All Questions
210,223
questions
0
votes
0
answers
6
views
Aggregated range for multiple confidence intervals
I am conducting a simulation involving 40 different stores in a specific area. Each store receives a varying number of customers in a given time period. I am calculating the expected final margin and ...
- 1
0
votes
0
answers
6
views
How to know when to use non-parametric coefficient confidence interval estimates for regression?
Say I have either logistic regression or simple linear regression and I am not sure if I have a moderate number of observations, $n = 40$.
How do I know when to switch to using a non-parametric ...
1
vote
0
answers
7
views
Diffrence in probability distributions of seperated groups
If I were to measure some quantitavie metric of a sample population and record its mean, and then I were to split by random selection all members of the population into two groups of equal size and ...
- 11
1
vote
0
answers
6
views
Does reverse causality from Z to Y violate exclusion restriction in IV?
I am estimating the effect of endogenous X on Y using 2SLS estimator with an instrument variable (Z).
X: Safety net program participation (binary), designed to increase household income
Y: Household ...
- 11
0
votes
0
answers
10
views
How to add multiple embeddings (layers) to LSTM layer [closed]
The similar question was asked before here https://stackoverflow.com/questions/52627739/how-to-merge-numerical-and-embedding-sequential-models-to-treat-categories-in-rn/52629902#...
0
votes
2
answers
39
views
Mean squared error (MSE) vs Least squares error (LSE)
From my understanding the only difference between MSE and LSE is that with MSE you divide the sum of squared errors by the total number of values to get an average rather than just using the sum.
This ...
- 2,091
1
vote
0
answers
17
views
Is there such a thing as an omnibus confidence interval?
One sample test statistics (i.e. for null hypotheses about the relationship between a population quantity and some constant term) can be inverted straightforwardly to produce a confidence interval for ...
- 28.9k
1
vote
0
answers
18
views
Frequentist vs Bayesian approach
Alice and Bob play the game - the rules of the game are not important, and after 8 rounds Alice has 5 points and Bob has 3 points. Every round one of 2 players gets 1 point and the winner of the game ...
- 11
2
votes
0
answers
16
views
Logistic Regression Power Analysis with Multiple Predictors
So I'm working on my dissertation and I'm trying to figure out a binary logistic regression power analysis to show how many participants I should collect. My proposed analysis is as follows and the ...
- 21
0
votes
0
answers
11
views
What are these interruptions in queueing networks?
I'm interested in modifications of Kendall queueing networks where agents in the network can be arbitrarily (according to a distribution or a deterministic function) moved from one part of the network ...
- 6,988
1
vote
1
answer
31
views
How to interpret survey data with demographic information?
I have little statistical experience, but am helping to run a community needs survey for my organization. Many of the questions have a yes/no or multiple choice answer format. For example, "Do ...
- 11
0
votes
2
answers
18
views
Survival analysis large number of small batches
I have a group of >10,000 right-censored survival cases, composed of a large number of small batches, with 1 to 7 cases in each batch. Failure rate overall is low, with 95% survival at maximum ...
- 232
-1
votes
0
answers
14
views
Self supervised learning [closed]
I want resources and code for using self supervised learning for counting small images in a picture . i already have a code for it but it is not sufficient to count small images .
0
votes
0
answers
12
views
How to model suspected piecewise-linear data with a lasso GLM
My data consist ~130 observations. Each observation has several thousand features (including many collinear or otherwise useless features) and a position along a single spatial dimension. Some sets of ...
- 63
1
vote
1
answer
9
views
Latent growth curve model: The variance-covariance matrix of the estimated parameters (vcov) does not appear to be positive definite
I have run a latent growth curve model in R using lavaan and got the below warning. It would be good to hear suggestions on how to resolve this warning. The full output is below.
Note that I dummy-...
- 115
0
votes
0
answers
5
views
incongruences between F-stats in the R cancor package
I'm using the R package candisc to perform canonical correlations.
Since my dataset has missing values (only 36 rows without any NAs out of 88 rows total), I have two options:
I can use the raw ...
- 33
0
votes
0
answers
7
views
If you are doing a replication study using the same instrument, can you statistically compare the results of the two studies
Scores on the Sexual Attitudes and Beliefs Survey in this sample will be significantly higher, indicating less comfort, than scores in the published national sample collected by Tennille et al. (2022)....
0
votes
1
answer
30
views
Which model for highly skewed data
The response variable in the dataset is highly skewed with a "ceiling effect". The errors of a fitted regression model, will thus also be skewed. I tried to fit a regression but as expected ...
