# All Questions

21 views

### machine learning to predict unknown future positions of a vehicle

I want to predict the future steps(arbitrary physical location) of a vehicles trajectory using machine learning algorithms at least 4 to 6 seconds ahead. Currently I have tried to predict before 6 ...
3 views

### Excluding cases before or after calculating mean-centered variables?

I stumbled upon the following problem and was wondering how to address is adequately: I have a large dataset with around 60 groups, each of them with 4-6 people. For my study, each participant's ...
31 views

### Relationship between event and random variable?

I've been told that an event is just a random variable that has been assigned, and that random variables are a generalisation of events. However, I can't relate that to the definition of an event as a ...
20 views

### How to make a 2-way ANOVA graph cleaner? Is there another test for these data?

I'm working with data from an experiment where we tested 4 different concentrations of a drug on cells, plus the same drug but inhibited, an inert protein (BSA) and the medium only control. We also ...
39 views

### Bayes theorem in odds form - incorrect in Tetlock's 'Superforecasting' book?

Page 170 in Philip Tetlock's et al. Superforecasting book shows Bayes' theorem in odds form as: $$\frac{P (H|D)}{P (\neg H|D)} = P (D|H) P (D|\neg H) \frac{ P (H)}{P (\neg H)}$$ Posterior Odds = ...
13 views

### Sampling vector so they will have a given euclidean distances matrix

Given a matrix $M\in\mathbb{R}^{P\times P}$ , is it possible to sample $P$ vectors $u_i\in\mathbb{R}^N$, $i=1..P$ so that $\|u_i-u_j\|=M_{ij}$. Obviously for not any $M$ this is possible, i.e. it has ...
20 views

### Aggregating standard deviation to a summary point

I have a range of data (server performance statistics) is formatted as follows, for each server: ...
5 views

### Odds of specific generated population of exponential distributed stochast

I'm trying to generate a sequence of samples using an exponentially distributed stochast, i.e., making a Poisson arrival process. In my specific case I generate 337 samples using a lambda (rate ...
26 views

### Fit error-in-variables polynomial regression using mle2 (R)

I need to fit a polynomial regression that accounts for measurement errors. I found out how to do it with a mcmc model (using RJags) and I would like to do it with a Maximum Likelihood Estimator ...
11 views

### Cluster into communities a graph with negative edge weights representing repulsion [duplicate]

Consider an undirected graph $g$ with some edges having negative weight - all weights in $[-1,1]$. We are seeking communities or clusters. Negative edge weight means repulsion and positive means ...
5 views

### Comparing 2 treatment groups in a randomized experiment

Good morning, I am drafting a randomized experiment testing the effects of A. an increase in quantity of kcal assumed in meals B. an increase in the quality of meals (quality defined both in terms ...
12 views

### Where can I find the documentation of syntax for Alogit (the Conjoint analysis software)? [on hold]

I have to use the Alogit conjoint analysis software (http://www.alogit.com/) in a conjoint study but I can't find any complete documentation on all the modelling syntax available to use in its ...
21 views
+50

### Recurrent neural network for object tracking & position filtering?

Would a recurrent neural network be appropriate for object tracking tasks? Mainly I will have 3D feature vectors $(x, y, t)$ where $x$ and $y$ are the positions of an object in the image and $t$ is ...
22 views

### Can I use k-folding to train a model without testing set?

If I have few data, testing the model can be a problem as I have less data to train it, so I would like to know if it is possible to generate a model with all data I have, and give as AUC the mean of ...
19 views

### Why does gradient descent work so well with multi-layer neural networks?

It seems that whenever neural networks can be applied successfully, there are sufficiently many local minima on the optimization surface $S(\mathbf{w})$ (as a function of the weights $\mathbf{w}$) ...
11 views

### Nonlinear control by neural network

A Furuta pendulum is a highly nonlinear mechanical system and I'd like to attempt to create a NN that "learns" to control this system by learning the dynamic properties of the system via trying to ...
30 views

### Tricky Question re Customer Purchase Probabilities

I would like to calculate some parameters relating to customer purchasing in a retail situation. I have some basic information which I can use: Customer visit frequency in the form of probability ...
10 views

### Correlation between text and numerical data [on hold]

Is it possible to correlate text and numerical data? I work with R or Excel at the moment. I tried to find answers for that but its really difficult and very much dependen on the case. I have data ...
8 views

### Computing conditional probaility: population Spearman rank correlation

Let $Z$ and $U$ are independent random variable distributed over $[0,\infty]$ and $(0,1)$ respectively. We also assume $S$ and $T$ are identically distributed random variable over ...
9 views

### Test fitness proportionate selection algorithm implementation

I implemented a couple of algorithms for fitness proportionate selection (roulette-wheel, alias method and roulette-wheel via stochastic acceptance) and now I want to write a test to ensure that ...
26 views

### Cutoff value in linear discriminant analysis with two groups

I have a simple linear discrimininant analysis with two classes. Prior probabilitiest are fixed to 0.5 and number of cases is equal between groups. In this case the cutoff value could be calculated as ...
3 views

### Comparing classifiers using F-score obtained from cross-validation

I've seen in this post: Averaging precision and recall when using cross validation, that using F-Score obtained from cross-validation for comparing two classifiers has some issues, like the case of a ...
15 views

### How to capture investment preferences from a conversation between banking and advisor using machine learning?

we are trying to build a technology helping to connect investment advisors to their clients. The goal would be to push "relevant information" to the clients (performance thresholds, major market ...
13 views

