All Questions
205,205
questions
0
votes
0
answers
14
views
Split-split-plot design: Analysis and error terms
Can I have three levels of randomization and three error terms even when the replications are produced under same whole plot treatments under split split plot design? For example, three reps are ...
- 11
0
votes
0
answers
15
views
Constraint Linear regression in finance
Below you can find the problem that I am trying to understand. My main problem is to understand where do the reparametrization that they propose come from. Alternatively I have try to connect it with ...
- 217
0
votes
0
answers
22
views
Universal approximation related to activation regions
We assume we have an interval $I=[a,b]$. We define $C(I)$ to be the set of continuous functions on $I$. We further define the set of one-hidden layer neural networks
$$NN(H,\theta)=\left\{ f_{\theta}=\...
- 161
-1
votes
0
answers
14
views
R code for prediction of capital in a new company [closed]
Construct R code to calculate the capital required for a new insurance company
at ages 30.0, 30.1, 30.2, … , 54.9, 55.0. Display this
capital as an additional line on the plot.
i got an r code like
...
- 7
1
vote
0
answers
10
views
Identifying groups/patterns in a random dataset using Matlab [closed]
I have the datasets which may contain multiple patterns. The data needs to be classified based on grouping in the data. The figure below shows an example of the data. The circles around the data are ...
- 111
2
votes
0
answers
18
views
Theoretical Results for MICE Imputation
Is there any literature exploring convergence guarantees of the MICE imputation method for missing data? In practice, the method seems to work pretty reliably with different regressor but I can't seem ...
- 21
1
vote
2
answers
50
views
Regression Analysis for Proportional Data
I am going to try to simplify the context of my analysis into an apples/oranges scenario.
I have 30 baskets, each with 10 fruits. The 10 fruits are made up of a number of apples and oranges.
Each ...
- 13
-1
votes
0
answers
12
views
How to generate sequences given an arbitrary Cohen's kappa value [closed]
I could I create two sequences s,t of arbitrary numbers out of 0..N, length L elements such that
sklearn.metrics.cohen_kappa_score(s,t) ~= k
where k is a value I ...
- 303
0
votes
0
answers
10
views
How to concretely make predictions with ARIMA models? [closed]
I am currently studying ARIMA models and I think I understand the idea behind it. I've tried to predict future values of a stock price just to try out these methodologies. I am using log of the price ...
- 1
-1
votes
0
answers
8
views
Uniformly most powerful test for a poisson distribution [closed]
Let X X X n , , ..., 1 2 be a random sample from the pmf
0,1, 2, ..., ( 0) (; ) !
0,
x e
x f x x
otherwise
Find a Uniformly Most Powerful (UMP) Unbiased size α test for 0 0 H :θ =θ against
1 0 H :θ ≠
2
votes
0
answers
22
views
Gillespie's Algorithm's Connection to Kolmogorov's Forward Equations
I've been learning Gillespie's algorithm to simulate continuous time Markov chains. I understand how the algorithm is derived from the reaction probability density function
$P(\tau, \mu)$ = ...
- 21
0
votes
0
answers
9
views
Recalibration of Aleatoric and Epistemic Regression Uncertainty
i was reading about the problem of calibration of the credible intervals provided by bayesian neural networks
In this paper Recalibration of Aleatoric and Epistemic
Regression Uncertainty in Medical ...
- 259
0
votes
1
answer
7
views
Superlearner Without OOB Results
I'm interested in creating a superlearner algorithm. Unfortunately, my situation is such that I have access to the predictions of submodels I'm interested in on new data, but don't necessarily have ...
- 1
-1
votes
0
answers
11
views
Estimating standard deviation of a posterior generated by importance sampling MC uncertainty propagation [closed]
If I want to the esimate the statistical properties of a black-box model with uncertain parameters with known distributions, I can quite easily run an MC simulation to generate a histrogram of model ...
1
vote
0
answers
53
views
Reversible-jump MCMC for knot selection
Let $\{Z(\boldsymbol s):\boldsymbol s\in\mathcal D\}$ denote the Gaussian spatial random field on a spatial domain $\mathcal D\subset\mathbb R^2$.
Suppose that at $N$ locations, we have observations $\...
- 1,720
0
votes
0
answers
7
views
Inference with LSTM Seq2Seq for numeric data
I am adapting this great notebook that uses an LSTM seq2seq model for machine translation for electric signals. Specifically, I have couples of signals, and I want to use a similar model to map from ...
