Mathematical re-expression, often 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.

learn more… | top users | synonyms (2)

0
votes
0answers
6 views

Conducting a correlation when one of the covariates is a proportion

Is there anything that I should be wary of when conducting a correlation when one of the covariates is a proportion? I shall be running a Spearman rank analysis, correlating a continuous variable ...
0
votes
1answer
35 views

Linear regression with sine/cosine elements

How can you derive formula and regression coefficients for a regression model of a form $y(x)= A + B\, x + C\, \cos (2 \pi x) + D\, \sin (2 \pi x)$? I know that there are automatic tools who can do ...
0
votes
1answer
20 views

Whether to apply the logit transformation to proportional predictor variables in a multiple linear regression? [including proportions of 0.0%]

In a linear regression, I have a number of predictors variables that are expressed as proportions. The outcome variable is continuous. My residuals are not normally distributed, with a mild to ...
1
vote
1answer
43 views

What is the difference between a $\log_{10}$ and logit transformation?

What is the difference between a $\log_{10}$ and logit transformation? I have tried to find the answer elsewhere but cannot find a strict distinction.
1
vote
1answer
52 views

Does one need to transform percentages/proportions for a multiple linear regression?

I am aware that one should transform percentages and proportions when using them in an ANOVA, due to the values being bounded by 0 and 1. I have seen suggestions that the best transformations are ...
1
vote
1answer
48 views

Interpreting test results on log-transformed data

I have data that is not normally distributed. I can log-transform it to be normally distributed, and then perform, for example, a t-test. But how do I interpret the results of the t-test? Do I have ...
0
votes
2answers
23 views

Which data transformation can improve the performance of MLP neural networks for classification?

I am trying to fit several MLP neural networks models with a single hidden layer using the caret R-package. My main concern now is in the preprocessing step. My train data features (16 in total) are ...
0
votes
0answers
8 views

Error in eval(expr, envir, enclos) in apply(boxcox) [migrated]

I have a matrix of about 650 columns and for each column I want to find the optimal lambda for the boxcox transformation. I want to use the function boxcox from the MASS package, which outputs two ...
0
votes
0answers
17 views

Dealing with zeros when computing proportional change

I'm attempting to investigate the independence of the proportion of dividend payouts which is not linked to the movement of the stock index. The data I have is in the form of a list of dividend ...
1
vote
1answer
17 views

Transforming models in order to use linear least squares estimations

As a pre-exam question, I found a question asking to consider the following three models $$ y = \beta_{0}(x_{1})^{\beta_{1}}(x_{2})^{\beta_{2}}\epsilon $$ $$ y = \frac{1}{\beta_{0} + \beta_{1}x + ...
0
votes
0answers
27 views

Model design for queue position prediction

The goal of the model is to predict progression in position in a FIFO queue, given our current position and other predictor variables. This is progression in the sense that the number ahead of us in ...
1
vote
1answer
35 views

What is the origin of squaring centred data as way to model variances instead of means?

I recently came across this Answer by @mpiktas wherein he suggested a transformation of $y_i \rightarrow y_i^{\prime}$ $$y_i^{\prime} = (y_i - \overline{y})^2$$ followed by fitting a model for ...
0
votes
0answers
21 views

What is a good non cryptographic Hash for string feature translation?

What would be a good non cryptographic Hash function to use for converting string features to a numerical representation for feeding into machine learning algorithms? To explain the scenario my ...
0
votes
1answer
10 views

goodness of fit log transformed vs not log transformed

I have a relationship of two variables which is somehow log shaped. Now, I establish two models for this dataset, for one I log transform the dependent variable: ...
0
votes
1answer
29 views

Converting a 5-point Likert scale to 0 to 30 range

Hi thanks for viewing my question. In my research I want to adopt a measure from prior work and apply it to a new context. The question related to a 5- point likert-scale, however, further reading ...
1
vote
0answers
7 views

