0
votes
0answers
2 views

What tests and plots to use with conditional probability?

I have datapoints collected from Italian students' curricula, including final marks received for one Exam (between 18 and 31) and their Final Degree (cum- or sine-laude). I’m interested in studying ...
1
vote
1answer
8 views

Different results using Brier score and Logarithmic scoring rule

Let $X_i\sim B(\pi_i), \text{for }i=1,2,\cdots,n$. I have two models and I want to compare which of them forecast better. Model 1: Estimates the parameters with maximum likelihood. Model 2: ...
0
votes
0answers
4 views

Difference in Difference vs repeated measures

Hi I am trying to understand the difference between Difference in Difference analysis and a repeated measures ANOVA. My DiD data set is made up of 32 treated and 32 non treated subjects each with 2 ...
0
votes
0answers
3 views

How to round strata size in stratified sampling?

I'll try to illustrate my question with an example of a stratified sampling study. Let's say we have a population of 1000 and we want take a sample of 100, hence a fraction of 10% from each strata. ...
0
votes
0answers
3 views

Pattern-mixture models

I am currently looking at pattern-mixture models but I don't see to understand them and I wonder if someone could help. I can see the model comes from the factorisation $ f(y,r;\phi, ...
1
vote
0answers
15 views

How to analyze trend in non-periodic time series

Suppose I have following non-periodic time series. Obviously the trend is decreasing and I would like to prove it by some test (with p-value). I am unable to use classic linear regression due to ...
0
votes
0answers
5 views

Year on year model performance evaluation via bootstrapping

I am interested in monitoring the yearly evolution of model’s performance (a Loss Given Default model more specifically). The yearly additional data, however, is very limited (maximally 5 ...
0
votes
0answers
9 views

Normalize sum(case when..) [on hold]

In Netezza I ran the following query to make the nominal variables into binomial ones and sum them up: sum(case when c.COUNTRYCODE = 'US' then 1 else 0 end) as US ...
0
votes
0answers
10 views

Why training, validation and test set for 3 experiments

I have spectral data and I would like to make predictions. I record one spectra per minute and each run takes about 200 min (=200 spectra). I was taught to make 3 runs; one for the training set, one ...
0
votes
1answer
15 views

Combining two probability scores [duplicate]

This question is rather mathematic, and I am quite sure some theory should already exist but I can not find it... Say I have some data records, and for a certain record X two independent statistical ...
0
votes
0answers
6 views

Method validation in non-regression problems

Assume I have a sample of r species/classes that follow a multinomial distribution, where the vast majority of classes only are observed once. Further, let us say I have k models that all are giving ...
0
votes
0answers
2 views

CIFAR - Why is it stored using RGB Chanels?

I am now fiddling around with the CIFAR dataset. After reading this page I have come to know that the images in CIFAR are not stored as RGB Pixels but as RGB channels. That means all the red values ...
1
vote
0answers
12 views

How Do I choose parameters of prior on regression coefficients in a Bayesian linear model?

I'm trying to perform a linear regression in a Bayesian way. The response is normal,the prior I would like to put over Beta (vector of regression coefficients) and Sigma^2 (variance of the error ...
0
votes
0answers
12 views

Representative observations from the hierarchical clustering results

I'm using the hierarchical clustering to generate groups from unlabeled dataset (or observations). I’m using the matlab function ...
0
votes
0answers
4 views

Selecting/Filtering data for analysis in Gephi [on hold]

I have a question regarding filtering and statistics. Specifically, I would like to run statistical analyses such as average degree only for a part of the data (e.g. all data where gender=male) So ...
0
votes
0answers
7 views

ordinal logistic regression with time series

At several time points, I sample different individuals from a population (say 60 ind/time point). I assign to each of them one category (either low < middle < high). I then want to model this ...
0
votes
1answer
9 views

Can (how) you enter control variables in a binary logistic regression?

