dialog
listlengths
4
30
title
stringlengths
15
150
category
stringclasses
14 values
dialog_time
stringdate
2016-01-21 01:59:30
2018-07-01 01:34:46
[ { "message": "I would like some help with a GARCH(1,1) volatility modeling. I am working with the assumption the volatility is the weighted sum of three factors: Long run variance + $n-1$ squared return + $n-1$ varianceIf that is accurate, my doubt is, what is the difference between the 1st and 3rd parts of the...
Understanding the GARCH(1,1) model: the constant, the ARCH term and the GARCH term
stats
2017-11-18T16:57:47.133
[ { "message": "I am not quite sure if I understand the concept of the AIC and the model order of a time series model correct. My understanding is that it is some kind of algorithm which looks likeTake the ARMA (1,1) model, estimate the parameters via Maximum LikelihoodWith this Maximum Likelihood, calculate the ...
How to find ARMA order with AIC
stats
2017-11-18T17:57:52.127
[ { "message": "So I am trying to fit a real data set with initial plot of acf being<a href=\"https://i.stack.imgur.com/OZoSe.png\" rel=\"nofollow noreferrer\">But I don't recognize a time series with an ACF that looks similar to this.Should I try differencing?I attempted to remove seasonality on my original data...
What can be done in case with periodic acf?
stats
2017-11-18T20:36:09.050
[ { "message": "If I have some data in $\\mathbb{R}^N$ space, with $N$ beiling large and I want to estimate the density function of this data, $\\mathbf{P}_{data}(x)$, using the fantastic property of neural networks that allows approximation of very complex functions...I will then start with some parameterized fo...
How to estimate normalization constant during optimization of complex parameterized PDF using MLE?
stats
2017-11-18T21:41:54.123
[ { "message": "I want to predict the duration a trip would take. For this I transformed my dependent variable (trip time in sec) to log transformed.When I do regression on this variable with some other features,I get this: <pre><code>The score on held out data is: 0.08395386395024673 Hyper-Parameters for Best Sc...
Regression RMSE when dependent variable is log transformed
stats
2017-11-19T02:59:37.587
[ { "message": "I want to plot the RMSE of some models to compare their performance in a dataset. I'd like also to include error bars, because I know they may have very different standard deviations. The problem is, does it even make sense to talk about standard deviation of RMSE? I thought about taking the squar...
Does it make sense to talk about the standard deviation of RMSE?
stats
2017-11-19T05:20:58.820
[ { "message": "I am currently dealing with an issue regarding cluster validation. I have a pairwise distance matrix (based on the hamming distance between a set of core genes of different strains of a bacterium). I performed k-medoids clustering on the pairwise distances, attempting to validate my initial suspic...
Silhouette index on clusters of different intracluster variability / intercluster distances
stats
2017-11-19T11:44:38.603
[ { "message": "In page 485 of the book [1], it is noted that \"it is pointless to bag nearest-neighbor classifiers because their output changes very little if the training data is perturbed by sampling\". This is strange to me because I think the KNN method has high variance when $K$ is small (such as for neares...
Is it pointless to use Bagging with nearest neighbor classifiers?
stats
2017-11-19T12:15:19.033
[ { "message": "I know, that fitting an AR(q) model can easily be done by OLS.Now I wonder, how to do it for MA(q) and ARIMA(p,q), but cant find enything useful, except, that one uses Maximum Likelihood and needs many iterations.But how exactly is it done?My guess would be (for MA(q)), to initialize a time series...
Fitting MA(q) and ARIMA(q) model
stats
2017-11-19T14:15:15.370
[ { "message": "I am trying to understand how I can get the feature importance of a categorical variable that has been broken down into dummy variables. I am using scikit-learn which doesn't handle categorical variables for you the way R or h2o do.If I break a categorical variable down into dummy variables, I get...
Feature importance with dummy variables
stats
2017-11-19T18:45:00.150
[ { "message": "I have trying to improve a multiple regression model (reducing RMSE further), and have found heteroscedasticity evidence for 2 variables. I have found 2 options for reducing heteroscedasticity in linear regression: first is to get square root Y (response variable), and second is to use box-cox tra...