- 56
0
votes
0
answers
11
views
Gamma Distribution MLE After New Condition
I found the MLE of $\theta$ where $(x_1,...,x_n)$ is a sample from a $Gamma(\alpha, \theta)$ distribution where $\alpha>0$ is known to be $\frac{\alpha}{\bar{x}}$. However, suppose it is now known ...
- 155
0
votes
0
answers
26
views
Distribution of Poisson Sample Variances
Understanding that the variance of a sample of normally distributed random variables is chi-squared distributed with mean = population variance, what distribution describes the variance of a sample of ...
- 121
0
votes
0
answers
12
views
Understand whether any items are ranked significantly higher/lower in a survey using likert scale questions?
Say I have a survey asking a single group of 50 participants to rank the importance of 10 different aspects of using a website.
E.g., How are important are the following when using a website:
How ...
- 1
0
votes
0
answers
17
views
Why does a RM ANOVA require more subjects than levels?
I have never completely understood the theory behind why you need to have more subjects than levels in a RM ANOVA. For example, I was using the package "ez" to run an ANOVA, and got an error ...
- 33
0
votes
0
answers
45
views
Comparing the AUC of two models by using a combination of nested cross-validation and bootstrapping
Main question:
I have an imbalanced binary labeled dataset (6% positive labels) and two different methods of training a predictive model for binary classification (e.g. Tree Model vs. Neural Network), ...
- 13
0
votes
0
answers
14
views
Interpreting cubic splines graph where plot doesn't go to final knot
I have this plot where I found that the best degree of freedom is 8, as it minimizes the SSE when predicted from the training data. However, the graph does not go into the final 8th knot in the spline....
- 1
1
vote
1
answer
19
views
What kind of test should I run in SPSS/Jamovi to analyze a Randomized-Controlled trial? I have 3 groups and 2 time points (and small sample sizes)?
I have 3 groups:
Intervention 1 (n=6)
Intervention 2 (n=9)
Treatment as usual (n=12)
And I have 2 time points (pre and post intervention)
What kind of test do you recommend? Thank you!
- 11
0
votes
0
answers
8
views
Clustering sparse dataset with mix of continuous and categorical variables
I am trying to cluster sparse heterogeneous datasets containing demographics and diagnosis variables ( mix of categorical and numerical variables).
How should I start my clustering endeavors ? start ...
0
votes
0
answers
11
views
0
votes
0
answers
18
views
Optimizing a Laplace distribution's scale parameter for rejection sampling in R
I am using the Laplace distribution (location = 0, scale = b) to sample from a standard normal distribution. The normal distribution ranges from -1 to 2. I am using the rejection sampling method. In ...
- 61
0
votes
0
answers
8
views
Comparing two binomials with with partially matched sample
Imagine a scenario where I want to understand a population's support for a political candidate. I sample n=500 people randomly with replacement and ask them if they want to vote for candidate A or B. ...
- 159
0
votes
0
answers
14
views
Mediation analysis in mixed model ordinal logistic regression
For my thesis i want to perform a mediation analysis in a mixed model ordinal logistic regression.
y = survey data (ordinal variable)
x = year (2021 data compared to 2020 data)
...
- 11
0
votes
1
answer
24
views
Choose optimal lags in months for annual data
I try to forecast annual monthly price changes using annual monthly X changes. To choose the best lag, I run the VAR model and aim for the minimal AIC value. The problem is that the price is ...
- 111
1
vote
1
answer
18
views
Propensity Score Matching and Regression
I'm currently writing a undergraduate dissertation about the impact of participation in IMF programs on economic growth, and as part of it I'm trying to control for selection bias. Based off my ...
- 11
0
votes
0
answers
35
views
Fitting a 3D GMM in a 3D space is equivalent to fit a gaussian in each 1D coordinate?
I have a 3D data set data represents positions in X,Y,Z space. The positions are generated by a Poisson model. I would like to filter out outlier positions, i.e., positions that are farther than the ...
- 1
1
vote
0
answers
10
views
Age Adjusted Prevalence at region level with only country-level population distribution
I'm trying to calculate age-adjusted prevalence for a bunch of different chronic diseases from hospital data in a specific area and I'm having some difficulty. I have total country level population, ...
- 11
0
votes
0
answers
9
views
Error in inla code [closed]
I am running the model using inla. It gives the error mentioned below. I am actually running a landslide susceptibility model on slope-unit shapefiles. Can you help ...
0
votes
1
answer
41
views
Dealing with violation of linear regression assumptions
I have a data set where some extreme, but not nonetheless important observations are present which prompts violation of the linear regression assumptions of normality and constant variance. The ...
