All Questions

1
vote
1answer
13 views

Removal of partitioning variable in final glmtree with new (unused) partitioner — why?

I'm modeling the likelihood of forest recovery from fire (data here), using glmtrees from the partykit package. I'm quite new to this approach and CV, so I ...
0
votes
0answers
15 views

What is the difference between finding the threshold and training a binary classifier?

I have 1-D data: the output of a Cosine similarity (COS) distance between two features. The data is bounded by [-1,1]. When I just try to find the optimum threshold for class labels - I get an ...
0
votes
0answers
21 views

Using chi square on unequal groups with unequal repeated trials

My dataset includes four groups (A, B, C, D) of unequal numbers of individuals. Each individual engages in an activity that results in three categorical outcomes (X, Y, Z). The individuals repeated ...
0
votes
0answers
5 views

Binding Sets of Points to a Set of Polygons in R [on hold]

I am trying to bind a set of points to a set of polygons for the purpose of spatial analysis. I want to retain the attribute information associated with both the points and the polygons. I understand ...
1
vote
1answer
43 views

One-to-one best string match [on hold]

I have two vectors of strings, and each element in one vector matches one or zero elements in the other vector. No one-to-many or many-to-one pairs. The closest matches are found with a stringdist ...
0
votes
0answers
18 views

Gamma glm log link - what does predicted values mean

Does the predict function in R for gamma glm with log link predict the actual values or the mean value? There is a gamma glm model in R with log link. Using predict(model,data,type = 'response') to ...
0
votes
0answers
6 views

Adding Bad Events from the past to the risk default model to avoid Down/Up sampling techniques

We have been trying to build a classification model for credit default prediction using two different models one being Random forest and another being the Logistic regression based scorecard model. ...
1
vote
2answers
15 views

correlation-based effect size

how can a correlation coefficient of .40 be a "medium" effect size when r2 shows that the variables only have 16% common variance? Seems like the 16% suggests a small effect size. Jim
0
votes
0answers
8 views

How to draw a random matrix from Wishart distribution in Python? [migrated]

I am interested in drawing a random matrix from Wishart, and I wonder if there is anything in numpy/scipy for it. Google returns this for R, but haven't found anything for python.
1
vote
1answer
24 views

New factor levels in testing data set not present in training data in h20.randomforest

In randomforest classification using h20 package, there are factor levels which are present in testing data but not in training data.There is a warning message in predicting the values of testing data,...
1
vote
1answer
22 views

Propensity score matching: bias adjustment

I'm using propensity score matching to match similar individuals. I.e., I first estimate a propensity score (the probability of treatment conditional on some set of variables) and then match on the ...
0
votes
0answers
20 views

Number of Hidden Layer Nodes in Recurrent Neural Networks

There's already a decent discussion on how to select the right number of hidden layers and hidden nodes in a feed-forward neural network: How to choose the number of hidden layers and nodes in a ...
0
votes
0answers
11 views

Deep learning on localisation [on hold]

I am using a dataset consisting of the deplacement of one person. Let's say that the time scale is one month. Throughout the day at more or less random intervals, the position of the person and the ...
0
votes
1answer
51 views

How are p-values computed from t-values when doing regressions?

I'm performing a regression analysis using the statsmodels module in Python. The regression gives both t-values and p-values for each coefficient, but I'd like to understand exactly which test is ...
0
votes
0answers
11 views

Robust meta-analysis with robumeta package in R

I used the samples' mean ages as a moderating variable for a meta-analysis on the relationship between two variables. I used the robumeta package and I found the mean age in 20 of the 21 studies (the ...
0
votes
0answers
13 views

How to train a own question and answer dataset [on hold]

I have question and answer data set and i want to train a model so that similar questions will have same answer, How to train the data and which network should i use.. As classification may lead to ...
0
votes
0answers
7 views

DCGAN generator accuracy doesnt improve for high-res images

I trained a DCGAN on MNIST and CelebA dataset with 28x28 image size. Both the models were able to train successfully. I used many tips from https://github.com/soumith/ganhacks to make both the G and D'...
1
vote
0answers
12 views

Find roots of regression function

Physical problem: Signal data comes from several sensors (e.g. 4) and there is empirical knowledge, that data of one of them (e.g. "productivity") depends on other data. Signals of other sensors could ...
0
votes
0answers
9 views

Can an embedding layer be replaced by a fully connected layer?

