAP estimators?

Suppose we obtain a point estimate using a maximum a posteriori estimator $\hat{\theta}_{MAP}$. Note that I'm aware Bayesian approaches generally do seek point estimates, but suppose this is an ...
0
votes
0answers
10 views

which copula function is used in financial industry [closed]

There are so many copula clayton, guassian , frank , archimedian copula but which one is most used in the financial industry.
0
votes
0answers
2 views

How to combine multiple stratified sampling results?

I have done a multistage sampling by first dividing the population into some strata and then using system(or simple random) sampling to sample in each stratum. I calculated the proportions or means(...
0
votes
0answers
2 views

Acceptance criteria and sample size for paired semi-quantitative data?

I am trying to perform a comparison test on multiple variables, in order to compare 2 montages (A and B for example). Lots of variables are semi-quantitative, whose values are under a limit of ...
0
votes
0answers
11 views

Mixed effects model - level 2 differences

Panel data, showing respondents answers across two waves; ...
0
votes
0answers
11 views

Is there a distribution that does not hurt softmax? [closed]

I am using hyperopt. I generate 3 random numbers then feed it into softmax to calculate. However, if I use uniform distribution in range (1, 100) for example, if it generates (1, 1, 100) it will badly ...
1
vote
0answers
17 views

Why is the Kullback-Leibler divergence defined with a negative sign?

I am aware of Gibbs' inequality, but I still want to know why the Kullback-Leibler divergence is defined with a negative sign. Here is my reasoning so far: Let $X$ be a Bernoulli random variable with $...
0
votes
0answers
10 views

Tumour cells and ResNet

A patient is represented by a set of images (1000 at maximum) of his tissues of either healthy or tumour cells. A patient is classified as 1 if at least one of the images shows tumour cells. These ...
0
votes
1answer
7 views

What test can i use for this hypothesis? It has a continous variable and a categorical variable

I have two variables Financial literacy- It's a continuous variable with high and low scores Default(It means to Not pay their loan)- Yes or no (I can code this as 0 and 1) What test can I use to test ...
0
votes
0answers
4 views

WHICH weight matrix are shared in RNN and which change upon Time?

In my opinion there are basically 4 weight matrix in the RNN. SO there are different names given in different scenarios but let me point out what I know about RNN in very simple terms. Please correct ...
0
votes
1answer
29 views

ML estimator of $\theta>0$ is $\hat{\theta}_n=\frac{\sum_{i=1}^nX_i^2}{n}$ and $I(\theta)=\frac{1}{\theta^2}$. Show $\hat{\theta}_n$ is consistent

In this problem we have that $I(\theta)=\frac{1}{\theta^2}$ is the Fisher information for a general probability density function $f(x;\theta)$ and $X_1,..., X_n$ are IID random variables from this ...
0
votes
0answers
9 views

Validity and Meaning of Feature Importance in Neural Networks

I’m trying to identify the features of products which consumers are most passionate about through sentiment analysis of product reviews. While there are plenty of models which seem to be quite ...
2
votes
1answer
103 views

Why are means not relevant to binary variables?

Trying to learn Basic Statistics from the Coursera. At the time 29 second, the video says: Means are not relevant with such a binary variable. Why?
0
votes
0answers
14 views

nested logistic regression model [duplicate]

I had a dataset that consists of 20000 chess matches. In this dataset, there are columns and variables- such as the players' ratings- that might have an impact on binary data, a white player is more ...
0
votes
0answers
6 views

How to use Principal Components Analysis (PCA) to find overall orientation of polygons collectively?

I was advised to use the Principal Component Analysis (PCA) to find first eigenvector which gives the direction of the first principal direction. Principal Component Analysis (PCA) is a new concept to ...
0
votes
0answers
3 views

How to get group p-value from subjects' t-values in a random effect linear model

I know that for a single participant, the two-tailed p-value will follow pvalue = 2 * tcdf(-abs(t_value), dof); where tcdf is ...
1
vote
1answer
18 views

Intercept in lm() and theory not agreeing in simple linear regression example

I have data $y_i,x_i$ and the model $y_i=\alpha x_i^\beta + \epsilon_i$ where $\log{\epsilon_i} \in N(0,\sigma^2)$. Thus, I define $z_i=\log{y_i}$ and $w_i=\log{x_i}$ and my normal linear model ...
0
votes
0answers
8 views

Nested regression model

I had a dataset that consists of 20000 chess matches. In this dataset there are columns and variables- variables like the players’ ratings- that might have impact on a binary result, white player ...
0
votes
2answers
29 views

Why is least squared loss sometimes written multiplied by $\frac{1}{2}$?

The base least squares formula that makes sense to me is: $$\sum(y^{(i)}-h_{\theta}(x^{(i)}))^2$$ Where $h_{\theta}$ is the hypothesis function, $y^{(i)}\in R, x^{(i)} \in R$. Then sometimes I see the ...
2
votes
1answer
23 views

How to choose a model? Residual deviance or AIC

I have two models of logistic regression with the same variables in the first model I got: Residual deviance: 61.097 on 73 degrees of freedom AIC: 79.097 in the ...
0
votes
0answers
3 views

Regression analysis comparison of Betas with different dependent variables

I have a quite simple question but am suddenly not sure about whats correct. I have conducted two multiple regression analyses. In both analyses, I had the same predictors, but different dependent ...
1
vote
0answers
6 views

Read auto_arima summary from pmdarima package correctly [duplicate]

I run auto_arima model with seasonality from pmdarima python package in the following way: ...
1
vote
0answers
7 views

Proof of Autocorrelation function property

I am trying to intuitively make sense of a specific property of the autocorrelation function: $$ \lim_{\vert\tau\vert \rightarrow \infty} R_{XX}(\tau) = \bar{X}^2 $$ where $\bar{X} = \mathbb{E}[X(t)]$ ...
1
vote
1answer
6 views

Standardizing the target variable aka the dependent variable

I have standardized the independent variables(X) used in feature selection using Ridge regression. Do I need to also standardize the target variable(y)?
0
votes
0answers
9 views

Losing degrees of freedom for chi-square random variable

Let's say $Y=\alpha + \beta x + e$ is a normal random variable, with parameters $\alpha, \beta$ and a normal error $e$. When data points $(x_{i}, Y_{i})$ are taken $(i = 1, 2, 3, ... ,n)$, then the ...

15 30 50 per page
1
2 3 4 5
3478