Tagged Questions

Statistical classification is the problem of identifying the sub-population to which new observations belong, where the identity of the sub-population is unknown, on the basis of a training set of data containing observations whose sub-population is known. Therefore these classifications will show a ...

learn more… | top users | synonyms

2
votes
0answers
9 views

Baseline for Precision-Related Metrics

When working with ROC-AUC as a metric for binary classification, one often considers a value of 0.5 as a baseline from a random classifier (i.e. a data-blind classifier that randomly classifies test ...
0
votes
0answers
14 views

Finding genuine arrears and default arrears from rent payment patterns

I am currently working on some housing data - in particular analyzing the tenants' rent payment information and I am stuck on progressing with the following: I have to classify tenants based on their ...
0
votes
0answers
27 views

Trying to find a classifier that will give me probability predictions between 0-1 in weka

This is the first time I've done any sort of predictive modelling and I think I've really confused myself. I have a training set of data with a column at the end that has either a 1 or a 0 in it. ...
0
votes
1answer
18 views

Structural risk minimization and SVMs

I know what is SRM but I didn't understand the relation between SRM and SVMs. Can anyone explain me this? Why they say that SVMs rely on a SRM approach? Thank you so much!
0
votes
0answers
9 views

Is it OK to resample data in one vs all multiclass classification?

I have a multiclass classification problem and decide to use one vs all logistic regression. Since some classes are very rare (pos vs neg is like 1:100), I plan to use some balancing strategy during ...
5
votes
1answer
38 views

Is it possible to have a case where $D'$ is zero but Logistic Regression is still able to classify accurately?

I want to know if it is possible to construct a problem with following properties: $M_1$ is $n \times p$ matrix of $n$ observations from Class A $M_2$ is $n \times p$ matrix of $n$ observations from ...
1
vote
1answer
15 views

How to get random classification to assess the performance of classifier with McNemar test?

I'm trying to replicate a study where the author used the McNemar test to assess the performance of classification compared to random classification. I have the original classifier and I'm using R to ...
0
votes
0answers
19 views

Appropriate classification model for combination of continuous, binary and categorical inputs

I have a binary classification problem for classify my samples to two classes (class_1 and class_2). I have different kinds of ...
1
vote
0answers
19 views

Intution on Interchangability of Regression and Classification

Dear Oracles of CrossValidated, I've been trying to gather intuition on the relationship between methods that seems to be escaping me. Can someone explain how regression and classification can be ...
1
vote
2answers
34 views

Why Adaboost with Decision Trees?

I've been reading a bit on boosting algorithms for classification tasks and Adaboost in particular. I understand that the purpose of Adaboost is to take several "weak learners" and, through a set of ...
1
vote
1answer
36 views

Testing Logistic Regression Classifier in R

I am testing the logistic regression classifier in R. I created some test data like this: x=runif(10000) y=runif(10000) df=data.frame(x,y,as.factor(x-y>0)) ...
1
vote
0answers
13 views

Using Canonical Correlation Analysis (instead of EFA/PCA) to reduce the dimensionality of two sets of variables prior to clustering/classification

I have two sets of paired continuous data obtained from two tests. My goal is to answer the following research questions: Q1. To what extent can results on one test be used to predict the results on ...
0
votes
0answers
5 views

How to deal with clustered features in classification

Imagine there are three classes of data, labeled A,B and C. I have separated the train set ...
0
votes
1answer
14 views

ROC / AUC for polynominal Labels

How can I calculate the Area Under Curve for a classifier of a plynominal label in Rapidminer? I could only find a performance operator for binominal labels that provides the AUC value.
0
votes
0answers
16 views

Ideas to identify cutoff points for tumor classification?

