Stack Overflow
Stack Overflow

Questions tagged [multivariate-testing]

Multivariate testing (aka multi-variable testing) is hypothesis testing in the context of multivariate statistics

257 questions
13
votes
2 answers

Multivariate Outlier Detection using R with probability

I have been searching everywhere for the best method to identify the multivariate outliers using R but I don't think I have found any believable approach yet. We can take the iris data as an example as my data also contains multiple fields…
Duy Bui
  • 1,348
  • 6
  • 17
  • 38
9
votes
2 answers

Does scikit-learn perform "real" multivariate regression (multiple dependent variables)?

I would like to predict multiple dependent variables using multiple predictors. If I understood correctly, in principle one could make a bunch of linear regression models that each predict one dependent variable, but if the dependent variables are…
CSquare
  • 624
  • 6
  • 16
8
votes
1 answer

How to effectively use Route53 for online experiments?

As a product owner for a 2million+ unique per month site, I want to do some A/B testing that I can track with Google Analytics goals, without paying the high fees for other online testing services. Using Google's own Content Experiments requires…
ljs.dev
  • 4,449
  • 3
  • 47
  • 80
7
votes
6 answers

Alternatives to GWO (Google Website Optimizer)?

We're using GWO (Google Website Optimizer) now. The multivariate and A/B testing is exactly what we need and works great from the perspective of showing the variations to the users. However, we have several issues that make me want to use a…
at.
  • 50,922
  • 104
  • 292
  • 461
6
votes
1 answer

Adding Independent Variables to Prophet Package

There is an R package called prophet which is very good. It is a generalized additive model. The dependent variable is the the metric you are trying to solve and the independent variables are: the growth function, seasonality function, and a…
nak5120
  • 4,089
  • 4
  • 35
  • 94
6
votes
3 answers

Algorithm to optimize multiple variables more efficiently than trial-and-error

Google's results on this seem to require more advanced maths than I'm familiar with (and I might not be smarter than a fifth grader, but I don't intend to find out). I'm looking for a general way to solve multivariate optimization problems,…
Paul Smith
  • 3,104
  • 1
  • 32
  • 45
5
votes
2 answers

How to create a boxplot for multiple dependent variables from the WeightLoss dataset?

I'm trying to make a boxplot from the WeightLoss dataset from the car package. The variables of interest are separated by month, so I made boxplots by month separately, with all the groups (Control, Diet, Diet and Exercise) showing. I only want to…
struggling student
  • 53
  • 5
5
votes
3 answers

A/B Testing with apache and mod_rewrite

Tried searching for this but my google-fu is lacking today. So I have 2 versions of site, in /var/www/vhosts/testa.mydomain.com/httpdocs and /var/www/vhosts/testb.mydomain.com/httpdocs where each documentroot is pretty much a complete site…
David Shields
  • 596
  • 1
  • 12
  • 34
5
votes
2 answers

R - Modelling Multivariate GARCH (rugarch and ccgarch)

First time asking a question here, I'll do my best to be explicit - but let me know if I should provide more info! Second, that's a long question...hopefully simple to solve for someone ;)! So using "R", I'm modelling multivariate GARCH models based…
cmembrez
  • 53
  • 1
  • 2
  • 7
4
votes
1 answer

How to color code scatter-plot of PCoA

So I am new to this. I need to run PCoA on the following data matrix. I am able to run my analyses using ADE4, labdsv, Ginko, Aabel softwares. Whats bothering me is how to color code the labels in the scatter plot. My matrix is a presence/absence…
Lord Voldemort
  • 199
  • 1
  • 2
  • 8
4
votes
0 answers

Improper priors for bayesian multivariate generalized linear models in R

I am trying to run a bayesian multivariate generalized linear model with OFT1, MIS1, wt, and g.rate as the response variables, grid, collar, sex, fieldBirthDate, and trialnumber as the predictor variables, and sq_id as the random effect. My data…
Blundering Ecologist
  • 1,199
  • 2
  • 14
  • 38
4
votes
0 answers

Add indval values on a multivariate regression tree

I used the mvpart package in R to generate a multivariate regression tree. To determine the indicator species responsible for the split, I used the indval command in the labdsv package. My question is, how do I insert my indicator species into my…
Tim Quimpo
  • 85
  • 1
  • 7
4
votes
2 answers

Extracting Multivariate Tests from the output of Anova or Manova function from car package

I wonder how to extract the Multivariate Tests: Site portion from the output of fm1 in the following MWE. library(car) fm1 <- summary(Anova(lm(cbind(Al, Fe, Mg, Ca, Na) ~ Site, data=Pottery))) fm1 Type II MANOVA Tests: Sum of squares and products…
MYaseen208
  • 22,666
  • 37
  • 165
  • 309
3
votes
1 answer

Are there any Rails gems/tools/templates to sandbox experimental features for split-testing?

We want to set up an easy mechanism for engineers to throw experimental code and features into our app, in order to try out new things for a sub-group of users, do A/B testing on different app behaviors, and generally offer a sandbox environment…
Wolfram Arnold
  • 7,159
  • 5
  • 44
  • 64
3
votes
1 answer

Error/warning on running glm in R - Coefficients: (1 not defined because of singularities)

When I run this glm on model_df (dput below): model <- glm(outcome_variable_data ~ ., data = model_df, family = 'binomial') lrm <- summary(model) When I print lrm, I get the error: Coefficients: (1 not defined because of singularities) and Taunton …
Ishan Mehta
  • 326
  • 1
  • 9
1
2 3
…
17 18