Due to architecture choices and organization of code, I have a file called data.py that processes texts and returns two vectors : X and Y which are the vectorized text and the corresponding label. ...
1
vote
1answer
19 views

I need help with choosing a mid-long term forecastic method for this demand

I am trying to forecast the demand of a product for the next 36 months, based on its sales history. The demand plot is shown below. I honestly don't know what to do with it. I tried linear and non-...
0
votes
0answers
14 views

Solving optimization problem with Neural Network [on hold]

I have a dataset with 4 variables (X1,X2,X3,Y) and my goal is to find the optimal combination of X1,X2,X3 that maximizes the Y. I've started by fitting a Neural Network model with inputs X1,X2,X3, ...
0
votes
1answer
34 views

Regression for Non Normal data using SPSS/R [on hold]

How can we model our non normal dataset using regression? By using Gauss Markov theorem, we can estimate our model, but how can we test our linear model and significance of parameters?
2
votes
0answers
17 views

does Informativeness of the prior always decreases similarity of the posterior mean to the data mean?

I am looking for a proof of the statement "If the variance of the prior distribution is greater, the posterior is more affected by the data". More specifically, if X, X' are priors such that E(X)=E(X'...
1
vote
1answer
19 views

Using log-log graph to find equation of power law relationship?

I have a set of data that I think forms a power law relationship, however I am struggling to work out the equation of the relationship. Here is a subset of the data I am working with: ...
1
vote
1answer
15 views

norm of SVM's weights vector

From solving a hard-margin SVM primal problem we get: $$ w = \sum{\alpha_i y_i x_i} \\ \sum{a_i y_i} = 0 $$ Where $\alpha$ is the lagrangian multiplier vector. After solving for $w$ (using the dual ...
1
vote
1answer
15 views

Existence of weakly stationary process for given mean and covariance

I know that if a process is weakly stationary, the mean of the process will be time-independent and the covariance will be a function of the time difference. My question: if I have a time-...
0
votes
0answers
16 views

Finding Probability of a digit given a sequences?

I have a n sequences of numbers ranges from 1 to 4, say sequence s1 = [1,3, 1, 4] and s2 = [2,1,3,4] up to s(n). My question is how can i find probability of a number coming right after a sequence, ...
0
votes
0answers
19 views

UMP test for $H_0:\theta=\frac{1}{2}$ vs $H_1:\theta>\frac{1}{2}$ when a sample is drawn from $f_{\theta}$

Suppose $X$ has the density $$f_{\theta}(x)=\left(2(1-\theta)x+\theta\right)\mathbf1_{0<x<1}\quad,\,\theta\in[0,2]$$ Is it possible to derive a uniformly most powerful (UMP) test for testing $...
1
vote
0answers
12 views

Weights as a fixed effect in a GLM

I am using a GLM to model a percentage outcome variable. Because the outcome is a percentage, I need to supply the model with weights. There is an argument that the weighting variable also has value ...
0
votes
0answers
11 views

Does 1 divided by standard deviation tell us anything? [duplicate]

(1/standard deviation) I've seen someone use this and I would like to ask for clarity on this because the intuition of it isn't immediately obvious. Standard deviation tells us how dispersed the ...
0
votes
0answers
13 views

Sklearn BaggingRegressor does not work with LightGBMRegressor & MAE objective

I'm trying to use BaggingRegressor from scikit-learn together with LightGBMRegressor and Mean Absolute Error objective and I'm receiving nan outputs. I reproduced ...
0
votes
0answers
16 views

Experimental design: two distinct, extreme group vs gradient design

I am designing an experiment in which I am exposing animals (the salt marsh-inhabiting amphipod Orchestia gammarellus) to environmental drought and salinity stress. I want to induce an evolutionary ...
0
votes
0answers
16 views

smoothen fit with nls model in R [on hold]

I'm trying to fit the following. I have measured decays per minute (DPM) over time and by this I want to estimate K according to equation formula = ...
1
vote
0answers
12 views