My lab models breast cancer in mice. I am using a 36-gene signature (derived from one of our mouse models). In the signature, all genes are elevated. I have 997 human samples and would like to apply ...
0
votes
0answers
12 views

Determine performance in which subject improves overall performance

I have a dataset in .csv format as shown: ...
0
votes
0answers
12 views

$\alpha$ and $\beta$ values in SVM classifier

James et al. in An introduction to the statistical learning (p. 351) claim that the solution to the support vector classifier problem involves only the inner products of the observations. They ...
1
vote
1answer
42 views

Ratio between positive and negative examples in a training problem

When training a 0/1 classifier, what should be the ratio of positive to negative, how to decide the ratio between them based on the classifier I use and the data set under analysis?
0
votes
0answers
10 views

Is the approach for PLSDA for categorical variables the same as that used for “PLS for regression”?

I understand the approach used for partial least squares for regression (PLS) where the principal components are chosen such that the correlation between the scores in the principal component space ...
0
votes
0answers
33 views

Learning Decision Trees on Test Data Using R

How can I use R to learn classes on test data? I currently have a training set of about 1000 entries and a test set of about 10000 entries. I split it up so that the training set has the class label ...
0
votes
0answers
27 views

How do we generate the ROC curve for Linear Discriminant Analysis method

I know the method to generate the ROC curve for other methods such as naive Bayes where the tuning parameter is the threshold like also in logistic regression. If we want to generate the ROC curve ...
0
votes
1answer
14 views

What is the intuition behind the Kappa statistical value in classification

I understand the formula behind the Kappa statistic value and how to calculate the O and E value from a confusion matrix. My question is what is the intuition behind this measure? Why does it work so ...
0
votes
0answers
6 views

Classification under uncertainty in observations

I am tackling a multiclass classification problem where the values of the independent variables are not known with certainty. Instead, each observation is represented by a multivariate Gaussian pdf ...
1
vote
1answer
13 views

Extract features to explain different states of the world

I have a problem that can be seen as the inverse of a classification problem. I don't need to classify points, but to explain the differences (if any) between points in different, pre-specified ...
0
votes
0answers
8 views

Do you know about SVM plait?

I need to know about how I can applied many single SVMs? because I have read about SVM plait that does this kind of classifications that is using many single SVMs to improve the classification process ...
0
votes
0answers
12 views

Can you use accelerometer data for classification with Conditional Random Fields?

I want to recognize activities, based on accelerometer data from the smartphone. I studied Conditional Random Fields and the CRFSuite. Now I am Confused. In my opinion CRF training uses static single ...
0
votes
0answers
18 views

Statistical test for Comparing 6 classifiers over 5 datasets

I did the Friedman test to compare 6 classifiers which are tested over 5 datasets. The null hypothesis was rejected so I proceed with the post-hoc Bonferroni. The X classifier is always first on all ...
0
votes
0answers
5 views

Using Quality metrics of BIRCH Clusters

What is significance of quality metrics of BIRCH Clusters Distance3 and Distance4. Appreciate if there are pointers are how to use Average Intra Cluster Distance (D3) and Average Inter Cluster ...
0
votes
0answers
7 views

Testing Cluster Assignment/Pattern Matching against BIRCH Clusters

I have a dataset of size >35K in size / >50 dimensions. Used BIRCH algorithm for clustering. While testing, the data points with which cluster formed is not matching i.e., The data point shows closer ...
1
vote
0answers
14 views

Classification with two different dataset

I am working on a cancer classification model.Task is ,I am initially given a data set of 500 people and 1000 features.These people are given some kind of treatment(say Treatment 1). Some people are ...
0
votes
0answers
14 views

Recommendation system [closed]

I'm newbie in data mining and statistic. I'm trying to build a recommendation system that recommends existing users / new users on products. Basically what we have is Products (grouped by categories) ...
0
votes
1answer
13 views

Binary classification in imbalanced data

I have a binary classification problem where my data is highly imbalanced (80:20). Given this imbalance is present in both training and test set, does it make sense to apply specific strategies during ...
0
votes
1answer
34 views

How to compare probabilistic classifiers?

