2
votes
2answers
68 views
+50

One-to-many matching of propensity scores and average treatment effect on the treated

I've been working on a propensity score matching project, but having no stats classes under my belt I'm struggling to calculate the so called "average treatment effect on the treated" (ATT) so that it ...
1
vote
1answer
42 views
+50

Performance metric based on five-star ratings

Although I think my question might be a specific case of a generic problem, I'll include some background info that might be relevant. There is a sort of concierge/delivery service I know that uses a ...
5
votes
2answers
118 views
+100

By which ways can we, in principle, evaluate whether a model succeeded in generalizing?

A disclaimer: By using an informal term such as "generalize", I am aware I am getting close to philosophical territory, and that my question could be seen as unsuitable for CV. I will do my best ...
10
votes
1answer
631 views
+100

Using generalized method of moments (GMM) to calculate logistic regression parameter

I want to calculate coefficients to a regression that is very similar to logistic regression (Actually logistic regression with another coefficient: $$ \frac{A}{1 + e^{- (b_0 + b_1 x_1 + b_2 x_2 + \...
9
votes
1answer
807 views
+50

What to conclude from this lasso plot (glmnet)

Following is the plot of glmnet with default alpha(1, hence lasso) using mtcars data set in R with mpg as the DV and others as ...
3
votes
0answers
58 views
+50

Calculating probability of an event involving two normally distributed random variables

I have two normally distributed, independent random variables $S^{(1)}$ and $S^{(2)}$: $$S^{(1)} \sim \mathcal{N}(\mu_1, \sigma_1^2),\ S^{(2)} \sim \mathcal{N}(\mu_2, \sigma_2^2)$$ Given two positive ...
0
votes
0answers
48 views
+50

Can I hack weighted loss function by creating multiple copies of data

Suppose we want to build a binary classifier with weighted loss, i.e., it penalize different types of errors (false positive and false negative) differently. At the same time, the software we are ...
23
votes
3answers
945 views
+50

If linear regression is related to Pearson's correlation, are there any regression techniques related to Kendall's and Spearman's correlations?

Maybe this question is naive, but: If linear regression is closely related to Pearson's correlation coefficient, are there any regression techniques closely related to Kendall's and Spearman's ...
4
votes
2answers
614 views
+50

Do we need gradient descent to find the coefficients of a linear regression model

I was trying to learn machine learning using the coursera material Andrew Ng uses gradient descent algorithm to find the coefficients of the linear regression model that will minimize the error ...
121
votes
10answers
70k views
+50

How should I transform non-negative data including zeros?

If I have highly skewed positive data I often take logs. But what should I do with highly skewed non-negative data that include zeros? I have seen two transformations used: $\log(x+1)$ which has the ...
2
votes
0answers
39 views
+50

Some help to get started with Spatio-temporal data analysis on different engines

I will soon receive experimental data from $n$ engines ($n$ is small, say, 10) for sensor data at the locations in figure: As you can see, each engine is equipped with $5\times8=40$ sensors, ...
4
votes
1answer
43 views
+50

What is the value of linear dimensionality reduction?

From the results I've seen, manifold learning methods seem to generally outperform PCA for complicated, very high-dimensional datasets like images or videos. This makes sense to me, since nonlinear ...
10
votes
2answers
694 views
+50

Least Squares Regression Step-By-Step Linear Algebra Computation

As a prequel to a question about linear-mixed models in R, and to share as a reference for beginner/intermediate statistics aficionados, I decided to post as an independent "Q&A-style" the steps ...
0
votes
1answer
15 views
+50

why Matrix Factorization map the two spaces into same space?

It's a common sense that Matrix Factorization map the two space(e.g. user and item) into same factor space. But is there any more formal way to explain the fact they are the same ? Say, I have $$\...