All Questions

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

In reinforcement learning, after an action, the state does not change

After conducting an action, the state of the agent may change into a new state, also may not change. So is it still reasonable to formulate the problem by MDP and solved it by reinforcement learning ...
0
votes
0answers
3 views

Causal inference - difference between blocking a backdoor path and adding a variable to regression

I have just started this introductory course to causal inference. The DAG approach is completely new to me even though I come from an econometric background (though that dates back to 15 years ago). ...
0
votes
0answers
2 views

How to properly calculate the average across multiple correlations?

I'm trying to obtain an average across 3 correlations. Using Python, I obtain these correlations with: corr = df.apply(lambda s: df.corrwith(s)) which outputs: <...
0
votes
0answers
3 views

Merging survival data with time varying covariates

In merging the data in R the censored observations are merged well but the observed subjects are not. For example, the second subject had an event at time 0.546. How can I merge the time varying ...
0
votes
0answers
3 views

How to explain these jump-discontinuities in the expected stopping time of a SPRT?

Suppose a sequential probability ratio test (SPRT) with $$\alpha=P(\text{Type I error})=P(\text{Type II error})=\beta = 10\%$$ is used to decide between $$\ H_0: p=1/2\quad\text{vs.}\quad H_1: p=b\,$$ ...
1
vote
1answer
10 views

causal graph - counting the number of backdoor paths in a DAG

I am following "A Crash Course in Causality: Inferring Causal Effects from Observational Data" on Coursera. I am struggling at correctly identifying backdoor paths in causal graphs (or DAG ...
0
votes
0answers
4 views

Example of time series with constant variance+expected values but time-dependent covariance

I just started to learn about time series analysis and I want to understand stationarity. (Weak) Stationarity is defined as having constant expected values and variance and autocovariances that do not ...
0
votes
0answers
3 views

How to get sample size estimation for two ordinal variables analysed with a linear-by-linear association test?

We would like to confirm a previous result by establishing a new cohort of patients. I compared the distribution of patients among 2 ordinal variables (figure below). One is a biomarker in 3 ...
1
vote
0answers
16 views

How to do negative binomial regression with the rms package in R? [closed]

How can I use the rms package in R to execute a negative binomial regression? With the MASS package, I use the ...
0
votes
0answers
9 views

Plot two datasets on the same figure [closed]

I have tried to use t-sne library to visualize data. So I did the following to visualize one dataset: ...
0
votes
2answers
13 views

How to check for correlation between 5 classes (Likert ratings) and continous variable?

Apologies if the question seems basic or technical terms are used incorrectly, but I am not very experienced in statistics. I have collected data concerning different properties of objects, let's say ...
3
votes
1answer
23 views

How is it that CLT can be used for around 8 light bulbs?

I have been given the following problem. The light bulbs available have an average lifetime of 1000 hours with a standard deviation of 50 hours. How many light bulbs should we stock so that we can be ...
0
votes
0answers
7 views

Estimated marginal means with emmeans

I have a mixed linear model, for example, Model <- Values ~ A + B + C + (1 | id) + A:B + A:C + B:C I wanted to do analysis with "emmeans" a.k.a estimated marginal means, so I used these ...
0
votes
0answers
7 views

How to merge coefficients from Lasso Logit and Logit with different “structure” into one table or data.frame

first off, I am sorry if there was some previous question thats strongly related to this one and likely includes an answer, but the terms I used to look for it did not help. I have conducted an OLS ...
0
votes
0answers
8 views

interview question: ridge regression the out-of-sample performance never change when tune the hyperparameter?

I happened to an interview question: In Ridge regression, what does it imply if the out-of-sample performance never change however we tune the hyperparameter (the coefficient of L2 regularization)? ...
4
votes
2answers
43 views

Can Z values be thought of as the number of standard deviations?

I read about the 68-95-99.7 rule that shows I also read that a Z value of 1.96 gives a confidence level of 95% Is it correct to think of Z as the "number of standard deviations" ? Only I ...
0
votes
0answers
9 views

Analytical Leave-one-out prediction variance for Kriging

I make extensive use of Kriging (Gaussian Process regression) methods in my work especially using the leave-one-out error calculation that you can get from the Gram matrix. Background: To compute the ...
0
votes
0answers
5 views

Augmetation techniques for satellite image time series

I am considered to apply some augmentation for a set of multivariate data (satellite image time series data) in aim to perform a LULC classification task. However I have some issues and imagination of ...
0
votes
0answers
12 views

How much precission is required for custom p.d.f. to integrate to one in Stan?