Assume that we have a very long sequence (i.e. a list) of nominal-valued observations. For example: A A C B ... B A B C We have also a corresponding sequence of ...
0
votes
0answers
4 views

Apriori like algorithms

The Apriori algorithm predominantly works by pruning the possible itemsets by using a fixed threshold namely, support threshold(lowerbound). Are there any other metrics which can be used as an ...
1
vote
1answer
30 views

Understanding SVM and when to precompute the normal vector

I've been reading a lot about SVMs and have some questions about performing classification from the SVM model produced from a package like libSVM. From my understanding, for a linear SVM without the ...
0
votes
0answers
27 views

One or two output neurons for a binary classification task with an artificial neural network

Suppose you have a classification problem in which you want to classify inputs into two exclusive classes (y1 and y2) with an artificial neural network (which models P(y|x)). Among the two following ...
1
vote
0answers
14 views

Confidence intervals for the Log Loss metric for model comparison?

Quite a few Kaggle competitions have used or are using the Logarithmic Loss metric as the quality measure of a submission. I'm wondering if there are other ways besides N-fold cross-validation to ...
0
votes
0answers
26 views

SVM One-vs-One vs One-vs-ALL SVM

For an unbalanced dataset annotated by human annotators in which each item is assigned to different classes, what is the argument for and against using any of One-vs-One vs One-vs-ALL SVM ...
0
votes
0answers
27 views

K-means and maximum likelihood!

Is there any relation between k-means and the maximum-likelihood estimate in unsupervised learning? Any references would be appreciates! Thank you!
0
votes
0answers
11 views

Generating Labeled Training data from 2 data sources for Predictive Classifier

I am trying to build a predictive risk model classifier for an product (classifying good or bad). I am in the process of creating a training dataset. Here are the challenges I am facing. I have 2 ...
0
votes
0answers
13 views

Comparing Two classification models using F1-score

I am trying to compare the results of 2 classifiers trained with SVM using the F1 score. Some papers that I have read and that do this have made me a bit confused. I have trained the 2 classifiers ...
3
votes
2answers
105 views

Can $p(Y|a,b)$ ever be equal to $p(Y|a) \cdot p(Y|b)$?

This strikes me as a simple question, but in re-visiting how the Naive Classifier works I started wondering if there is any probabilistic model that under certain independency assumptions obtains: ...
0
votes
0answers
5 views

Pyramid Match Kernel: How to fit histogram grid around data points?

This question is directly related with Kernel methods and SVM, so I think this is a good place to ask it. I am planning to use Pyramid Match Kernel method for object recognition from depth images: I ...
0
votes
0answers
22 views

How does rpart in R differ from SPSS classification trees?

I am using rpart in R for some decision trees. I decided to check the results in SPSS - classification - trees, and different variables were selected. In rpart, I'm using method="class" and the ...
2
votes
0answers
22 views

Classifying points in subspaces

I have a set of points in 5D and I am building a classifier. There are five classes. One interesting property of the data is that points in each class tend to be located in, or near, a 1D, 2D or 3D ...
1
vote
1answer
21 views

Optimizing for target metrics in Weka

I'm a PhD student in Information Retrieval with some limited experience in ML. We've been working on a binary classification task with weka (I'm using weka programmatically via Java), specifically ...
8
votes
3answers
927 views

Why downsample?

Suppose I want to learn a classifier that predicts if an email is spam. And suppose only 1% of emails are spam. The easiest thing to do would be to learn the trivial classifier that says none of the ...
0
votes
1answer
29 views

Interpreting rpart output for decision trees?

How do I go about selecting the ideal location to use for pruning the tree here? Or maybe someone can explain to me in simple language what this output means. I see that rel_error is constantly ...
1
vote
0answers
13 views

Real data examples for the Neyman-Pearson lemma?

Are there any interesting (and preferably published for that reason) real data examples to which the Neyman-Pearson lemma for simple binary testing or classification problems applies directly? I am ...
0
votes
1answer
57 views

When normalization is counter-productive [duplicate]

Could you give me general examples of when normalization is not used properly and affects badly the classification accuracy, or when it is not needed?