### Which model to choose [on hold]

given by spss expert modeler "ARIMA (0,1,0)" Normalised BIC 15.452 RMSE 5803 MAPE 13.081 Stationary R squared -5.54E-16 Ljung Box Test Sig 0.002 Given by auto.arima R package ARIMA ...
23 views

### VIF to find multicollinearity

I tried VIF on the Longley dataset to look for multicollinearity. (I have used a custom function returned in ...
15 views

### ln (log) of energy consumption in a econometric analysis [duplicate]

i'm applying a panel data analysis. I have four variables; real GDP, trade openness, energy price and energy consumption. I took ln (log)of trade openness,real GDP and energy price. but i cannot ...
3 views

### Getting a very low Phi value for a 2x2 table with pretty large effect size?

The 2x2 contingency table looks like this Converted Didn’t convert Hi 220 1606 low 188 1881 The ratio of converters for Hi vs Low is 0.12 ...
9 views

### How to calculate pseudo R2 when using logistic regression on aggregated data files?

I encountered a strange phenomenon when calculating pseudo R2 for logistic models when using aggregated files: the results are simply too good to be true. An example (but as far as I can see, every ...
9 views

### Select the baseline methods for ensemble time-series model

I have been reading about ensemble time series models which have often been shown to perform better than single methods. I did not manage to find any reference on how to select the baseline methods. ...
21 views

### Computing Blosum Matrix with threshold [on hold]

Why does the answers to the problem found in the referenced pdf, differ from my calculation below? I am trying to understand the math from this pdf from an online tutorial I am reading and my own math ...
12 views

### What happens if we use training data in reverse chronological order?

My SGD-Adagrad algorithm uses chronological data for training for future predictions. The test and validation data has occured after training data. What happens if I use training data in reverse ...
43 views

### Classification problem: does it makes sense? (looking for someone who can deliver a project) [on hold]

I got assigned this database from UCI containing categorical and numerical variables. auto<-read.table("https://archive.ics.uci.edu/ml/machine-learning-databases/autos/imports-85.data") The ...
4 views

### Generate points to test PR Curve plot

I would like to generate a list of (label, score) for which the PR curve is a line so that I can inspect it easily and see that my PR plotter works. If we consider ...
40 views

### What to do if number of features is much larger than number of observations?

I have the following concrete example of the problem. Every day I measure 15 different parameters. In the end of the month I have one number (let's call it "target") associated with the given month. I ...
5 views

### Models and features used to estimate the propensity score in financial services (Banking)?

I'm trying to figure out how to compute the probability of a bank customer converting after sending him an offer. After a lot of research i found that propensity scores is what i am looking for. This ...
35 views

### Detect if an incoming value in streaming data is an outlier

I am reading a sensor that gives data. Sometimes some data is false. I can store some samples before and I would like to detect a glitch on the fly. Process : Values are integers (distances in ...
39 views

### How probabilities are calculated for SVM model?

I would like to know, how probabilities are calculated in support vector machine. I have used Iris data set and here is my decision values for three "SupportVectorMachine" (please find the PMML below ...
16 views

### Measuring variable with different number of Likert scale

I have 5 latent variable which 3 of them are measured using 5 point Likert Scale and the other 2 measured using 7 point Likert scale. is this going to be a problem when I make regression for my modmed ...
14 views

### How to estimate a Simple Quadratic Equation

Hello i am quite new to economic application and have a really simple question about estimating a quadratic equation. I have a time series data set with 55 points and want to estimate a quadratic ...
9 views

### Best performance evaluation measure for GARCH model?

I want to compare the performance of various volatility models like GARCH, eGARCH, and gjrGARCH from actual volatility (computed using high frequency data). I found three common performance evaluation ...
14 views

### How to specify weights for the adaptive LASSO in R? [on hold]

To implement an adaptive LASSO, we need to first specify weights. However, in the "parcor" package of R, the adalasso function just assumes that we use weights from LASSO. Is there any way to specify ...
82 views

### Find probability of sample mean if sample size is unknown [on hold]

In a Normally distributed population, Population Mean and Standard Deviation is 1 and 2 respectively. Find the Probability of Negative Sample mean.
23 views

### What does prime mean in the notation $k(x,x')$ in the context of kernels?

I admit it's a very specific question, but what is meant by the notation $'$ in Bishop's book Pattern Recognition and Machine Learning? I'd always thought it's a transpose, but this marked by a ...
6 views

### How to create this graph in SIGMAPLOT

I'd like to ask 2 questions. 1. How to create this graph in SIGMAPLOT. I have tried it in several ways but didn't find the right one? 2. What model will be used for fitting to this data?
20 views

### Time series with missing data period

I have time series measured every 10 seconds with missing periods in between and a repeating pattern.How do I handle this data to fit a model and forecast the future using R
4 views

### How to estimate parameters of data sets that have different missing value type with 3PL model in R?

I had a 10 complete dichotomous (1-0) data responses which were responded by 100 person and I created with it three data sets that each of them has different type missing value (MCAR, MAR and MNAR). ...
68 views

### Finding the distribution for the sample mean from a normal distribution not knowing its size [on hold]

My Intro to statistics professor asked this question in class today: If the mean of a normal distribution is 1 and the standard deviation is 2, what is the probability of a negative sample mean? My ...
54 views

### Differences between statistical computing vs computational statistics vs statistical programming? [on hold]

I am writing resumes and material for PhD applications and feel it is very important not to say I do something which I don't actually do. These terms get jumbled up some times and I am interested if ...