# Tagged Questions

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.

31 views

### Whether to transform non-normal variables prior to performing EM imputation?

I recently received the following email: I have a sample of 100 and approximately 6-7% missing data on each independent variable of interest, and non-normally distributed IVs. I have square root ...
69 views

### OLS robust to outliers

I am facing the following problem: I have a training sample and estimate a model on that training sample. My model is simply OLS: $y_t = a + \beta x_t + \varepsilon_t$. The model is estimated on ...
90 views

### Factor analysis across different levels of data aggregation

I have survey data for thousands of individuals from hundreds of towns. I want to identify factors underlying certain characteristics at the town level and the individual level. The individual level ...
80 views

58 views

### Locating a set of 5 geometrically constrained points within a cloud of points

What is the most efficient way to find a set of 5 rigid, coplanar, non-collinear points within a 3D point cloud of, for example, 100 points? (1) The configuration is specified by 2D coordinates (or ...
96 views

### Transforming data with both negative and positive skew

I am attempting to run a MANCOVA of memory assessment data. My IV has three levels (no memory impairment, moderate memory impairment, and severe memory impairment). The covariate is education. The DV ...
94 views

### When analyzing a difference for log-transformed data, when to take the log?

I am working with laboratory data that needs to be transformed due to skewness. It has been gathered at 2 time points and I am interested in the change from time #1 to Time #2. My question is, do I ...
109 views

### Bounded response variable [-1;1] - Should I transform it?

I am planning to use two response variables. One is bounded between 0 and 1, and I guess I can use a binomial (or related) error structure. The second variable is bounded between -1 and 1. I am not ...
29 views

### Differentiating experimental data

I'm trying to differentiate experimental data which are measured with time. However, the time increments are not equally spaced. I first obtained a trend line for these data and then did a linear ...
66 views

### Transforming two sets of test scores to be “comparable”?

Given 2 sets of test scores (the same students take both tests), I'd like to transform them such that they can be added to give a combined score. The 2 tests have different variances, so adding them ...
44 views

### Transforming data: correlate regardless of distribution

Is there a way to correlate data regardless of distribution? I know the Choleksy transformation is used for normally distributed data, but is there a general method that applies to any case? To ...
288 views

### PCA on log transformed data

I am about to conduct two Principal Component Analyses (PCA) on species abundance data and species composition data. I have about 12 different locations where abundance data for over 50 invertebrate ...
63 views

### How to reduce dimensionality of vector?

I have a set of vectors. I'm working on ways to reduce a n-dimensional vector to a unary value (one-dimensional), say (x1,x2,....,xn) ------> y This single value needs to be the characteristic value ...
25 views

### BoxCox Transformation for time series with multiple instances

I have time series data with multiple instances. For example, instances like (0.36,0.35,0.32,0.31,0.31,0.30,0.30,0.28,0.30) occur 20 times (20x9 array). I am wondering how to do variance stabilization ...
334 views

### xtlogit: panel data transformation's recast to double makes model incomputable (STATA)

I am experiencing a very peculiar problem in STATA. I have a panel dataset with 8000 groups and 4 million observations. I want to run a fixed effects panel binary logistic regression (xtlogit). As ...
52 views

### Can one apply different transformations to the same variable within different analyses?

My stats questions concerns the appropriateness of using different transformations of the same variable within different analyses (within the same larger study). My research involves emotional ...
196 views

### Presentation of summary log-transformed data aiming at easier interpretation

I have a list of measurements that is not normal and need to be log-transformed so that parametric statistics can be applied (e.g. mean, CI). I can calculate the mean and CI without problem when the ...