famargar
  • Member for 5 years, 1 month
  • Last seen more than a week ago
2 answers
9 votes
12k views
How to prepare interactions of categorical variables in scikit-learn?
Accepted answer
10 votes

Indeed you can use Patsy with scikit-learn to obtain the same results you would obtain with R, or with the formula notation in stats models. See code below: from patsy import dmatrices # create ...

View answer
1 answers
5 votes
2k views
Three Parameter Gamma Distribution
3 votes

The three parameter gamma distribution is needed only when you need to shift the distribution itself. In the two-parameter gamma distribution, you could read the shape parameter as a proxy of the most ...

View answer
2 answers
1 votes
47 views
What is this clustering technique called?
2 votes

It seems like your problem is actually supervised problem; to be more precise, a two-class classification problem: either the point has some property, or it does not. You are coloring the data points ...

View answer
6 answers
42 votes
23k views
Why do we need multivariate regression (as opposed to a bunch of univariate regressions)?
2 votes

1) Nature isn't always simple. In fact, most phenomena (outcome) we study depend on multiple variables, and in a complex manner. An inferential model based on one variable at a time will most likely ...

View answer
2 answers
1 votes
127 views
How to develop a model if you don't have a clear response variable
2 votes

Not sure I fully understand the question. If the question is how to choose the sample of people to offer the free trial, I would start by analyzing the properties of customers that paid the service ...

View answer
5 answers
8 votes
766 views
How Well Does the Mean Describe a Multimodal Probability Distribution?
1 votes

There are many good answers here. I’ll just add here the general point to be made. You can summarise a distribution of values with a single number, the mean (or even two, say the standard deviation) ...

View answer
2 answers
4 votes
1k views
Understanding very high p value with Spearman's rank correlation
1 votes

You are misinterpreting the p-value. It actually represents the probability to observe a certain effect or stronger (in your case a correlation) if the null hypothesis - i.e. no correlation - is the ...

View answer
3 answers
5 votes
334 views
What to do if you suspect combinations of two distributions?
1 votes

Observing a distribution that is actually the convolution of two or more distinct distributions is very common. In general, you can be observing the same phenomenon for a single population, but ...

View answer
2 answers
1 votes
507 views
Compare two Roc curves with same Auc
0 votes

Typically, the “business use” of a classifier depends on sensitivity and specificity, not on AUC. What you have is to model with same average performance (what the AUC measures) but one is optimal at ...

View answer
10 answers
23 votes
6k views
Best term for made-up data?
0 votes

Data is Latin for given, that is used in modern times as a shorthand for given set of recorded facts. So in a way referring to fabricated recordings as some sort of given facts would be an open ...

View answer
4 answers
2 votes
830 views
Accepting or rejecting the null hypothesis based on p-value and R value
0 votes

Did you try plotting the data in log-log scale? It may be that the small correlation becomes very discernible on a log-log scale. Just remember to add 1 when log-transforming: x -> log(x+1) I don’t ...

View answer
2 answers
2 votes
851 views
Measure spread of non normal distribution?
0 votes

You properly say that the distribution is bimodal. A perhaps slightly more articulated analysis would be to try to measure the relative contribution of the two subsamples (promoters and detractors) ...

View answer
5 answers
12 votes
7k views
How do I interpret this Scatter Plot?
0 votes

Trying a linear regression will teach you something about this relation, as suggested in the first answer. Since It looks like you are using python plus matplotlib for this plot, you are one line of ...

View answer
3 answers
1 votes
1k views
How to deal with Class imbalance problem for classification algorithms?
Accepted answer
0 votes

One option is to down-sample you majority class - i.e. randomly throwing away events belonging to the majority class. That is of course feasible only if you have large enough data to afford this. An ...

View answer
1 answers
1 votes
467 views
Standardization or Feature Scaling?
Accepted answer
0 votes

Standardization (or normalization using Student's t statistics, to use a longer name) is a good practice if you don't want your machine learning algorithm to improperly assign a larger relevance to ...

View answer
1 answers
1 votes
30 views
identifying possible machine learning approaches
0 votes

Keeping the assumption that human-derived severity score is the "truth" label about the severity of the disease, then your approach is correct, and the only question left is "is there a possibility ...

View answer
1 answers
1 votes
125 views
Weighting hospital visit (independent variable)
0 votes

It seems like you would like to build a new variable "hospital visit cost" that is the result of a regression model whose independent variables are a categorical variable "hospital stay type" (...

View answer
2 answers
2 votes
798 views
Is Gamma distribution appropriate for sales transaction data?
0 votes

I wonder if you tried fitting your data with something like a powerlaw distribution ($ax^{-b}$ with both $a$ and $b$ positive) or its discrete equivalent, Zeta or Yule-Simon distribution (thanks ...

View answer
2 answers
-1 votes
67 views
Regression Analysis
0 votes

Do you care about interpretability of your results, or just about the prediction accuracy? If accuracy is what you are looking for, you could try using other machine learning algorithms (Boosted ...

View answer
5 answers
45 votes
14k views
Why are regression problems called "regression" problems?
-1 votes

"Regression" comes from "regress" which in turn comes from latin "regressus" - to go back (to something). In that sense, regression is the technique that allows "to go back" from messy, hard to ...

View answer