Most Popular
1500 questions
36
votes
2 answers
Performing a statistical test after visualizing data - data dredging?
I'll propose this question by means of an example. Suppose I have a data set, such as the boston housing price data set, in which I have continuous and categorical variables. Here, we have a "quality" variable, from 1 to 10, and the sale price. I…
Marcel
- 1,430
36
votes
3 answers
Utility of feature-engineering : Why create new features based on existing features?
I often see people create new features based on existing features on a machine learning problem. For example, here : https://triangleinequality.wordpress.com/2013/09/08/basic-feature-engineering-with-the-titanic-data/ people have considered the size…
Matthieu Veron
- 493
36
votes
4 answers
How is Poisson distribution different to normal distribution?
I have generated a vector which has a Poisson distribution, as follows: x = rpois(1000,10) If I make a histogram using hist(x) , the distribution looks like a the familiar bell-shaped normal distribution. However, a the Kolmogorov-Smirnoff test…
luciano
- 14,757
- 36
- 100
- 134
36
votes
3 answers
Feature importance with dummy variables
I am trying to understand how I can get the feature importance of a categorical variable that has been broken down into dummy variables. I am using scikit-learn which doesn't handle categorical variables for you the way R or h2o do. If I break a…
Dan
- 1,457
36
votes
1 answer
Differences between a statistical model and a probability model?
Applied probability is an important branch in probability, including computational probability. Since statistics is using probability theory to construct models to deal with data, as my understanding, I am wondering what's the essential difference…
Honglang Wang
- 955
- 3
- 9
- 16
36
votes
3 answers
I've heard that ratios or inverses of random variables often are problematic, in not having expectations. Why is that?
The title is the question. I am told that ratios and inverses of random variables often are problematic. What is meant is that expectation often do not exist. Is there a simple, general explication of that?
kjetil b halvorsen
- 87,534
36
votes
5 answers
Can you overfit by training machine learning algorithms using CV/Bootstrap?
This question may well be too open-ended to get a definitive answer, but hopefully not. Machine learning algorithms, such as SVM, GBM, Random Forest etc, generally have some free parameters that, beyond some rule of thumb guidance, need to be tuned…
Bogdanovist
- 6,739
36
votes
5 answers
Is an overfitted model necessarily useless?
Assume that a model has 100% accuracy on the training data, but 70% accuracy on the test data. Is the following argument true about this model? It is obvious that this is an overfitted model. The test accuracy can be enhanced by reducing the…
Hossein
- 3,544
- 4
- 23
- 36
36
votes
5 answers
Modelling longitudinal data where the effect of time varies in functional form between individuals
Context : Imagine you had a longitudinal study which measured a dependent variable (DV) once a week for 20 weeks on 200 participants. Although I'm interested in general, typical DVs that I'm thinking of include job performance following hire or…
Jeromy Anglim
- 47,292
36
votes
1 answer
Why is LogLoss preferred over other proper scoring rules?
It seems anytime people care about estimating probabilities accurately they choose LogLoss as the evaluation metric. But there are many other evaluation metrics which will prefer accurate estimation of probabilities (and not only ranking or…
Meir Maor
- 610
36
votes
5 answers
Why do we take the square root of variance to create standard deviation?
Sorry if this is has been answered elsewhere, I haven't been able to find it. I am wondering why we take the square root , in particular, of variance to create the standard deviation? What is it about taking the square root that produces a useful…
Dave
- 2,791
36
votes
6 answers
Why is the expected value named so?
I understand how we get 3.5 as the expected value for rolling a fair 6-sided die. But intuitively, I can expect each face with equal chance of 1/6. So shouldn't the expected value of rolling a die be either of the number between 1-6 with equal…
36
votes
7 answers
t-test for partially paired and partially unpaired data
An investigator wishes to produce a combined analysis of several datasets. In some datasets there are paired observations for treatment A and B. In others there are unpaired A and/or B data. I am looking for a reference for an adaptation of the…
Frank Harrell
- 109,729
- 6
- 222
- 516
36
votes
5 answers
Prove that F-statistic follows F-distribution
In light of this question : Proof that the coefficients in an OLS model follow a t-distribution with (n-k) degrees of freedom I would love to understand why $$ F = \frac{(\text{TSS}-\text{RSS})/(p-1)}{\text{RSS}/(n-p)},$$ where $p$ is the number of…
user1627466
- 463
- 1
- 5
- 5
36
votes
1 answer
What are some useful guidelines for GBM parameters?
What are some useful guidelines for testing parameters (i.e. interaction depth, minchild, sample rate, etc.) using GBM? Let's say I have 70-100 features, a population of 200,000 and I intend to test interaction depth of 3 and 4. Clearly I need to do…
Ram Ahluwalia
- 3,131