Newest Questions
218,409 questions
0
votes
1
answer
24
views
Differentiating the effect of exposure and the level of the dose in cox regression models
I am working on a project where the goal is to assess the effect of a certain drug on the risk of developing a diagnosis later on in life after discharge from the hospital. The point is to find ...
- 3
0
votes
0
answers
12
views
What are the benefits of consistency loss in consistency model distillation?
When training consistency models with distillation, the loss is designed to drive the model to produce similar outputs on two consecutive points of the discretized probability flow ODE trajectory (eq. ...
- 151
1
vote
1
answer
14
views
Need help understanding and applying a Cross-Lagged Panel Model for my undergrad thesis (psychology)
I'm an undergraduate psychology student working on my thesis, and I'm struggling to fully understand how to use a Cross-Lagged Panel Model for my proposed research.
I'm usure about how to structure ...
- 11
3
votes
0
answers
53
views
Is it valid to use age again as a fixed effect in the model if the outcome already includes it?
I'm modeling a longitudinal risk calculation function using linear mixed-effects models (lme() in R, code below). The outcome is not a raw clinical measure — it's a derived risk score that already ...
- 529
0
votes
0
answers
20
views
Papers and research about brand awareness effects on revenues in b2b [closed]
I’m trying to find any relevant paper discussing any potential effects (or lack of) brand awareness on prevention in the b2b industries, specifically the software industry. My VP unluckily is not a ...
0
votes
0
answers
11
views
Are there different variations of partial eta-squared for a split-plot ANOVA?
There are two questions for this post:
¿Are there different variations of partial-$\eta^2$ for the between factor of a split-plot ANOVA?
If so, ¿when would you use one or the other?
In brief, when ...
- 6,682
1
vote
1
answer
37
views
Clarification of Linear Process Big O Bound
I'm working through some asymptotic theory for time series, and I came across the following:
Let $x_t$ be a sequence of random variables such that: (A linear process / moving average process): $$x_t = ...
- 135
-2
votes
0
answers
34
views
Linear Operator for Ridge Regression and Lasso [closed]
The linear Operator in scikit-learn regression methods is implemented as a matrix (ndarray or sparse matrix according documentation) but I'd like to use a general linear operator, similar is in scipy
- 1
0
votes
0
answers
25
views
interpreting the intercept and coefficients of fixed factors in mixed effects logistics model with weighted effect coding
This is the first time I used mixed effect logit model with effect coding, and I am a very confused. I have been trying to understand this for a few weeks, and would be deeply grateful for your ...
- 79
1
vote
0
answers
80
views
+50
Request: critique my framing of the statistics inference "pipeline" versus ML
I have been thinking about the meta/historical processes of statistics, how they differ from ML, and rapprochement between the fields. (This is motivated by interest in uncertainty quantification for &...
- 183
8
votes
2
answers
345
views
Why/when will negative binomial regression flip the sign of the effect from analogous Poisson regression, after covariate adjustment
First, to be clear, the issue mentioned in the title does not happen often and, in every parametric simulation I've tried, both NB and Poisson produce similar estimates, regardless of the type of ...
- 81
0
votes
0
answers
21
views
How can neural networks be used/trained to get a near continuous input and a real time output (forecast)?
So you have a neural network that predicts rain probability based on 10 different sensors. The trick is the sensors give readings some in 12 minute intervals some in 8 minute intervals and some in 3 ...
- 91
1
vote
1
answer
39
views
Legitimate use of GEE
I have some data relating to the number of attritions in a portfolio consisting of savings accounts over 120 months. I want to model them and then use the model to predict the next 6 months. I think ...
- 11
2
votes
1
answer
37
views
How to obtain the propensity score weights from Gradient Boosted Model in R
For a gradient boosted model with n data points using multinomial regression where the response variable is a categorical variable "class" with four levels (A, B, C, D), the probabilistic ...
- 31
1
vote
0
answers
19
views
How could I account for the uncertainty in the change of my variables over time in a soft clustering method?
I've extracted out the median and the 95 % CI for my expected response variables from a GAM model using fitted_samples from the ...
- 141