I am in the process of writing a fairly complicated custom probability density function in Stan. The function is composed piece-wise like a spline, and it is impossible to get an integral of it with ...
0
votes
0answers
13 views

Recreating research paper with HMM and K-S test

I am trying to recreate this research: https://www.mdpi.com/1911-8074/13/12/311/htm My first question is when they present the regime breakdown: ...
0
votes
0answers
13 views

Demand forecasting task without demand column

I apologize for the naive question in advance, I'm completely new to forecasting. I have a Machine Learning demand forecasting task for a healthcare service. I have some columns such as date, ...
0
votes
0answers
12 views

How to calculate univariate conditional distribution of a trivariate gaussian

I am trying to find the conditional distribution of a trivariate gaussian. So here is a hypothetical trivariate gaussian: $$\mathcal{N}(\mu_{ABC},\Sigma_{ABC}),\;\mu_{ABC}=\begin{bmatrix}\mu_A \\ \...
1
vote
0answers
13 views

Alternatives to Rank Probability Score metric (RPS)

I'm looking for alternatives to RPS to evaluate if my model is "good", as I can't use the RPS (because I do not have the actual probabilities). My problem is a multiclass classification (30 ...
1
vote
0answers
9 views

Real-World, Operationalized Applications of Multi-Arm Bandits

Multi-armed bandits are wonderful and have lots of potential applications. However, I don't know many companies or real-world practitioners who have implemented bandit algorithms. What are some ...
0
votes
0answers
10 views

Pooling variance of two samples with sample means and sample variance [duplicate]

I am new to this so I don't have enough reputation to comment on the original post here. I have a similar problem with equal weighting, and have n = m = 3. I believe this means I need to use sample ...
0
votes
0answers
5 views

How to filter in R with subsets [migrated]

I have a dataframe with columns: coast, weight gain, length gain, release weight, release length. Coast is categorical ("E" or "W") and the other variables are numeric. I would ...
0
votes
0answers
6 views

Regarding autocorrelation in LMMSE

I'm trying to get my head around a problem from a previous exam in a course about stochastic processes. The problem is expressed as: Let X, Z1 and Z2 be independent random variables with mean 0 and ...
3
votes
1answer
28 views

What is a Q distribution?

In this 1967 paper by Hogben it is shown that the sample correlation coefficient $r=\frac{\sum_{i=1}^n(Y_i-\bar Y)(x_i-\bar x)}{\sqrt{\sum(x_i-\bar x)^2\sum(Y_i-\bar Y)^2}}$ is Q-distributed with n-2 ...
0
votes
0answers
8 views

Is this transformation to the input of an RNN “valid”?

I'm reading through some pytorch code published as part of a research paper. The input data is of the shape (batch_size, number_of_time_steps, number_of_predictor_variables, height, width). The code ...
0
votes
1answer
22 views

Should I use Spearman's rho or Pearson's r to estimate correlation between worker anxiety level and job performance?

I want to correlate the level of anxiety of workers (normal, moderate, severe, etc.) and their job performance (very high, high, moderate, etc.) what should I use?
0
votes
0answers
9 views

Importing Training Dataset into TensorFlow [closed]

I previously built a CNN using ml5.js. I've migrated to TensorFlow.js, due to its extensive documentation and additional features. I'm new to TensorFlow, and still trying to understand how to build a ...
0
votes
0answers
9 views

How can I evaluate my multiclassification model using cumulative gain?

I want to run a model for multiclassification problem and I am only interested in the top x% results (recommendation model). I think using the ndcg@1000 evaluation metric is the best for this purpose, ...
0
votes
1answer
15 views

Estimating robust variance without cluster id in survival model

I built a survival model with coxph. I have a large dataset (1 000 000 instances) and the global model is not proportional. It cannot be improved by introducing time-dependent coefficients or ...
0
votes
0answers
14 views

Predictive analysis model for growth

I am trying to create a model for predicting the weight of pigs based off their age, Using a few different calculators I established that the function seemed to be polynomial rather than exponential ...
0
votes
0answers
6 views

Proposal never gets accepted in mcmc-algorithm

What could be reasons for non-acceptance of a proposed parameter value in the mcmc-algorithm? In my specific case the sampler correctly goes towards regions of higher probability such that the ...
0
votes
0answers
11 views

what bayesian method to use to estimate posterior with this question (poisson -> binomial )?

