Statistical Analysis Stack Exchange
Statistical Analysis Stack Exchange

Questions tagged [variance-stabilizing]

For questions about data transformations that aim to stabilize variance. See also https://en.wikipedia.org/wiki/Variance-stabilizing_transformation

25 questions
66
votes
1 answer

Why is the square root transformation recommended for count data?

It is often recommended to take the square root when you have count data. (For some examples on CV, see @HarveyMotulsky's answer here, or @whuber's answer here.) On the other hand, when fitting a generalized linear model with a response variable…
gung - Reinstate Monica
  • 132,789
  • 81
  • 357
  • 650
21
votes
5 answers

What could be the reason for using square root transformation on data?

What is the primary reason that someone would apply the square root transformation to their data? I always observe that doing this always increases the $R^2$. However, this is probably just due to centering the data. Any thoughts are appreciated!
MarkDollar
  • 5,575
  • 14
  • 44
  • 60
10
votes
5 answers

What other normalizing transformations are commonly used beyond the common ones like square root, log, etc.?

In the analysis of test scores (e.g., in Education or Psychology), common analysis techniques often assume that data are normally distributed. However, perhaps more often than not, scores tend to deviate sometimes wildly from normal. I am familiar…
Mike Wong
  • 377
  • 1
  • 4
  • 10
7
votes
1 answer

How do I find a variance-stabilizing transformation?

I wonder how to solve this classical problem: Recall that for a binomial proportion $\hat p$ based on a sample of size $n$ we have $$E(\hat p)=p$$ and $$\operatorname{Var}(\hat p) = p(1-p)/n.$$ Show that the variance-stabilizing transformation of…
Daniel Santa-Clara
  • 71
  • 1
  • 2
7
votes
3 answers

How large does a Poisson distribution's mean need to be to use normal distribution statistics?

As the mean of a Poisson distribution increases, the Poisson distribution approximates a normal distribution. I assume that once the Poisson mean becomes large enough, we can use normal distribution statistics. Therefore we can start saying things…
luciano
  • 12,197
  • 30
  • 87
  • 119
4
votes
1 answer

GLM vs square root data transformation

I am currently analysing some pretty awful/awkward data on the abundance of fish under three different "Hydro-Regimes" (5 abundance measurements for each regime - Short/Medium/Long). The current analysis plan had been a one way ANOVA. Looking at the…
user2037072
  • 39
  • 3
3
votes
1 answer

Underperforming SELUs - How to correctly constrain layer weights in TF/Keras?

The promise of SELUs and SNNs I first read up about the 'power' of SELUs on a machine learning blog post. The promise of a Self-normalizing Neural Network (SNN) sounds too good to be true; its ability to self normalise and self regularize internally…
Avelina
  • 809
  • 1
  • 12
3
votes
1 answer

How to do a bias-variance analysis on a machine learning modelling process

I searched on topics of the bias and variance trade-off and got back lots of questions with different levels of response. The information is scattering too much and unsystematic to answer my own question which stuck me. So I open a new question here…
LUSAQX
  • 453
  • 1
  • 4
  • 13
3
votes
0 answers

Relation between variance stabilizing transformations and effect sizes?

When researching effect size for proportions, in particular the paper Effect-Size Indices for Dichotomized Outcomes in Meta-Analysis, that at least two of the usual effect sizes are realy variance stabilizing transformations on the binomial…
Jacques Wainer
  • 5,032
  • 1
  • 20
  • 32
2
votes
1 answer

How do I prove the square root is a variance stabilizing link for Poisson?

I have searched google, and wikipedia, and have come up with nothing. If there are links that you could provide to help me figure out how to prove this, that would be very beneficial. Is it possible to do this by checking the approximated variance?…
Fire
  • 147
  • 1
  • 6
2
votes
2 answers

Model stability and variability

I am using polynomial regression to predict mean occupancy in a hospital unit using average length of stay (LOS) and arrival rate to the unit. I am using different percentages of training sets to train the model and 5 fold cross validation to pick…
Statwonder
  • 31
  • 4
2
votes
0 answers

What are some unstable classifiers?

In my understanding, classifiers that tend to overfit (high variance) are unstable. Two examples would be unpruned decision trees and k-Nearest Neighbors with small k. Can you suggest some more classifiers like this that would have high variance?
user191389
  • 95
  • 3
2
votes
2 answers

interpretation of boxcox with lambda equal 0

I am working on this non linear data set, and running my Box-Cox I find that the best value to use is $\lambda = 0$. If I understand correctly, $\lambda =2$ implies $Y^2$. Similarly, $\lambda = -0.5$ corresponds to $1 \over \sqrt Y$. However how…
rannoudanames
  • 740
  • 1
  • 5
  • 20
2
votes
1 answer

Transformation versus projection to Normality

Can anyone explain the theoretical consequences of a traditional variance stabilizing transformation such as sqrt(lambda) for the Poisson versus projection to a normal distribution and the pros and cons of each? I am familiar with the concepts of…
ashokragavendran
  • 409
  • 2
  • 6
1
vote
1 answer

Stabilizing the variation in a time series

Is it necessary to transform the data here in order to stabilize the variation in this series? I do not think it is. How "bad" do the fluctuations have to be before stabilization becomes necessary? I'm assuming a linear trend is suitable; not…
Chesso
  • 313
  • 1
  • 6
1
2