# Tag Info

### Why am I getting strange upper & lower limits on a gamma distribution?

The reason for obtaining strange results is that you use empirical standard deviation as scale parameter, but the parameter is not equal to standard deviation. If ...
Accepted

### Outlier/anomaly detection on histograms

Outlier or anomaly detection methods always rely on some notion of distance between the "data points" to be subjected to the detection algorithm. So your first step needs to be to decide on ...
Accepted

### Fixing outliers and normalizing a vector using R

Techniques of Exploratory Data Analysis (EDA) can help with this feature engineering problem. I want to emphasize how just a couple of well-chosen plots tell us, forcibly, how we ought to proceed. ...
Accepted

### Standardize dataset with high outliers

This data would be better visualised (and quite possibly analysed as well) with a transformation. A log transformation is usually a good solution for right-skewed data such as this. If you have zeroes ...

### MAE vs MSE for Linear regression

Since the error is defined $\hat{u}=y-\hat{y}$ (difference between actual and predicted value), taking the squared error will give a high weight to outliers (with "large" difference between \$...

### MAE vs MSE for Linear regression

It depends on your problem, but I personally like MAE the most. Things to take into account: Historically, MSE has been used instead of MAE because the math is easier to write and naturally appears ...
1 vote

### Fixing outliers and normalizing a vector using R

If you want to force the vector of observations to have a distribution close to normal, you can use inverse normal scores transformation. There are a few different varieties such as Elfving, Blom, ...
1 vote

### Standardize dataset with high outliers

if it is one category of data then okay. Otherwise, you will use some robust statistics to overcome the problem like median, quartiles etc. Z-score will not be suitable as it is based on deviation ...
1 vote

### How to use box plots to detect outliers?

I think all your computations are correct, so with that criteria you expect outliers at a given frequency. I think this makes sense, even by chance you can get extreme values, right? The point you ...

Only top scored, non community-wiki answers of a minimum length are eligible