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)

0
votes
0answers
11 views

Ordination or Clustering method using layered data

I need a clustering method that makes use of layered data. I have around 50 random sampling points from a surface. Each point samples layers below that point. Imaging geological layers or water layers ...
1
vote
0answers
58 views

How many clusters would you divide this dendrogram into?

I'm struggling as to where to cut this dendrogram: any help would be appreciated. Thanks
0
votes
0answers
30 views

Clustering on this reinforcement learning approach?

I am trying to create an agent that selects an action depending on a state that gives back maximum reward. To keep things simple I will keep it to two actions and 24 different states. The states is ...
0
votes
1answer
66 views

Probability for selecting centroids - K-means++

K-means++ selects centroids one by one, where each point has the chance to become next centroid with probability proportional to distance to closest centroid already selected. I implemented it like ...
0
votes
1answer
22 views

Hierarchical clustering methods using a similarity metric for which d(x, x) != 0, and possibly assymmetric

I want to cluster files based on an information distance, which is obtained by comparing the compressed length of two files separately and the concatenation of the two files, using a real-world ...
2
votes
1answer
57 views

Cluster analysis without knowing the structure of the data set

I’m working on a task regarding cluster analysis for about half a year now, but since the fields of pattern recognition and cluster analysis are quite complex ones, I would call myself a beginner in ...
1
vote
0answers
59 views

Gaussian mixture models restriction? [closed]

I read this note that with striction on GMM with some condition this algorithm is more like to K-means: the adaptations of the Gaussian mixture models algorithms with Restrict each $\Sigma_i$ ...
7
votes
1answer
544 views

Jenks Natural Breaks in Python: How to find the optimum number of breaks?

I found this Python implementation of the Jenks Natural Breaks algorithm and I could make it run on my Windows 7 machine. It is pretty fast and it finds the breaks in few time, considering the size of ...
0
votes
1answer
20 views

Significance of a cluster with respect to the whole dataset

I mainly am a machine learning guy and my knowledge of statistics is a bit limited. I have a (small) dataset of objects described by two categorical variables: $$ \begin{array}{|l|l|l|l|l|} \hline ...
0
votes
1answer
30 views

FAMES in case of Dynamic Time Warping

I found this paper Using Pivots to Speed-Up k-Medoids Clustering in which authors explain how to use triangular geometry and cosine law to speed up search of new medoids in case of K-medoids. My ...
2
votes
1answer
57 views

Clustering Matrices

Suppose I have a set of 100 $n \times 2$ matrices that all have the following format: Bid Profit [5.00 7.10] [3.14 6.04] [2.9 10.08] Where the numbers ...
2
votes
0answers
88 views

jenks natural breaks vs k-means

I am new to this topic. As far as I know both are data clustering methods. Then my question is when is Jenks prefered over k-means? I read on this website that jenks is particularly suited for ...
2
votes
0answers
22 views

Cluster Assignment in Bayesian perspective

I am going to study clustering methods in the Bayesian perspective. I understood how k-means works, and I found it pretty clear, due to the notion of distance and assignments to specific centers. I ...
0
votes
0answers
40 views

How to generate multidimensional data with specific clustering properties?

In section 5.A of a research paper the researcher used the following synthetic datasets: GAUSS consisted of six Gaussian clusters with identity covariance, each with 500 points in five dimensions. ...
-1
votes
2answers
39 views

k-means nstart equivalent for EM Clustering? Report only the best solution from a large number of initializations?

In K-means clustering, you can specify an nstart=i parameter, which performs the algorithm i times (i.e. selects the initial k random centroids i times) sand reports the best answer only. If I perform ...
0
votes
1answer
51 views

Finding natural groups / clusters in an undirected graph / over several undirected graphs

What kind of methods are there to find natural groups or clusters within an undirected graph structure? I am new to graph theory, but the project seems to have confronted me with questions that could ...
0
votes
1answer
13 views

Clustering with summarised variables

I have a total of 32 observation that I would like to cluster. The data avaiolable comes in 2 formats: Continuous data Summarized categorical data What I mean with summarized categorical data is ...
1
vote
1answer
26 views

Statistical tests for a binary response variable with more than 2 repeated measures?

