Most active questions

Ask Question
27 questions from the last 7 days
Newest Active Bountied 3 Unanswered
12 votes
3 answers
504 views

The Mcnemar test always seemed “odd” to me, and the more I dig into it, the more puzzled I become. I did look at some posts on CV (e.g. here, here or here) which also questioned the validity of the ...
jginestet's user avatar
  • 13.9k
10 votes
1 answer
473 views

I have a collection of many experiments. In each experiment I do a simple linear regression where I get a regression parameter $\theta_i$ and I also compute the standard error of $\theta_i$ which I ...
B Statistics's user avatar
  • 103
3 votes
2 answers
111 views

I'm working with big data time-series and am trying to detect outliers. Upon my research I've come across a variety of different simple methods (e.g. here and here) and I'm trying to understand the ...
Anke's user avatar
  • 389
5 votes
1 answer
102 views

I have a dataset that consists of fixed effects (time, pH, data type), a response variable (species richness - count data), and a random effect (mesocosm). Since I am working with count data collected ...
ramateur's user avatar
  • 93
4 votes
1 answer
53 views

I think that this formulation of Bayes Theorem is wrong, even though it is in a textbook. Shouldn’t both instances of P(B) actually be ...
Christopher Bottoms's user avatar
  • 141
4 votes
1 answer
151 views

I'm trying to understand how Lichess.org has devised their model for calculating the accuracy of a particular chess move given how it changes the evaluation of the position by a chess engine (the ...
Nelson O's user avatar
  • 143
4 votes
1 answer
134 views

I'll try to explain my problem: What I have: I built a Thompson sampler which given a data set it classifies data with a key and determines if it is considered a success or not, thus having for each ...
Alejandro Ferrante's user avatar
  • 41
2 votes
1 answer
60 views

I'm running a simulation study with multiple replications. The goal is to analyze the recovery of the random-effects parameters of a statistical model. The random‑effects parameters vary across ...
Watson's user avatar
  • 21
3 votes
0 answers
94 views

I’m sure I’m missing something obvious, but just can’t get started finding the sample size. I would normally post my efforts but absolutely no idea how to start to find the sample size, other than it ...
Ian's user avatar
  • 31
4 votes
1 answer
26 views

I’m currently working in a survival analysis setting with the goal of risk prediction. In earlier work, I used static (baseline) covariates together with Random Forest–based survival models, and I ...
Marco Simoni's user avatar
  • 41
2 votes
0 answers
70 views

I have $n$ $x$ values uniformly spaced between $-1$ and $1$: $$ x_i = \frac{2i}{n - 1} - 1 $$ for $i=0,\ldots,(n-1)$. I calculate the $y$ values: $$ y_i = ax_i + b $$ with $a = 2$ and $b = 3$. Next ...
Andy's user avatar
  • 909
2 votes
1 answer
35 views

In this analysis, I aimed to cluster a sample of customers based on how their purchasing attitudes changed before and after COVID-19. For this, I used a skew-t distribution for clustering. During the ...
09Bruna's user avatar
  • 501
0 votes
0 answers
56 views
+50

I'm trying to learn Transposed convolution, and I stumbled upon that animation (Blue maps are inputs, and cyan maps are outputs.): I don't understand how this makes sense (it probably is correct, it ...
FluidMechanics Potential Flows's user avatar
  • 233
0 votes
0 answers
34 views

I'm using post-PCA varimax rotation with code I developed in Python and comparing it to the SPSS result. The final result is the same, however, two things appear different: PC1 and PC2 swap positions ...
João's user avatar
  • 1
5 votes
0 answers
42 views

The exact transformation via quantiles is slow $$Z = \Phi^{-1}\!\left(F_{t_\nu}(T)\right)$$ A good approximation for fixed $\nu$ (optionally, cubic term could be added, it will be even better). $$Z = ...
Alex Craft's user avatar
  • 633

15 30 50 per page
1
2