All Questions

146,409 questions
Filter by
Sorted by
Tagged with
13 views

How do I appropriately control for a limiting/maximum value in regression?

I have a dataset where one variable is limited by the value of another. It is a study of participants with a particular disease; therefore age of disease onset, A, is limited by age of registration ...
30 views

How does weights argument in gam() to handle the heterogeneous variance issues

In my case there were multiple observations per Group(random effect) in a single Year. So I aggregate these cases by calculating ...
23 views

Penalize the MSE of half of predicted values more than the other half

I'm using MSE loss for an multi-layer perceptron that learns to approximate the target feature vector $[\hat{x_1}, \dots, \hat{x_N}, \hat{y_1}, \dots, \hat{y_N}]^\intercal$. The catch here is that I'd ...
139 views

Including a baseline risk for each participant to consider having a different number of data points in Cox model

We used the Cox model to associate environmental exposures with time to heart failure using cohort data. The following question has been raised: When using the extended Cox model, did you include a ...
67 views

The value of the Margin of Error E that corresponds to a 95% confidence level (z subscript bevelled alpha over 2 end subscript space = 1.96) for a random sample of size 694 and sample proportion p ...
11 views

Testing significant difference between two independent means

I have two groups within a dataset. One group completed one 10-point Likert, the other completed a similar but different 10-point Likert. Beyond simple descriptives, I'd like to identify whether one ...
20 views

Differences between cumulative link models (ordinal) and multinom (nnet) for fitting multinomial data

I'm trying to understand cumulative link models and how they differ from multinom models in R. Here's a simple example of a multinom model and plot output using the nnet package: ...
11 views

Correlation and skewness

I have a data set on which i want to run a machine learning algorithm , some of the columns are skewed. If I apply a transformation (lets say log) to those columns and I want to display the matrix of ...
28 views

16 views

44 views

Maximum Likelihood with dependent observations

In the context of a normally distributed dependent variable, the likelihood for a single observation is given as: \$L(y_i|x,β,σ2)=\displaystyle\cfrac{1}{√2πσ^2}e^{\displaystyle\cfrac{(y_i−x_iβ)}{2σ^2}}...