Tagged Questions

Data organized into discrete categories or *classes* may present problems for certain analyses if the number of observations ($n$) belonging to each class is not constant across classes. Classes with unequal $n$ are *unbalanced*.

learn more… | top users | synonyms

3
votes
0answers
179 views

Mixed ANOVA: small and unbalanced samples

I have to analyze two samples ($n_1=10, n_2=18$) in a design in which there is a between-subject factor (Groups: 2 levels) and a within-subjects factor (...
7
votes
2answers
695 views

Does a big difference in sample sizes matter for an independent t-test?

There is a very confusing question in my mind. I have data, and would like to compare numeric scores between men and women. There is a big difference in those two groups: the number of men is 34, ...
0
votes
0answers
69 views

How do you analyse an unbalanced dataset using dummy variables?

I have a returns (finance) dataset with 3 factors, each with 3 levels: industry (banking, retail, others), year (2010, 2011, 2012), and size (small, medium, large). Each factor has been coded as a ...
0
votes
0answers
122 views

Interpreting coefficients for random effects models with extremely unbalanced data

I'm currently working with a data set that has numerous samples collected over time at different sites in a study area, and I'm interested in detecting a trend over time for that area. I know that in ...
3
votes
1answer
53 views

What test of significance should I use to analyse visits to a clinic by various groups?

Apologies for the noob question. After a day on Google and Wikipedia I still can't quite work out what to do. So here I am. A small private healthcare clinic in the UK has asked me to look at their ...
0
votes
2answers
81 views

Choosing the best featureset for prediction

I have this N sets of features F each with $F_i$ number of features. All the feature sets have 20000 examples and we have 20,000 labels for them. Lets say feature set $F_1$ has 10 features and ...
1
vote
1answer
81 views

Finding the best dataset for classification

I have 100 datasets. All of them have varying number of features. There are around 20,000 samples in each of them. Every $i$-th sample in the 100 datasets has the same label ($0/1$). The data is ...
0
votes
2answers
263 views

How similar are my 2 data sets?

I am kind of stuck with an easy question: I have two data sets with experimental data. The data sets do not have the same size. I would like to show that these data sets are possibly coming from the ...
0
votes
0answers
28 views

Impact of biased sampling on classifier training ?

Let's imagine I have a very unbalanced dataset with 99.99% of 0 and 0.01% of 1 on the target variable. What I want to do is make a classifier for this target. Now imagine that this dataset is very ...
5
votes
2answers
327 views

Classification problem using imbalanced dataset

I am working on a pattern identification/classification problem on an imbalanced dataset, with target to non target proportion in population approx as 1%:99%. There are around 0.5 million records in ...
0
votes
0answers
60 views

Sample size for binary text classification

In my application as a Binary text classification, one class has around 36,000 sample and another one has around 300 samples. I under-sample the first class. So, each class will have ~ 300 samples. ...
3
votes
1answer
281 views

classification threshold in RandomForest-sklearn

1) How can I change classification threshold (i think it is 0.5 by default) in RandomForest in sklearn? 2) how can I under-sample in sklearn? 3) I have the following result from RandomForest ...
0
votes
0answers
57 views

Model selection for unbalanced data

How to do model selection for unbalanced data? how many data points from the whole data set should be selected for model selection? how many for training and testing?
0
votes
2answers
744 views

Dataset of repeated measures with unbalanced sample size and unequal variace - What to do?

I have a dataset of three groups of cells treated with 10 different compounds and am not sure how to check for significant differences between those treatments. Within each group the data is also ...
0
votes
1answer
253 views

Imbalanced data classification using boosting algorithms

I am working on a binary data classification problem. The dataset is imbalanced, it consists of 92% 'false' labels and 8% 'true' labels. The number of features is 18 and I have a small number of 650 ...
1
vote
1answer
149 views

Denominator is Zero for Matthews correlation coefficient and F-measure

Recently, I built a classification model based on the imbalanced data set(positive sample is minority and negative sample is majority), and the model gave the following result for the test set: ...
4
votes
1answer
436 views

Is a large control sample better than a balanced sample size when the treatment group is small?

