Partitioning data into subsets of objects according to their mutual "similarity," without using preexisting knowledge such as class labels. Clustered-standard-errors and/or cluster-samples should be tagged as such; do not use the "clustering" tag for them.

learn more… | top users | synonyms (1)

6
votes
2answers
975 views

Dynamic Time Warping Clustering

What would be the approach to use Dynamic Time Warping to perform clustering of time series? I have read about DTW as a way to find similarity between two time series, while they could be shifted in ...
-1
votes
1answer
23 views

Exploring multiple semantic clusters of a given set of terms

I have a list of N object categories(e.g. apple, cell-phone, horse, chair, watch). Are there any methods of obtaining various clusters based on attributes of these categories ? For example, one ...
0
votes
1answer
19 views

K-Means Clustering on Distributed System

Can anyone explain how the k-means clustering algorithm converges on distributed systems? It seems that each node in our hadoop cluster would simply find a local optimum. How do we update across ...
0
votes
1answer
148 views

How to use both binary and continous variables together in K means/Hierarchical clustering in SAS/R?

I need to use binary variables( values 0 & 1) in K means. But K means works with only continuous variables. I know some people still use these binary variables in K means ignoring the fact that k ...
2
votes
2answers
45 views

Cluster analysis as a preliminary analysis

I want to produce four groups (high/high, high/low, low/high and low/low) using two continues variables and compare these groups in terms of a few dependent variables. I know that cluster analysis ...
1
vote
1answer
29 views

classification of the groups [duplicate]

Let's say I have two variables: height and weight. I want to produce 4 groups: high height/high weight, high height/low weight, low height/ high weight and low height/low weight. I also want to see ...
8
votes
4answers
353 views

Are there any non-distance based clustering algorithms?

It seems that for K-means and other related algorithms, clustering is based off calculating distance between points. Is there one that works without it? Thanks!
1
vote
2answers
24 views

Revealing structure of clusters in a dataset

I have obtained values for the same parameter in various locations and I want to cluster them (abundance fraction of different minerals in a hyper-spectral image). These fractions have spatial ...
0
votes
1answer
50 views

Update Rules in Expectation Maximization

I am emulating a certain PDF behaviour using a function. However, due to divergent improper integral, I don't have a closed form expression for the normalization constant. To get the PDF, I just ...
0
votes
2answers
123 views

Mahalanobis distance measure for clustering

Let's say I have a group of clusters. Would you recommend Mahalanobis distance measure for checking if new arrived data belongs to existing clusters or it is an outlier? Also, would you recommend ...
0
votes
2answers
73 views

Use of bootstrap in clustering algorithms

Are there clustering algorithms that take advantage of bootstrap? For example can one combine bootstrap with a standard K-Means algorithm to scale K-Means. I was thinking if the following at a ...
0
votes
0answers
13 views

How to segment/profile users after performing classification?

So let's say that you've used logistic regression with demographic factors to make prediction on user bebaviour (e.g. those who clicked on a particular link v those who didn't) and you are satisfied ...
0
votes
0answers
17 views

Conjoint analysis

I am planning to conduct a conjoint study, but am having problems in terms of the number of product profiles to include. I will have to interview respondents in the markets and hence wanted that the ...
0
votes
1answer
23 views

Benchmarking hard clustering results against soft clustering results (ground truth)?

Well, I don't have labels (ground truth) for my data points. However, by domain knowledge, I am certain that a particular soft clustering algorithm will produce satisfactory results. Hence, I may use ...
1
vote
2answers
90 views

Mutual information for two soft clustering results?