- 240
0
votes
1
answer
31
views
How do I incorporate a patient's current age into a survival model?
I have a dataset with 10,000 patients, and for each patient, I have the following information:
Biological sex (male/female)
Baseline age (age at the time the patient joined the study)
Age at the ...
- 1
0
votes
0
answers
11
views
A common mathematical framework to introduce different "measures of distributional divergences/similarity"
Preface. I am going to ask here the same question ("A common mathematical framework to introduce different "measures of distributional divergences/similarity") that I asked on math....
- 168
0
votes
0
answers
6
views
Post-hoc sub-ANOVAS on ezANOVA - how to correct for multiple tests
Using a dataframe which looks like this (with 3 raws per "id"):
...
0
votes
1
answer
30
views
Tests that Quantify Deviation from Null Hypotheses
I have been delving into non-parametric tests recently, and I've come to realize that most of these tests offer only a partial perspective.
For example, lets say the underlying distribution is $\theta$...
- 235
0
votes
0
answers
6
views
How to model risk with presence-only data?
I'm working on a dataset of bird electrocutions. There are 300 instances of electrocuted birds and I have a range of environmental data that I want to input as my predictor variables. The aim is to ...
- 901
1
vote
0
answers
10
views
Should I adjust for inflation in a staggereded DiD with money as outcome and if so, how?
This question is currently making my head spin, and I haven't been able to find a discussion on it so far:
Suppose I am interested in the effect of an intervention, such as a healthcare reform, on a ...
- 11
0
votes
0
answers
9
views
Are there any theoretic or computational criteria to apply log transformation on a sample dataset?
I am developing an R shiny app that contains more than 1,000 variables as choices for the user. It plots a choropleth map and an histogram. However for many of those, the visual information is ...
0
votes
0
answers
10
views
Bounding the distance of empirical average from its expected value
Suppose we have three sequences of random variables, $(Y_n)_n$, $(W_n)_n$, and $(X_n)_n$ such that:
If $Y_n=a$, then $X_n=b$. If $X_n=b$, then $W_n=c$. That is
$$
1_{[Y_n=a]}\leq 1_{[X_n=b]}\leq 1_{[...
- 584
0
votes
0
answers
4
views
Complex forecasting cases
I am building a model to forecast some metrics. Those metrics are quite seasonal giving me good forecasts as shown below:
However, some new requirements dictate that I target those forecasts per ...
- 21
0
votes
0
answers
14
views
On the expressivity of latent variable models
Empirically, we have seen that VAEs can approximate very complex distributions. I am interested in knowing if there are any theoretical results showing how expressive latent variable models can be. ...
0
votes
0
answers
8
views
Expectation of constant matrix sandwiched between two random matrices
I have a $N\times P$ random matrix $X$ with i.i.d. coefficients from a standard normalized Gaussian $\mathcal{N}(0, 1)$. The corresponding Wishart matrix is
$$W = \frac{1}{P}X X^{\top}$$
Calculating ...
1
vote
0
answers
6
views
RecSys model performance stalling at 47% AUC and F1-Score. Is the problem due to ratio of users to items in my dataset?
I'm having trouble with making my validation metrics go down for the binary_crossentropy and go up for the F1-score and AUC. I've tried tuning my hyper parameters such as the number of latent features ...
0
votes
0
answers
7
views
Comparing to methods / models with human evaluators
I have 2 methods / models. I want to compare them using expert human raters so the amount of samples/tests must be small.
I want to figure out which is the better method.
What is a good way of doing ...
- 123
0
votes
0
answers
5
views
Best practice for comparing data between completers and non-completers?
I conducted a study which collected data on a brief one-time intervention at 3 timepoints (pre, post, and one-week follow-up). There were some participants who dropped out between these 3 timepoints. ...
- 1
2
votes
0
answers
17
views
Why not use a half-normal distribution as a prior for variance parameters in Bayesian estimation?
Typically, distributions with fat tails, such as the inverse Gamma or the half-Cauchy are used as prior distributions for the variance parameters.
I am trying to understand why do we need a fat-tailed ...
- 267
0
votes
0
answers
7
views
modeltuner hyperparameter tunining [closed]
suppose I have a multimodel produced using modeltuner approach with nrounds = 5000 with differet values for alpha alpha = c(0, 0.001, 0.01, 0.1, 1, 10, 30). I have done cross validation on the model. ...