Counts from aggregating on a time period for poisson modeling

I have a data set where each observation is a count==1. I also have common demographic data for each observation such as SEX, AGE, etc. I also have a time stamp variable, HOUR. I would like to fit the ...
1
vote
0answers
22 views

Logit or arcsine transformation for proportion in meta-analysis

I am performing a meta-analysis with 137 study arms. From each arm I have extracted a proportion of a disease. Here are my proportions: ...
0
votes
1answer
23 views

GLMM with Gamma distribution vs. Gaussian distribution with log transformation

Is there really a difference in result if I use a GLMM with Gamma distribution vs. a model with a Gaussian distribution with log transformation? If so, how do I choose between the two methods? See ...
0
votes
0answers
4 views

Arithmetic operation on selective rows in R [migrated]

Here's what my data looks like: ...
1
vote
0answers
29 views

Which classification techniques perform efficiently under homomorphic encryption

I am reading a paper (pdf) on homomorphic encryption and its use in machine learning. This paper explores classification methods like Fisher Linear Discriminant Classifier (FLD) and the Linear Means ...
4
votes
1answer
99 views

Expected value of tangent of a normal random variable

If $z\sim N(\mu,\sigma^2)$ What is $E[\tan(z)]$ and $E[\tan^2(z)]$? Generally, it seems that the expectation does not exist. How about if $z$ is bounded $(0,\pi/2)$? Update: Theoretically, my ...
0
votes
0answers
41 views

Obfuscating sensitive data keeping data-properties intact

I am preparing a dataset for my academic interests. The original dataset contains sensitive information from transactions, like Credit card no, ...
0
votes
1answer
8 views
0
votes
0answers
9 views

Representative signal

I'm implementing machine learning with sensor data. I am having the problem that some sensors not always have good integrity, that is, not all data points arrive at destination because of ...
1
vote
1answer
24 views

Suggestions for appropriate transformations for Multiple Regression model

My residual plots look like this for each predictor: Does anyone have suggestions on transformations? I tried log transformations but some of my predictors have 0 so it doesn't work. Scatter plots for ...
2
votes
1answer
48 views

What to do if residual plot looks good but qq-plot doesn't, after transforming the predictor and response variables?

I'm doing a multiple regression model on environmental data and am stuck on checking the assumptions. Ultimately, I need to do a model selection for the data. There are various explanatory variables ...
0
votes
1answer
49 views

Using a value smaller than 1 for a $\log(x + C)$ transformation?

The data I am attempting to transform does not respond well to the traditional $\log (x + 1)$ transformation due to its distribution. The data ranges from 0 to 52.99183. The .RData file containing ...
0
votes
1answer
27 views

transforming exchange rate and inflation rate

I am testing some variables in percentage (exchange rate, inflation, and GDP growth rate), and I am a bit hesitate whether it is better leave them as percentage or transform them into log values. ...
0
votes
1answer
38 views

Interpretation of log(1 + x) transformed predictor

Interpretation of log transformed predictor neatly explains how to interpret a log transformed predictor in OLS. Does the interpretation change if there are 0s in ...
3
votes
1answer
100 views

Transform normal distribution to skewed distribution without changing its support

I've found many questions and answers about transforming skewed distribution to normal. This question might arise because the simplicity of working with normal data. But, is there any function that ...
0
votes
0answers
39 views

Downside to scaling and centering?

Bottom line up front: is there any reason not to center and scale continuous variables prior to model fitting for the sake of conducting model comparison? I'm conducting a model comparison on a large ...
4
votes
0answers
48 views

T tests on proportions - Wrong, but how wrong?

In psychology, and probably a number of other disciplines, it's common practice to test between-groups effects on a binary variable, such as accuracy, by aggregating data within participants, and then ...
0
votes
1answer
22 views

What is the distribution of a normalised (scaled) poisson distribution?