I understand that mutual information (MI) of two distributions $X$ and $Y$ is defined as In the case of clustering analysis, say we are looking for two clusters out of 3 data points. We have two ...
4
votes
1answer
107 views

Clustering into teams of fixed size

There is a particular team-based video game that exposes a ladder of individual ratings for each player that looks like this (player, rating, wins, losses): A, 2000, 35, 12 B, 1900, 41, 19 C, 1800, ...
1
vote
1answer
156 views

Anomaly detection: multivariate Gaussian distribution

I am trying to do anomaly detection on a heterogeneous dataset (There are unknown groups present in the dataset). I want to try multivariate Gaussian distribution based approach, but I was thinking of ...
0
votes
0answers
58 views

Find the radius of a cluster, given that its center is the average of the centers of two other clusters

I do not know if it is possible to find it, but I am using Kmeans clustering, and I am stuck to the following. In my implementation, I create with two different threads the following clusters: ...
0
votes
0answers
29 views

Clusters as input for classification

I'm currently performing clustering as a batch job and then in real time I'm assigning new points to cluster whose centroid is closest to new arrived point. The other approach that I see is to ...
3
votes
1answer
91 views

Best clustering algorithm for real estate data

I want to cluster real estate data to determine average price patterns in city and rural regions. My data set contains size, number of dorms, bathrooms and coordinates of the properties. Which would ...
0
votes
0answers
24 views

Which kind of analysis could be made to associate a set of genes to clinical values?

I have a set of 5 genes that can be mutated or not, so therefore are intended as dichotomous yes/no vars. I want to identify the effect of the mutation of this genes on a continuous response var. The ...
0
votes
0answers
15 views

Profiling high-scoring clusters in a multi-dimensional feature space

I have a large amount of samples, which have a multi-imensional feature vector associated with them. Each sample has a "score", and the length of the feature vector is substantial (n>100, and in ...
1
vote
0answers
39 views

Investigate correlation between one variable and combinations of others

We're conducting a study which correlate the incidence of various conditions during pregnancy and in newborns and the use of artificial reproduction technique (ART). This way we saw that some ...
5
votes
1answer
222 views

Clustering data into bins of variable sizes

I'd like to build a model (in R or excel) that takes in large amount of linear data and segments it into "bins". The linear data is an attribute that reflects what condition that section/record is at. ...
3
votes
0answers
63 views

Use of Hidden Markov Models for Clustering

I would like to ask whether Hidden Markov Models can be used for clustering and if so, in what cases. I have found somewhere, references like this but practically I haven't found a way to do this. Is ...
0
votes
0answers
19 views

Automatically classifying user activity/sessions on a website?

X-posted from Stack Overflow: I have a large body of records pertaining to user activity on a website. What I want to do is some sort of classification on each user as they navigate my website. Every ...
0
votes
0answers
17 views

Good mean shift clustering datasets

I am working on a modification of the Mean Shift algorithm and would like to validate my clustering results. I am struggling to find suitable clustering datasets to compare performance with. I'm ...
1
vote
0answers
123 views

Observation/case weighting in cluster analysis

Sampling weights, the inverse probability of a unit's selection into the sample, and other more complex and adjusted weights are very often used in the social sciences. There is statistical software ...
0
votes
1answer
29 views

What Grouping Method To Determine Average Over Lifetime?

I have the following data: When individual 'x' joined a company. As the data is limited to 2 years I do not know the start date of every individual. When individual 'x' left the same company. If this ...
0
votes
1answer
44 views

Cluster Sequences of data with different length

I need to cluster sequences of data that have different length. I am using Matlab and my first question is related to the method. Is KMeans sufficient to achieve this? IN KMeans I have to use the ...
0
votes
0answers
24 views

Logistic regression and cluster ID

The dataset consists of all prescriptions classified as on or off-label (0 or 1), meaning possible more than one prescription per child (pnr-number) I want to know the off-label rates per year for ...
1
vote
1answer
38 views

Hierarchical clustering: different result when I change labels

I am running hierarchical clustering with a distance matrix M_norm: hc <- hclust(M_norm^2, method = "ward.D") plot(hc, cex = 1, hang = -1) When I use ...
0
votes
0answers
29 views

Descriptive clustering of papers

Given a set of PubMed abstracts or keywords derived from MeSH terms, I would like to know how many and what topics are among them in order to write a paper review. Other information such as the number ...
0
votes
0answers
29 views