Question: Did plants experiencing treatment A vs. treatment B receive significantly more or less observations with zero visits from pollinators? Methods: Plants were clustered by similar physical ...
0
votes
1answer
60 views

K-Medoids swapping inside clusters

I'm a bit confused with concept of K-medoids. It seems that original algorithm (PAM) describes that swap step should be performed by swaping only one of the medoids with one non-medoid point from ...
3
votes
1answer
68 views

Ridge regression in multivariate Gaussian distribution

When implementing GMM (Gaussian Mixture Model) in practice, the covariance matrix ${\Sigma}_{D\times D}$ is often singular. The reason is that we have to estimate $\frac{D(D+1)}{2}$ parameters in ...
0
votes
0answers
37 views

Can a classification algorithm be used to measure the Clustering Quality (CQM)

Can a classifier be used to measure the Clustering Quality measure? I have come across this paper where the researcher uses a classifier like : five nearest neighbor classifier, a C4.5 decision ...
0
votes
1answer
19 views

Semistructured document classification

I am trying to cluster products based on the text descriptions of the products. I have millions of products. The nature of the products could be hierarchical. i.e; Clothing will have T-Shirts & ...
0
votes
1answer
51 views

K-means++ like initialization for K-medoids

Does it make sense to use initialization in K-medoids like in the case of K-means++? To be precise - is it good to select "farthest" points as initial medoids? (farthest in sense that points that are ...
4
votes
2answers
237 views

Can humans cluster data sets manually? [closed]

Can human cluster data sets manually? For example, consider the Iris data set, depicted below: Instead of using clustering algorithms like connectivity-based clustering (hierarchical clustering), ...
1
vote
0answers
50 views

Consensus methods for interpreting results of a cluster analysis

With cluster analysis, sometimes we want to assign meaning to the nature of the identified clusters. This is subjective and often done by a single person (or very few people) with perhaps some ...
0
votes
0answers
18 views

Which clustering method should I use and other useful statistical tools for grouping

I have 37 plant species (rows) and up to 18 corresponding traits (col). I would like to see if there are consistent species-wide attributes that are repeated in different species and can therefore be ...
0
votes
0answers
44 views

Using PCA to find most 'similar' points to a given observation (mixed data)

I am trying to find the most 'similar' points to each other in a dataset of mixed data. I understand that if these were all numeric variables on the same scale, one could simply use Euclidean Distance ...
1
vote
1answer
49 views

how to determine medoids based on (dis)similarity matrix

Given the (dis)similarity matrix and the clustering results, how do I select the medoid in each cluster? For example, one cluster contains totally 4 points: A, B, C, D. I know the similarity (or ...
0
votes
0answers
30 views

How many samples are enough

I have objects with large number of attributes (about 60.000). Attributes are actually deviations of object part from model. I would like to cluster this objects, to get centroids that will represent ...
3
votes
1answer
182 views

Understanding cluster plot and component variability

I have run k-means clustering. I have also plotted the results using the following code in R: ...
1
vote
1answer
55 views

Clustering singular vectors [closed]

I have a $n\times m$ matrix $A$ that I have done SVD on and picked off $k$ out of $n$ highest singular values and vectors. That is, I have decomposition for the $k$ rank approximation of $A$: $A^{k} ...
3
votes
1answer
210 views

Difference between K-medoids and PAM

I understood that PAM is just one kind of K-medoids algorithm. The difference is in new medoid selection (per iteration): K-medoids selects object that is closest to the medoid as a next medoid PAM ...
1
vote
0answers
15 views

How to divide scattered points among multiple curves? [duplicate]

I have the following scattered points graph: To me, it seems that the points describe 2 (maybe 3) logarithmic curves. Is there a way to say which point belongs to which curve?
1
vote
1answer
80 views

filling out NA values using clustering analysis

I have a data frame with a large number of NA values. I do not wish to leave out all these rows as that would reduce the size of my training set drastically. I filled out these missing values in a ...
0
votes
0answers
15 views

What does choice of metric say about the data?