I am running an experiment looking at brain volume changes in a rare disorder. We have a small number of patients (n = 8) but a large control group (n = 100). Some colleagues have suggested that a ...
2
votes
1answer
106 views

Outlier detection: at which degree of class imbalance would you consider a one-class model over a two-class model

Background: I am working on the problem of classifying objects found in some biological images. Time and again, we encounter objects which do not fall into any of the categories/classes we are ...
2
votes
0answers
225 views

Repeated measures ANOVA for an experiment with missing values

I have an experiment where several subjects (subjects $= S_1,S_2,...,S_m $) were asked to perform a set of tasks (tasks $= T_1, T_2, T_3,...,T_n$) using both their left ($L$) and right ($R$) arms. ...
2
votes
1answer
306 views

SMOTE throws error for multi class imbalance problem

I am trying to use SMOTE to correct imbalance in my multi-class classification problem. Although SMOTE works perfectly on the iris dataset as per the SMOTE help document, it does not work on a similar ...
3
votes
2answers
282 views

Named entity recognition and class imbalance

I have implemented Maximum-entropy Markov model (MEMM) for the Named entity recognition (NER) problem. I have four classes: geographical, people, material (book titles etc) and other. Class ...
1
vote
2answers
636 views

By using SMOTE the classification of the validation set is bad

I want to do classification with 2 classes. When I classify without smote I get: ...
2
votes
1answer
68 views

Looking for simple examples of how to calculate type III and type IV SS

I have data collected on five species of fish at half a dozen locations in a lake over four years. The categories are not (at all) fully crossed, and I have a lot of empty cells due to logistical ...
4
votes
2answers
370 views

Testing Classification on Oversampled Imbalance Data

I am working on severely imbalanced data. In literature, several methods are used to re-balance the data using re-sampling (over- or under-sampling). Two good approaches are: SMOTE: Synthetic ...
0
votes
0answers
108 views

How to create the class range given 1 as the middle class, 3 as the highest value and 0.65 as the lowest value?

Good day. I know getting the class interval given 3 as the highest value and 0.65 as the lowest value is easy. Here's the catch, the distribution of the interval starts at 1 which is considered as the ...
0
votes
1answer
265 views

How to balance classification?

I have a binary classification problem, where my training data is 70% positive labeled and 30% negative labelled. I use a logistic loss and it always classifies examples positive on the test data. ...
3
votes
0answers
217 views

Problem with classifier after using SMOTE to balance the data

We've ran into a problem while training a classifier on an unbalanced data set. The response is binary with 0 indicating 'non defaulter' and 1 indicating 'defaulter' (it's a credit scoring task). ...
4
votes
0answers
236 views

Mixed-effects model for a strongly unbalanced design

I am somehow unsure on the best option to analyze these data. Here is my study case: The response variable is a morphometric measure, one for each individual. During 10 years, say 2000-2009, people ...
3
votes
1answer
964 views

Which performance measure for unbalanced binary classification without an 'active' class?

My datasets have two classes A and B. The classes should be treated equally (there is no "active/inactive"). The datasets are unbalanced, sometimes A is more frequent, sometimes B is more frequent. ...
1
vote
1answer
816 views

How to set SMOTE parameters in R package DMwR?

For different imbalanced data-sets which rare class' proportion differ from 30% (rare) to 5% (rare), what is the best way to define the Perc.Over and ...
1
vote
0answers
79 views

Type I ANOVA tests not depending on the order of the factors

I have a dataset with two factors A and B and the following design (contigency table showing the number of individuals for each ...
1
vote
2answers
155 views

Can I run a GLMM model when I have one observation for most subjects?

I have a binary DV and my panel data set contains more than one observation for only 20% of the subjects which makes it very unbalanced. Is there anything methodologically wrong with doing a mixed ...
2
votes
0answers
189 views

How to use k nearest neighbours for binary classification with unbalanced classes?