- 229
16
votes
3
answers
1k
views
Should the y-axis on a survival plot go from 0 to 100 even if the lines are all above 0.9?
I am reviewing an article that includes a survival plot, with % survival on the y-axis and time on the x-axis. The y-axis goes from 0 to 100, but the two survival curves are both always above 90%.
I ...
- 97.5k
1
vote
1
answer
20
views
Why a small RSS indicates good linearity in general linear regression?
Consider a generalized linear regression problem where $EY=Z\beta$.
The Residual Sum of Squares (RSS) is $\text{RSS}:=\xi^T\xi$, where $\xi:=Y-\hat{Y}=\{I-Z(Z^TZ)^{-1}Z^T\}Y$ is the regression ...
- 199
1
vote
0
answers
23
views
Explainable AI - Noise in gradients and embeddings of large language models
I am doing experiments related to explainable AI. I have two BERT models - the standard bert-base-cased and a distilled ...
- 11
0
votes
0
answers
12
views
how to interpret the result from aregImpute () in the Hmisc package and how to interpret the NK value in their provided example? [closed]
I was just going though the document in aregImpute () function in the Hmisc package, the example was as below:
...
0
votes
0
answers
14
views
Which ANOVA in R: two way, nested, 2x3 mixed design?
I'm pretty novice in R, but I have to conduct following analysis, that include impact of two Cd treatments (without and with ascorbic acid = A) on several plant anatomical traits. Plants were sampled ...
- 1
2
votes
0
answers
44
views
Comparing the means of two groups with different sizes
I am doing an statictical study over ultra-marathon runners (100 km distance) where I have a large number of data points (race records) corresponding to the average race speed of different runners ...
- 21
-1
votes
0
answers
10
views
Significance test using r studio [closed]
used to be that 50% of the target population had tried marijuana, does this
data indicate an increase in marijuana usage? Do a significance test of
proportions to decide.How to extract the pop size ...
- 11
1
vote
1
answer
24
views
Logistic regression and confounders or mediators
For a researchproject I would like to use the logistic regression model.
I look at the relationship between SES (categorial) and participation in training (dichotomous). Now there are several ...
- 13
0
votes
0
answers
9
views
How can I help my model's batch-normalization layers converge?
I have a very deep convolutional network that I am training and found the batch normalization layers to fail to learn a good representation of the data.
My dataset consists of several subsets of ...
- 270
0
votes
0
answers
48
views
How did deep learning overcome numerical problems associated with earlier ANNs? [closed]
From my understanding, the basic design of an artificial neuron has remained essentially the same since the 1960s. Before the bloom of deep learning models in ~2010, there were two obstacles to deep ...
- 101
0
votes
1
answer
42
views
Why the means fluctuate so wildly when using models with gamma inverse and identity? It's like taking a trippy journey
My dependent variable is reading time. My two predictors are categorical.
I conducted a lmer model with the default family and the performance package indicated that the response distribution fits ...
- 57
0
votes
1
answer
32
views
Is it possible to use some form of curve identifcation algorithm or model in R to identify a curve based on data from three different treatments?
I was wondering if it is possible to train a model or algorithmn to identify a curve shape based on experimental data.
Say we have 3 treatments 0 mM sugar, 1 mM sugar and 10 mM sugar and three ...
1
vote
0
answers
16
views
Calculate standard error from confidence interval obtained for standardised incidence ratio
I would like to do a meta-analysis and pool data for standardised incidence ratio (SIR). I have the estimates for SIR and the corresponding 95% confidence interval (CI) for all studies. The CI are ...
- 215
1
vote
1
answer
19
views
How to estimate survival probabilities by assessing covariates in a multivariate Cox proportional hazards model?
I'm working through the examples for Cox proportional hazard models provided in http://www.sthda.com/english/wiki/cox-proportional-hazards-model, and I am on the last example labeled "Visualizing ...
- 203
2
votes
0
answers
34
views
Posterior predictive distribution for Bernoulli (and categorical)
I'm trying to confirm something I've tried to figure out about the posterior predictive distribution for Bernoulli vs. Binomial (and categorical vs. multinomial) random variables after a Bayesian ...
- 27.2k
1
vote
0
answers
18
views
Including Random Slopes for Variables That Are Not Specified as Fixed Effects
I am interested in whether it is ever logical to specify a random slope of a variable that is not listed as a fixed effect in the model. For clarity, I have provided an example below.
10 Participants ...
- 43