I am using KNN method. I have three choices of metric (Euclidean, Manhattan and Chebyshev). The Error rate was minimum when I used Chebyshev distance. What does it say about the distribution data?
14
votes
2answers
845 views

Why does gap statistic for k-means suggest one cluster, even though there are obviously two of them?

I am using K-means to cluster my data and was looking for a way to suggest an "optimal" cluster number. Gap statistics seems to be a common way to find a good cluster number. For some reason it ...
1
vote
0answers
12 views

Adapting clustering to partial clutering

This is a question primarily about re-appropriating existing clustering methods to work when only a fraction of datapoints are likely to originate from a cluster (as opposed to a global background ...
5
votes
1answer
156 views

Within-group sum of squares of cluster

I have a multivariate dataset for which I have only a table including the cross-wise Euclidean distances between all points and a list giving the assignment of each point to one of several clusters. ...
0
votes
0answers
20 views

Clustering objects with missing values

I have some time-series that I would like to cluster, but they can have missing values. One approach that may be ad hoc is to use an algorithm like K-medoids, and to use similarity measure that will ...
0
votes
0answers
35 views

Reveal confusing class blocs in a large confusion matrix

I built a linear classifier for 85 classes. When I get predictions, I construct a confusion matrix. If I visualize it, it looks pretty noisy. I would like to reorder rows and columns such that I ...
2
votes
1answer
120 views

Unsupervised Clustering using randomForest

Outline of clustering technique using Random Forest A synthetic data is created by randomly sampling from the data of interest. It is used as the base line to measure the "structureness" or ...
3
votes
1answer
150 views

What is the difference between graphs/networks? [closed]

Note: read down to below "Question" to find the question. Background: In a previous question I asked how to group what I would call nodes on a network graph based on a connectivity matrix. (link) ...
0
votes
1answer
51 views

interactive clustering of a 3D point cloud by changing the granularity

I want to cluster a point cloud in a 3D space (maybe with 200k points). For this I'm locking for a botom up approach. My goal is, that I can change the granularity of the clustering with a ...
1
vote
2answers
606 views

How can an artificial neural network ANN, be used for unsupervised clustering?

I understand how an artificial neural network (ANN), can be trained in a supervised manner using backpropogation to improve the fitting by decreasing the error in ...
0
votes
0answers
14 views

Determining clustering words

I'm looking for an alternative to PMI for the following problem: I have a set of $n$ classes of text corpuses, and I'm trying to find the keywords that differentiate the corpuses from each other. For ...
0
votes
0answers
13 views

How to make clustering / segmentation on date to percentage intervals?

I've got a table with 3 columns: query, ctr and mean position I want to identify all the cases where the CTR is low while the mean position is good. First of all I need to segment the continuous CTR ...
1
vote
0answers
36 views

How can we say that a clustering quality measure is good?

There are few well known measures like silhouette width (SW), the Davies- Bouldin index (DB), the Calinski-Harabasz index (CH), and the Dunn index . How can we say that a clustering quality measure ...
0
votes
1answer
37 views

Finding words belonging to a topic

Consider forum posts or any text where we'd be interested in finding out related words, given the data. What would be a solution for creating a topic cluster based on this data? E.g. We are interested ...
4
votes
2answers
374 views

Approach and example of graph clustering in “R”

I am looking to group/merge nodes in a graph using graph clustering in 'r'. Here is a stunningly toy variation of my problem. There are two "clusters" There is a "bridge" connecting the clusters ...
1
vote
1answer
120 views

Procedure for the cluster-robust Hausman test

The Hausman test cannot be run on robust std. errors we have separately make the FE and RE standard errors robust to serial correlation and heteroskedasticity by clustered standard errors. So, is ...