I have 5 groups of very different sizes. I want to know if various attributes are the same for the groups when I have corrected for the differences in size, e.g. ...
3
votes
1answer
59 views

Transformation among power-means

It is well-known that arithmetic and geometric mean are strongly related via logarithmic transformation, i.e. if we take arithmetic mean of logarithmic-transformed values we get the same as if we take ...
1
vote
0answers
15 views

Simple Path to Route Algorithm [closed]

I'm currently conducting research into subway paths, but stand in front of a problem, with no programming knowledge and an extremely short time-limit. Probably the question I am asking is trivial, ...
0
votes
0answers
25 views

Rewriting linear equation

So I have a linear equation produced in R: logBodyWt = -1.08968 + 1.22496 x logBrainWt And that's all groovy but there is a question in a module which asks me to "Rewrite your model as a non-linear ...
0
votes
1answer
50 views

Transforming a Random Variable's distribution to Normal using Z-Scores

I have a random variable and many observations of that variable. The random variable is not normally distributed; its distribution is unknown. However, to analyze this variable and construct a time ...
1
vote
1answer
31 views

GLM or arcsine and two-way ANOVA

I am trying to analyse data on how long deer have been vigilant in a 2 minute observational period and how this varies between males and females and also whether they were in the centre or edge of the ...
3
votes
1answer
194 views

Interpreting regression with transformed variables

I have conducted a linear regression analysis with four variables. The response, say $\#$ of eggs per 2000 hens, and one of the predictors, say temperature change, are highly skewed. I have hence ...
0
votes
1answer
45 views

What is the best data transformation for absolute zero inflated distributions?

I have 3 variables with the following distributions: What is the most appropriate transformation to make them as normally distributed as possible? This data is absolute zero inflated.
2
votes
0answers
18 views

Compare Procrustes values

I have two sets of spatial data which underwent a transformation. I'd like to compare the effect of the transformation on two sets of data to test the hypothesis that the transformation had a larger ...
11
votes
2answers
511 views

Transforming Data: All variables or just the non-normal ones?

In Andy Field's Discovering Statistics Using SPSS he states that all variables have to be transformed. However in the publication: "Examining spatially varying relationships between land use and ...
1
vote
2answers
29 views

How do I evaluate two models that have different (transformed) DVs?

I'm testing two different models that differ only in terms of how the dependent variable has been transformed (e.g., Model 1 DV = Y, Model 2, DV = √Y). I've read that AIC is not appropriate here -- ...
0
votes
1answer
43 views

So survey data cannot be normal distributed?

I am analyzing a data from survey. The data is from a 2X2 between subjects experiment design with 45 subjects in each of the four conditionsThe questions are based on a 5-point or 10-point scale. ...
3
votes
0answers
149 views

Standardized VS centered variables

I have found many useful posts about standardized independent variables and centered independent variables on stats.exchange.com, but I am still a bit confused. I am asking you an evaluation of what ...
0
votes
0answers
35 views

Practical beginners resource for building a dynamic OLS model

I need to model the current account balance of a country. The regressors are the real effective exchange rate, the domestic GDP and the GDP of the world. I am using data for 30 years (in logs). It is ...
2
votes
0answers
37 views

Untangling lump samp panel data?

Edit: Context: I am estimating persistence analog Heckman (1981) based on firm level data. The endogenous variable is the distribution amount of profits directed to the owners. To estimate ...
2
votes
1answer
20 views

One-mode network (data transformation)

I'm looking for a solution to perform network analysis among my data set. My database is shaped like this : Table 1 : ...
0
votes
0answers
24 views

Using the linear equation with log transformed data

If I have log transformed axes and then produce a nice linear regression model. How do I use the equation of the line? i.e. Can I use my raw data $x$ values to predict real values for $y$? Is the ...
5
votes
1answer
210 views

How can you convert a gamma distribution into normal distribution? [closed]

A region has 200 stores served by a single distribution center. Demand of X during lead time (the time interval between order placement of X and arrival of X) at each store is forecasted to be gamma ...