Default CausalImpact Package

I am trying to gain an understanding of the CausalImpact package and the BSTS approach. Consider the following model: $y_t = \mu_t + z_t + \epsilon_t$, where $\epsilon_t \sim N(0,s^2)$, and $\mu_{t+...
0
votes
0answers
14 views

Multiple regression, stepwise regression, interactions (Step by step) [on hold]

I have some issues to perform a multiple regression, with interactions with R. Here are my data : Independants variables (predictors) 3 levels of job categories (JC1, JC2, JC3) Yoga practice (...
1
vote
0answers
19 views

Test statistics of LMM with significant covariate interaction

When reporting on the LMM that I fitted to my data with R, I was asked to include the test statistics (df and others). But I have no idea where to extract them from, I don't see them in the summary as ...
2
votes
1answer
25 views

$k$-th order statistics when the value of $j$-th one is known

Suppose there are $n$ random variables $X_i,~i\in\{1,\cdots,n\}$ which are independently drawn according to a CDF $F$ and pdf $f$. Suppose also that we know one of the realization, say $X_{(j)}=x_{(...
0
votes
1answer
30 views

How to deal with overestimation of small values and underestimation of high values in XGBoost? [on hold]

I'm running XGBoost to predict prices on a cars dataset, I was wondering what alternatives are there for this kind of problem ...
0
votes
1answer
12 views

Distinguishing between global and national population changes of a species (a theoretical question)

So I have global and national population estimates of a migrating bird species. The species is declining nationally, but it is also declining slightly throughout the world. I want to know if the ...
0
votes
0answers
9 views

What is the best way to cluster categorical data to form homogenous groups?

I have a dataset with categorical data, some are binary some are options that have been numerically coded but are not ordinal. Most of this data is categorical "Yes/No" or Nominal for example Favorite ...
0
votes
1answer
19 views

Why there is decrease in AUC values with increase in number of iteration in Held out validation?

I have a dataset with 600 rows and 4000 columns for which I am trying to do held-out cross-validation with 10 and 100 iterations. At first, the dataset is split into 80%:20% training and “held-out” ...
0
votes
0answers
12 views

R multiple barchat per column/Graphique [on hold]

hello as part of a job I'm trying to make a graph in the form of barchat. each chart should have a column (155 column) and have the same name as the one in the column and save it afterwards please how ...
0
votes
0answers
13 views

Time-series classification of Kinect data using Keras

For my PhD project I recorded using Kinect and Myo 11 people performing Cardiopulmonary Resuscitation (CPR), repeatedly doing chest compressions to a manikin (one person per time). I collected in ...
0
votes
2answers
50 views

can one make statistical inferences from 6 patients?

Is it conceptually correct to make statistical inferences from a very small number of patients (even when using exact methods like Fisher's test, etc)? What do I have to look out for: power or p-value?...
0
votes
1answer
9 views

What is the difference between a one sample t-test and sign test?

If I've conducted an experiment with only 10 samples and the data acquired have some wide gap in values, what would I use from the two statistical method. Here are my values sample values:
0
votes
0answers
11 views

Can I ignore statistical distribution if errors are small

I'm struggling to find the right distribution for my data and only after I know which distribution suits best I wanted to select a certain statistical model. But now I can't find an appropriate ...
3
votes
0answers
22 views

IRT analysis on large sparse dataset

I have a dataset with 0/1 response data for a set of test questions. There are approx 7.5k items that have been randomly allocated to participants in an online quiz. Just over 10,000 participants (set ...
0
votes
0answers
13 views

Interpreting significant model parameters in less well fitting AIC model

I have two linear mixed effects models (among other models representing competing hypotheses) as coded in R: ...
1
vote
1answer
9 views

Testing for the significance of treatment on intervention/target group compared to control group when group sizes are different?

So I have have been conducting an experiment of an interesting feed on livestock. So essentially what I have done is, divided the total livestock $N$ in two different sized groups $n_1 $ and $ n_2$. I ...
1
vote
1answer
13 views

What is the definition of a “rectified conv feature map” in a convolutional neural network mentioned in the paper of “visual explaination”?

I have read the answer of the question What is the definition of a “feature map” (aka “activation map”) in a convolutional neural network? But I don't think that it is same as what I want. I ...

15 30 50 per page