Incidence of disease x = 0.5 cases per 100 person-years Sensitivity of a test to detect disease x, prob(postive test|disease x present) = 87.2% Specificity of a test to detect disease x not present, ...
0
votes
0answers
22 views

Pushing a normal distribution through the error function [closed]

I am interested in the output moments after pushing a multivariate normal variable $x\in R^D$ with $x\sim \mathcal{N}(\mu, \Sigma)$ elementwise through the error function $\text{erf}(x)$. I see that I ...
2
votes
1answer
55 views

Correlation between $x$ and $x^{2}$

Parts of my question have been answered on the website separately. I was trying to find a way to reconcile between the two. The two parts are: The correlation between $x$ and $x^{2}$ is not zero if, ...
1
vote
1answer
33 views

In MCMC, can I accept proposals from another MCMC process without trying to approximate the proposal distribution?

I'm trying to sample a Markov chain which takes proposal from another Markov chain. Normally one would have a proposal distribution one could sample from. However, say in this case the proposals come ...
4
votes
1answer
26 views

Confidence interval and p value from prop.test() in R contradict each other

I am running the following simple Z test for proportions in R: prop.test(x = c(10, 20), n = c(100, 500)) The results are as follows: ...
0
votes
0answers
8 views

ANOVA IN R ON REGRESSION SLOPES [closed]

I am trying to run ANOVA in R for comparing regression slopes. When I run the test I can develop the model using the command modro <- lm( variable 1 ~ var2*var3) Now I do model $coefficients t give ...
0
votes
0answers
14 views

Significant logistic regression but non-significant chi-square

I have a study design with one independent, categorical, variable with 5 conditions, and a binary outcome (0,1). When I run the chi square test, I see no overall effect of condition for the binary ...
0
votes
0answers
10 views

Can you write the correlation matrix of AR-2 (or AR-p)? [duplicate]

It is easy to write the autoregressive of order 1 (AR-1) correlation matrix: $$R_{k-1}=\begin{pmatrix} 1 &\rho &\rho^2 &\cdots &\rho^{k-2} \\ \rho &1 &\rho &...
1
vote
1answer
21 views

When are diagnostics not required for logistic regression?

Logistic regression models (generalised linear models with a binary response) are odd things. I am in the habitat of using randomised quantile residuals (R package statmod) for GLM diagnostics. I have ...
1
vote
1answer
16 views

Difference in slope in longitudinal study

I have a longitudinal study where subjects are measured at given time points and a response is recorded. Each subject belongs to one of three groups (A, B, C) and I'm interested in whether the slope ...
0
votes
0answers
28 views

A follow-up to 'The meaning of an analyt. result concerning the… mean of the square of a reciprocal of a norm. distrib. rand. variable'

This question concerns the same subject matter as this previous question of mine. However, a moderator felt that the questions I posed there are significantly different from the question I am about ...
0
votes
0answers
4 views

What is the advantage of Uplift modeling over the multiple comparison using experimental data?

The ultimate goal of the both methods should be getting the true treatment effect based on different treated groups(i.e.The interaction effect). However, what is the difference between comparing the ...
0
votes
0answers
16 views

PROBABILITY OF SURVIVAL [closed]

Owing to a medical condition, a man aged 60 is subject to the force of mortality πœ‡π‘₯ πœ‡60+𝑑 And πœ‡60+𝑑 β€²=πœ‡60+𝑑+0.05, π‘“π‘œπ‘Ÿπ‘Žπ‘™π‘™π‘‘β‰₯0 where, follows the AM196770 Ultimate table. Calculate the ...
0
votes
0answers
4 views

Using a pre-defined embedding layer in Tensorflow and avoiding updating its values [closed]

So in applying recurrent neural networks on texts, usually vocabularies are converted into IDs and then some embeddings. Are these embeddings obtained by ...
0
votes
0answers
32 views

Hurdle model: How to compare slopes?

I'm analyzing the change in seagrass cover (count data of shoots) between two years of different species. Therefore, I made a model similar to this: ...

15 30 50 per page
1
2 3 4 5
…
3659