The best algorithm for short documents clustering

I have a corpus of short text documents. Each document is an automatic recognized phone conversation (a dialog) from a large call center. The texts are not clean and have lots of grammar and other ...
3
votes
1answer
83 views

A valid distance metric for high dimensional data

I asked a question about forming a valid distance metric yesterday (Link1) and got some very good answer; however, I have got some more questions about forming a proper distance metric for high ...
3
votes
1answer
41 views

Can I use k-means with a distance matrix composed of percentages? [duplicate]

I have objects o1, o2,...,on and for each pair I calculate a value that measures the pair's difference. This is a percentage, so for example o1o2 differ by 56%. Now I want to cluster this data. I can ...
1
vote
3answers
100 views

How to get a valid distance metric?

I have got a problem to devise a distance metric to get the similarity measurement of vectors. Someone suggested me to use dot product, which seems to me the same as the Cosine similarity metric; ...
0
votes
0answers
146 views

INTRA-cluster and inter-cluster distance

Thank you for your reply I have generated a valid partition using the following code IDX = kmeans(data(:, 1:end-1),k,'replicates',10,'EmptyAction','drop'); and I am comparing the intra and ...
0
votes
0answers
7 views

The authenticity of the N-cut measure when the number of components in the data is high

I'm running a clustering task on unlabeled data, and assume we're validating our results by applying the Min-Cut measure as an internal validity index. Let's refer the normalized version of the ...
1
vote
0answers
57 views

clustering vs fitting with a distribution

I have a question about using a clustering method vs fitting the same data with a distribution. Assuming that I have a dataset with 2 features (feat_A and feat_B) and let's assume that I use a ...
0
votes
0answers
82 views

Middle point between k-means and DBSCAN in R

I have a big data sample of unrelated events in lon,lat,date format (booking locations to dispatch). I am trying to divide these events into clusters (k=50) where I ...
0
votes
0answers
23 views

How to measure whether the number of points belonging to a cluster is statistically significant

I have a set of data in five clusters (say C1 through C5). From this, I also have the probability of a random point belonging to each of these clusters (p1% through p5%). I select a subset of my ...
1
vote
1answer
31 views

Unnatural clustering with known clusters shapes and optimization criteria

My question is similar to this question Clustering with shape prior, but with additional information. The second answer suggests a mixture model approach to this problem, which is something like ...
2
votes
2answers
67 views

Generate a random chain with cauchy distribution using C language

Here is my question: I want to simulate a random variable using cauchy distribution with C language. Scale and position must be setted manually. I fuond the GSL library wich contain the function: ...
1
vote
1answer
69 views

What kernel function can be used to project data into a feature space that is a “circle”?

I am working with cyclical data (Days 1-7, hours 1-24). I want to project it into a feature space that can understand that 1 and 7 are close days and 1 and 24 are closer than 22 and 24, etc, and then ...
1
vote
1answer
76 views

Distribution of p-values in this thought experiment?

I'm trying to check whether my clustering was informative above and beyond random clustering. This is my thought experiment to do it, can someone help? Suppose I have a large number, $N$, groups. ...
0
votes
0answers
41 views

How to analyse a factor experiment with feature extraction, clustering and classification algorithms as factors?

Currently I am doing my final project, which consists of designing an experiment to test several combinations of algorithms on a dataset, such as feature extraction, clustering, classifiers and ...
0
votes
1answer
47 views

After Clustering, how can I evaluate which features had the biggest impact?

I've just performed unsupervised clustering (using DBSCAN) on a dataset for which I have no expert knowledge on. I'm interested in working out which features had the greatest impact on my clustering. ...
1
vote
0answers
22 views

How do I find corresponding clusters in independent samples?

Lets suppose you believe that observations in your data come from K natural but not directly observable categories and you wish to identify these categories with minimal prior assumptions, so you find ...
0
votes
1answer
25 views

Why do two identical feature vectors (distance score 0) get different labels in DBSCAN?

I have two identical feature vectors. They have a distance score of 0. I perform DBSCAN Clustering (using sci-kit) and they get different labels. Is this expected behaviour?