- 1
0
votes
0
answers
28
views
Why Query, Key, Value matrices in Transformer implemented using nn.Linear() layer and use of FFN? [duplicate]
I am trying to understand the transformer archtiecture, in many of implementations the Q,K,V matrices are implemented using "nn.Linear()" layer. If I understood internal working of linear ...
- 1
0
votes
0
answers
17
views
Resources for Probabilstic forecasting
I was planning on learning probabilistic forecasting and im completely lost. Suggest some online resources. I have started with Probabilistic Forecasting and Bayesian Data Assimilation but its a bit ...
0
votes
0
answers
8
views
Contrasting Results in Regression Models: Flow vs Stock Variables in Policy Impact Analysis
I am conducting a study to analyze the impact of a specific policy on the number of businesses in each region. The policy was implemented in a staggered manner across different regions, and I'm ...
- 46
0
votes
0
answers
24
views
Difference between multi-head and single-head attention
Attention, as long as gradient calculations care, is two nested tensor multiplications and a softmax. I thought that, then, multi-head attention with $h=8$ and $d_k=64$ results in the same tensor with ...
0
votes
0
answers
48
views
Design of experiment in multiple regression
Suppose we have the following model of our environment:
$\hat{y}_t = e^{dayofweekeffect} * x_{1, t}^{\beta_0} * x_{2, t}^{\beta_1}$
which we can linearize into: $log(\hat{y}_t)= dayofweekeffect + \...
- 1
1
vote
2
answers
40
views
Why do we need to generate a random prediction in logistic regression? [closed]
I am trying to understand theory from my Model Identification And Data Analysis course at University.
The example I am referring to is the probability of predicting a heart attack. Essentially, from ...
- 19
0
votes
0
answers
26
views
Is it normal to have a sharp increase in validation error when using 10% of the data instead of something like 20-30%?
Scenario:
I'm training a relatively simple neural network to classify pairs of tabular datapoints (~150k), lets say drugs and diseases, whether they are related (positive) or not (negative). As I only ...
- 75
0
votes
1
answer
43
views
How to find the equation on a log-log scale plot (in R)?
I have plotted about 40 000 polygons (topographic depression dataset data) according to their area and volume (see plot below) by the code below:
...
- 1
0
votes
0
answers
33
views
How to aggregate survival type of data to single measure independent of time?
Thank you for the opportunity to ask this question. Since I do not speak fluently (still learning) the language of mathematics, I explain this in plain English. I understand this is too ideal but I ...
- 267
1
vote
1
answer
60
views
Calculation of multivariate probability mass function
How to calculate the following multivariate probability mass function:
$P(X_1-X = n, X_2-X = n, ..., X_{N-1}-X = n)$
Where $n$ and $N$ are positive integers, and $X_i$ and $X$ are iid random variables ...
- 11
0
votes
0
answers
34
views
The derivative of log likehood function [closed]
when I take the derivative of the log-likelihood function, it equals n (the sample size). So how can I solve the problem about the maximum likelihood estimator for the parameter λ . Could you give ...
- 1
0
votes
2
answers
28
views
Posterior of binomial and mixed prior
I'm currently studying posterior distribution with likelihood $y|\theta \sim B(n,\theta)$ and mixture of prior distribution $\theta \sim \pi Beta(\alpha_1, \beta_1) + (1-\pi)Beta(\alpha_2, \beta_2)$. ...
- 101
2
votes
1
answer
165
views
Is batching needed for the test set?
I'm just starting to learn about CNN (convolutional neural networks). Does the test data also need to be divided into batches, similar to how it's done with the training data?
- 21
0
votes
1
answer
25
views
Why the probability of rejecting the null hypothesis tends to 1 in this case?
Suppose we have an estimator $\hat\mu$ of population parameter $\mu$ and we know that
$$\sqrt{N}(\hat\mu-\mu)\overset{d}{\to}N(0,1).$$
We are interested in the following hypothesis scheme:
$$H_0: \mu=...
- 141
0
votes
1
answer
21
views
On the structure of Iterative Reweighted Least Squares(IRLS)
In Iterative Reweighted Least Squares (IRLS) algorithm, an optimization problem with the weight treated as known is solved in each iteration during solving the main optimization problem. For instance, ...
- 345
0
votes
0
answers
10
views
Determining change in underlying variable to reach 80th percentile in metric
I have a dataset of bus routes and their run times. The dataset contains the time variances of bus stops from the schedule. link to subset of data
I use some rules to classify each stop as being ...
- 119