I'm running a binary logistic regression to test whether personality ratings (scale of 1-5) predict a binary outcome, in children. I want to enter factors such as age and gender as control variables, ...
0
votes
0answers
8 views

Which test statistic to use to test for cross-sectional dependence in panel data (R, plm)?

I would like to test for cross-sectionally dependent residuals in my panelmodel (pooled). I found pcdtest() in plm package and tried ...
0
votes
0answers
4 views

How to properly project a value representing 38% to 100% to show potential range of true value?

I have a value x that represents 38% of total customer's data. I want to project it to 100%, but the result of (x/38)*100 is much higher than what the true value should be. What is the best way to ...
0
votes
0answers
12 views

How to model Not Applicable (N/A) input in a Neural Network?

Assume I have a Neural Network with an input value to distinguish 2 discrete categories, e.g. Bicycle (input -0.9 in case of tanh) or Car (input 0.9 in case of ...
0
votes
0answers
10 views

Probability Independent events

I am currently doing an online statistics course for my program. I am stuck on one question where it is asking me to determine if the two events are independent. I would like a confirmation from those ...
0
votes
1answer
16 views

Significant in bivariate regression, but not significant in multivariate regression

I have two variables A and B, predicting X. The variables were entered in a two stage hierarchical multiple regression, with variable A entered in Stage 1, and Variable B entered in Stage 2. The ...
1
vote
0answers
4 views

Continuous, sometimes negative residuals from Poisson-distributed variable - how to analyze?

It's been years since I've taken my grad school stats courses, and it's a subject I struggle with, so bear with me. I am attempting to analyze a dataset containing two Poisson-distributed variables ...
0
votes
0answers
12 views

Cost function: output layer should sum up to roughly 1

I have a convolutional neural network classifying some images for me. The output layer is not one-hot encoded but outputs a distribution around the predicted class (because neighboring classes are ...
0
votes
0answers
4 views

OLS and GLM - residuals plots and lack/goodness of fit statistics in JMP

It's been years since I've taken my grad school stats courses, and it's a subject I struggle with, so bear with me. I'm attempting to fit some sort of linear model to several response variables. In ...
0
votes
0answers
9 views

Loss function selection for weighting errors differently

I am building a regression model where I want to score/optimize/train 'over-predictions' to be twice costly as under predictions. I am attempting to do this in R and hopefully with caret package. ...
1
vote
0answers
18 views

R Poisson process simulation for a queuing problem [on hold]

I'm working on the problem - patients come into a clinic according to a Poisson process with time parameter 10 minutes starting from 9 am until 4pm when the clinic stops admitting new patients. There ...
0
votes
0answers
3 views

Draw samples from distribution that add up to specific value

I'm currently working on a fire distribution model in which fire sizes are log-normally distributed. In my simulation, in each time step, fire sizes are sampled and summed up until a certain fixed ...
1
vote
0answers
10 views

Calculating the probability of an event being early or late by a certain amount

I'm very new to this so I assume there's a better way to ask this that I just don't know about. Please point me in the right direction. Suppose I'm running a library and books are due 30 days after ...
0
votes
0answers
4 views

Non Homogeneous Poisson Process Insurance example [on hold]

An insurance company finds that for a certain group of insured driver , the number of accidents over each 24 hours period rises from midnight to noon and then declines until the following ...
1
vote
1answer
21 views

Minimum “recommended” sample size for boxplots? Boxplots for different sample sizes

What is the minimum "recommended" sample size to generate boxplots? If I'm comparing different methods and each method has a different sample size, is it fine to use boxplots for this comparison? If ...
0
votes
0answers
9 views

Creating Naive Bayes Model for numerical data in R

I want to calculate the missing value using the NaiveBayes predictor. I am using a dataset with missing values at some rows, ...
0
votes
1answer
23 views

GLMM or LME? Repeated measures help?

I am having trouble using the correct test and r code for my experiment. Essentially I measured insect emergence daily from artificial streams with 3 treatments.: CONTROL - With 5 replicate streams ...
2
votes
2answers
65 views

Gradient descent: compute partial derivative of arbitrary cost function by hand or through software?

