Tagged Questions

2
votes
1answer
60 views

Principal component analysis (PCA) on long-tailed data

(1) When doing PCA, do you assume the variables to be bell-shaped? Say if I have a bunch of variables, some are bell-shaped but some have characteristic long (right) tails (highly skewed and ...
1
vote
0answers
36 views

Calibration of probabilities in online learning (real-time learning) with Vowpal Wabbit

How exactly Real-Time Learning techniques deal with the problem of skewed distribution in dependent and independent variables? I am getting acquainted with Vowpal Wabbit and face this problem. My data ...
1
vote
0answers
46 views

Skewness in robust regression

I am doing a robust regression to predicted a left-skewed outcome. Do I still need to do a transform on my data before doing robust regression, or will that issue be taken care of by the robust ...
0
votes
1answer
83 views

Modeling a outcome variable heavily skewed toward 0

I am working with a data set to model student performance with various variables from the class/school/district/provincial level. Student performance is extremely low though--~70% of reading ...
4
votes
1answer
530 views

Transform continuous variables for logistic regression

I have large survey data, a binary outcome variable and many explanatory variables including binary and continuous. I am building model sets (experimenting with both GLM and mixed GLM) and using ...
2
votes
1answer
47 views

Small Sample, Low Baseline in DV, Interaction anyway?

Please assume that I have two metric independent variables (e.g., two blood parameters), and a dependent variable (e.g., a disease). On the DV, 0 represents the absence from the disease, 1 represents ...
0
votes
0answers
114 views

How to deal with a variable that ranges from 0 to 1 and the distribution has two spikes at these values with normal-like distribution in the middle.

I have the following setting (& would like to pick a model/or transformation that can help): dv is normally distributed continuous variable, all IVs are continuous, but one of them is the above ...