Mathematical re-expression, usually nonlinear, of data values. Data are often transformed either to meet the assumptions of a statistical model or to make the results of an analysis more interpretable.
0
votes
0answers
44 views
“system is exactly singular” in R function BoxCox.ar
I'm trying to perform a Box-Cox transformation on some financial data (SPY).
The BoxCox.ar function (in the package TSA) gives me the following error:
...
0
votes
0answers
52 views
Variable Transformation for calculating mahalanobis distance
I am working with health insurance claims data. I am trying to calculate the mahalanobis distance to explore for possible outliers.
Variables that I am using are:
1) % of business dollars for a ...
0
votes
0answers
47 views
Normalizing SVM predications to [0,1]
I have trained an linear SVM which takes a pair of objects, computes features and is expected to learn a semantic similarity function between objects(we can say that it predicts whether the two ...
0
votes
0answers
39 views
Taking the cube root before a correlation when comparing quantities usually bellonging to a skewed distribution?
I was trying to reconcile data the other day just by looking at the cross correlation to see how well it lines up and it was suggested to me that I first apply a cube root transformation given the ...
0
votes
0answers
41 views
What do I need to do svm train data as preprocessing?
I know I need to do some kind of normalization to the data but I am not sure which method is actually suitable. Do I need to do just fitting the values into the interval [0,1] or z-score ...
0
votes
1answer
40 views
General rules for forming groups for analyses
I am analysing EEG data. I have data from 19 electrodes from 25 participants divided into two groups (11 and 14 subjects). I asked my student to compare this two groups with some statistical test. ...
0
votes
0answers
38 views
Question on re-indexing data for graphing
A file contains data for 1975-2012 of housing prices across a panel of countries.
However, it's indexed to 2005, so each country's housing price series converges to 100 in 2005, then they spread ...
0
votes
0answers
102 views
Data transformation for PCA
I'd like to run a PCA (Principal Component Analysis) on my data, but I have a number of registries of some species as a dependent variable and 5 different variables of habitat (altitude, slope in ...
0
votes
0answers
42 views
When to use the raw dataset as opposed to a transformed dataset for computing divergence?
Let us assume I have a set of observations:
Dataset 1: Raw
$A = [a_1,a_2,a_3,a_4,...]$
$B = [b_1,b_2,b_3,b_4,...]$
One assumptions before I proceed: Range of the values that the random variable ...
0
votes
1answer
63 views
Do you have to transform the units? [closed]
Im new to the world of statistics and analysis. Do you have to transform the units of exchange rate data(99Q1=100) and interest rate (%) before using in regression ? I would like to investigate the ...
0
votes
0answers
78 views
Transformation for percentage data >100%?
I'm running GEEs models on percent data. For reasons that don't matter, some percents are >100. The data are not percent change.
Any thoughts on an appropriate transformation?
Thanks!
0
votes
0answers
35 views
How to discretize training and test files to not encounter inconsistency in data?
I have a problem in discretizing my data. My data comprises of two parts: training data and test data. I discretized training data using some parameters of equal-width binning and used the same ...
0
votes
0answers
75 views
Removing noise and distortion from data
I have hundreds of data with peaks which look like this:
My question
On the left and right there is noise which you can see doesn't look anything like the usual peaks. My question is, how I would ...
0
votes
0answers
88 views
GLM quasi family with log transformation?
I am working on my thesis analysis, and I have some error data that's right-skewed. I log-transformed it and ran glm on it (gaussian, identity in R) weighted by sample size, and my data is still ...
0
votes
0answers
106 views
R- replace values in a matrix with the average value of its group? Q2 [closed]
I realised I should have been more specific in my question so let me re phrase.
how would you do this when the number of columns and rows in each group (and indded in each mxtrix) is unknown and ...
0
votes
0answers
69 views
How to transform an independent variable with parabolic shaped logit plot in logistic regression?
I am building a logistic regression model. I have created some ratio variables. When I look at the logit plot (log odds) of these ratio variables, some of them follow parabolic shape. I am wondering ...
0
votes
0answers
55 views
Calculate moving average of given variable list from AA to ZZ in automated syntax?
Hello and thanks for your suggestion.
I would like to create a list of columns like MACOL1, MACOL2 and up to MACOLn which contain 5 years moving average of a list of Tickers/Symbols/Variables using a ...
0
votes
0answers
34 views
How to handle unbalanced dataset on classes distribution?
I have a big data-set (KDD'99 dataset), with 3 million instances but has also really unbalance for the distribution of 4 classes. Is there any way to balance the data-set as keeping it consistent.
0
votes
0answers
145 views
What are the Best Web Based Open Source Data Exploration Tools [closed]
I am looking for a web based and open source data exploration tool. Some of the key features I am looking for include:
faceted search capabilities
ability to hopefully connect to more than one data ...
0
votes
0answers
64 views
Data transformations of scales
Could really do with some help from someone with more stats expertise than I have.
I have some data relating to a customer survey along a range of measures which are consolidated into a number of ...
0
votes
0answers
43 views
Output rescaling in nonlinear optimization
I'm working on a nonlinear optimization problem (using the L-M algorithm) and I've been reading about badly-scaled problems, in which parameters vary on orders of magnitude so they must be rescaled ...
0
votes
0answers
54 views
Pre-process classification data according to ‘amount of evidence’
I have an area which is divided into polygons of different sizes. Each polygon has the same associated features/predictors and I know whether something occurs within the polygon or not. If something ...
0
votes
0answers
253 views
What data structure is necessary for survival analysis?
I'm relatively new to survival analysis and try to get my data in the right shape.
I have two tables both concerning the observed individuals. If I just would use one of the tables, I would have ...
0
votes
0answers
140 views
How to combine unbound variables with very different frequency distributions?
I want to combine three unbound variables. Each variable is the score provided by three different algorithms. Each algorithm predicts the likelihood (score) that a specific interaction between two ...
0
votes
0answers
754 views
Interpretation lin-log regression where the covariate is log(x1 + 1) transformed
I have a lin-log regression model like
$$Y = b_0 + b_1 \log(x_1 + 1) + e.$$
The distribution of $x_1$ is very skewed, thus I use the natural logarithm to get a more Gaussian like distribution. ...
0
votes
0answers
209 views
What is the uncertainty when dividing 25 samples into 4 groups? [closed]
In brief, my question is: what is the uncertainty when I divide X data into Y groups?
In detail:
I have high-resolution count data which I've binned into hourly counts. The result is anything from ...
-1
votes
1answer
203 views
Logarithmic regression of form $y=a+b \log(x_1)+c\log(x_2)$ using R [closed]
How can I fit a logarithmic regression equation of form $y=a+b (\log (x_1)) + c(\log(x_2))$ on a data set using R?
Here the main concern is that data contain zeros multiple times, so R will give ...
-1
votes
1answer
149 views
Interpreting demeaned variables [duplicate]
Regression:
$$
\begin{aligned}
y&=\beta_0+\beta_1x, \\
\text{where }x&=\ln(z)-\text{mean}(\ln(z))
\end{aligned}
$$
How would I interpret the coefficient on $\beta_1$ for this regression? What ...
-2
votes
2answers
1k views
How to remove skewness from the population?
Just want to know the ways to remove skewness from the skewed population. I am working on logistic regression (in the insurance domain) for finding out the repurchase propensity of existing users. ...
-2
votes
1answer
169 views
How to perform boxcox transformation on data in R tool [duplicate]
Possible Duplicate:
How should I transform non-negative data including zeros?
Error in boxcox.default(y ~ x) : response variable must be positive
I want to perform box cox transformation ...