I have relatively large (100k items) dataset which I need to split in two groups. So far I've tried knn and the results are not good mainly because I have disproportion in my training data: 90% of ...
3
votes
1answer
979 views

Balanced accuracy vs F-1 score

I was wondering if anyone could explain the difference between balanced accuracy which is b_acc = (sensitivity + specificity)/2 and f1 score which is: ...
3
votes
2answers
3k views

LibSVM cost weights for unbalanced data doesn't work

I have a dataset where the number of negative labeled values is 163 times the number of positive labeled values. That is, I have an unbalanced data set. I tried: ...
1
vote
0answers
101 views

Different Mean Square partitions in an unbalanced bifactorial ANOVA (with random factor) between R and Statistica

I am trying to extract variance components for selection and chance in a bifactorial design with Generation as a fixed factor and Replicate as a random term, for early fecundity. Since I am using ...
4
votes
1answer
110 views

Logistic regression without negative samples

I have a data set of RNA reaction values of breast cancer. I want to figure out which RNAs are essential genes by Logistic Regression & LASSO. The data set has no negative samples. What should I ...
5
votes
3answers
248 views

Experiment design: Can unbalanced dataset be better than balanced?

I'm on the stage of experiment design of some biomedical time-course study. Let's say we will have 2 groups of subjects - case and control. The total number of subjects is limited (for example, 30), ...
10
votes
1answer
505 views

How to handle the difference between the distribution of the test set and the training set?

I think one basic assumption of machine learning or parameter estimation is that the unseen data come from the same distribution as the training set. However, in some practical cases, the distribution ...
1
vote
0answers
190 views

How to compare multiple groups of unblanced repeated measures non normal data?

I'm trying to compare three groups data. But the data set is about a new drug trial. The data set has these characteristics: Follow-up set. That is, after administration of the drug, a series of ...
6
votes
1answer
472 views

CART (rpart) balanced vs. unbalanced dataset

I am fitting a tree (CART) to the olives-dataset. The training data has 436 observations (test data: 136). I have 3 responses (the 'Region' variable) which splits the training data into 116 / 74 / 246 ...
7
votes
2answers
925 views

Classification with GBM in R and imbalanced class sizes

I'm dealing with a supervised binary classification issue. I'd like to use the GBM package to classify individuals as uninfected/infected. I have 15 times more uninfected than infected individuals. I ...
0
votes
1answer
291 views

How to handle data imbalance in Principal Component Analysis?

PCA reduces data set dimensions while trying to keep most variations in data set. PCA can be used as a dimension reducing technique in discrimination, however it tries to keep the most discrimination ...
2
votes
0answers
864 views

Using AdaBoost on multi-class in R on unbalanced data

I have a data set which is highly imbalanced and I have used the SMOTE algorithm (using the R package DMwR) to balance the binary class in the data set. I have been using the R Ada package to then ...
2
votes
1answer
209 views

Proper order of variables in unbalanced ANOVA

If you have unequal sample sizes in cells, then the order in which you enter model terms changes your results for sequential or Type I SS. The first variable to enter the model is allocated its ...
10
votes
2answers
3k views

Training a decision tree against unbalanced data

I'm new to data mining and I'm trying to train a decision tree against a data set which is highly unbalanced. However, I'm having problems with poor predictive accuracy. The data consists of students ...
6
votes
1answer
765 views

A priori selection of SVM class weights

I remember seeing/reading somewhere that for multiclass SVMs with unbalanced data, there was a way to determine the class weights from the training data (rather than X validation). Does anyone know ...
3
votes
3answers
2k views

SVM vs. artificial neural network

I have multiclass unbalanced data (4 class with 15% 25% 45% 15% data in each class). Which method is good for classification of such data- SVM or ANN? UPDATE- Let me make the question little more ...
2
votes
1answer
466 views

Are there problems with inference using linear regression on observational data with highly skewed distributions of predictor values?

I am using a linear regression model to perform inference on some observational data. The samples are from an observational study and highly skewed along some of the dummy variables in the regression. ...
10
votes
1answer
1k views

Optimising for Precision-Recall curves under class imbalance

I have a classification task where I have a number of predictors (one of which is the most informative), and I am using the MARS model to construct my classifier (I am interested in any simple model, ...