I'm a software engineer, and I'm working my way through Stanford professor Andrew Ng's online course on machine learning. I'm able to follow most of the math related to gradient descent for linear ...
0
votes
0answers
25 views

Why coefficient changes sign between linear and logistic regression?

My dependent variable $Y$ is continuous a linear model is estimated: \begin{equation} Y = \beta_{0} + \beta_{1} X + \epsilon . \end{equation} I transform the dependent variable into $Z = 1 \text{ if ...
-1
votes
0answers
15 views

Don't Understand Installation and Use [on hold]

I have just downloaded r and r studio. I scroll to the bottom when I open the R studio but do not see anything about SDS despite the fact that I have tried to download it several times. Please advise! ...
0
votes
0answers
9 views

Accuracy in neural network for regression

I want to measure the accuracy in neural network that performs regression. I have two outputs. Is the root-mean-square deviation ( RMS wiki) the right way to go? From wikipedia RMSD is a good ...
0
votes
0answers
9 views

Predict function in r - time series

I have built a model on my training dataset where I have used the difference of the log(Y) i.e. diff(log(Y)) as my response variable. Now if I want to use this for predicting the Y variable in my ...
0
votes
0answers
16 views

Is Deep Neural Networks suitable for Cancer Detection? [on hold]

I am currently working on a project which main topic is to analyze a patient's medical images in order to know if she is affected by Cervical Cancer or not. One image contains 6000 pixels. For each ...
1
vote
0answers
8 views

How to plot ROC for knn (and potentially kernel spectral regression)

I understand how to plot ROC for logistic classifier (like varies the probability cutoff). For KNN, how can I find the ROC? Also, what about kernel spectral regression?
0
votes
0answers
5 views

Deriving the expectation of an OU model

I have an Ornstein-Uhlenbeck model (listed below) and I know what the expectation and variance should be, but I am having difficulty deriving them for myself. Can anybody point me towards a good ...
0
votes
1answer
14 views

glasso- Assumptions of Meinhausen-Buhlmann approximation?

First off, This is not an R question - it is a conceptual question, so there is no need to perform any code. Problem: I'm trying to invert a large dimensional covariance matrix of p features. For ...
0
votes
0answers
16 views

Selecting Subset of Quantitative Variables in R [on hold]

Is there a way to generate a subset of my quantitative variables in R, without having to manually select them in the subset() command? I have very many quantitative variables, and it would be too time ...
0
votes
2answers
17 views

Generating parameters from lognormal or Gamma likelihood

I need to draw the gamma or lognormal parameters only from their likelihood functions. I'm using uniform prior, so the posterior distribution coincides with the likelihood functions. Is there a ...
1
vote
1answer
25 views

Different coefficient values from multiple versus bivariate regression

I wonder how to generate such data, so that in single variable regression feature coefficient would be positive, and in multiple regression would be negative. So I read several related questions on ...
0
votes
0answers
5 views

Partial Correlation - Quantifying the effect of removing confounding variables on the correlation

I'm conducting partial correlation in order to quantify the association between two variables, X and Y, after the effect of a set of confounding variables Z has been removed from both X and Y. In ...
0
votes
1answer
9 views

How to properly calculate average need-based aid met by an institution?

As an institution we give out a certain amount of financial aid every year (need-based aid) to each student. This need-based aid does not always meet the students estimated need. My task is to compare ...
1
vote
1answer
11 views

Has order of an attributes impact on neural network learnig?

I want to ask if order of attributes can impact on neural network learning. Is it the same if the input vector looks like this: a b c d e and like this: ...
-1
votes
0answers
25 views

Who is most likely to create Artificial General Intellgence first? [on hold]

Is it Jürgen Schmidhuber with his Gödel Machine? If not, please state your reasons
0
votes
0answers
9 views

Mult regression: Dealing with assocation between a dummy IV and a continous IV

I'm running a multiple regression and I'd like to include two variables related to online reviews: one for review count and one for avg review score. The complication is that about half my sample ...

15 30 50 per page