How to apply heteroscedasticity to multiple linear regression in R?
stats
2017-11-20T00:14:04.403
[ { "message": "I have a dependent variable ($Y$) whose distribution is as shown below. In particular, the variable exhibits positive skewness, has a few negative values and many positive values (generally less than one), and peaks near zero. The distribution after log transformation ($\\ln(1+Y)$) is very similar...
Regression with a skewed dependent variable
stats
2017-11-20T13:02:03.630
[ { "message": "Background information:The investigation is under event study framework. The topic is on how the conversion to academies affects students' KS4 performance. The dataset is at school-level. Conversion before 2009 would be in the treatment group while schools converted after 2009 would be in the cont...
In difference-in-difference setting, why do I have coefficient for (treatment==0)*(post==1) when running regression
stats
2017-11-20T14:36:46.657
[ { "message": "I have a (integer) random variable that looks like this : <a href=\"https://i.stack.imgur.com/hooLw.png\" rel=\"nofollow noreferrer\">So as you can see, has a regular behaviour for most of the time, but at some point a peak appears, and after a while this effect disappear and the variable goes dow...
How to model a random variable with a peak, and quantify the effect of external event - Bayesian Analysis
stats
2017-11-20T16:46:09.847
[ { "message": "I have a data set (with $n$ points) and there are two models which I think will fit the data well. The first model is a simple power law and the second model is a power law plus a linear term and an intercept;\\begin{eqnarray}y&amp;=&amp;ax^b\\\\y&amp;=&amp;ax^b+cx+d.\\end{eqnarray}I would like to...
Using the BIC to select a model
stats
2017-11-20T19:04:48.227
[ { "message": "I am not a professional statistician and not a native English speaker, but I use simple statistics as a journalist. I am looking for a method to find a relationship between an ordinal variable with multiple choices and a binary one. I thought about Spearman’s ρ first, but I don’t know how to combi...
Relationship between an ordinal variable with multiple choices and a binary one?
stats
2017-11-21T00:36:21.907
[ { "message": "Boltzmann machines are stochastic recurrent neural networks with a specific architecture, and they are interesting in several contexts.They are stochastic in the sense that the sampling procedure involves repeatedly computing the activation functions for the next layer (hidden from visible or visi...
Why do we want (Restricted) Boltzmann Machines to be stochastic?
stats
2017-11-21T16:03:26.910
[ { "message": "I am running simulations from a paper on graphical clustering based on latent positions. Essentially, the first step is to do Multidimensional Scaling on the Adjacency matrix, after which the authors select the 'best dimension' by doing an elbow fit. When they truncate the MD Scaled data to only u...
Why normalize data after doing Multidimensional scaling?
stats
2017-11-21T20:07:21.807
[ { "message": "I am working with the following monthly time series to build forecasting models:<a href=\"https://i.stack.imgur.com/SrZIw.png\" rel=\"nofollow noreferrer\">From this plot, it's quite tricky to identify if there is some kind of seasonality or not. When I use the <code>ets</code> function, it comes ...
Seasonal or non-seasonal? ETS and auto-arima disagree?
stats
2017-11-21T20:31:58.837
[ { "message": "In the book «Introduction to Time Series and Forecasting», by Brockwell and Davis, the authors state in section 1.5.2.1 (3rd edition) something which I summarise below.<blockquote> Sample: $\\{x_1,..., x_n\\}$. We first estimate the trend by applying a Moving Average Filter (MAF) chosen speci...
Estimation and Elimination of both Trend and Seasonality with a Moving Average Filter
stats
2017-11-21T22:05:49.693
[ { "message": "I am trying to determine wether the time series data I have is (covariance) stationary or not. This is the hourly data:<a href=\"https://i.stack.imgur.com/mG91s.png\" rel=\"nofollow noreferrer\">I proceeded to look at the acf as well as pacf plots in order to determine what kind of stochastic proc...
Counterintuitive Augmented Dickey Fuller test results
stats
2017-11-22T11:27:23.367
[ { "message": "Consider I have a training set where each data sample is a tree and each node has(including leaf node) its own feature vector. For example, single data sample will look this<a href=\"https://i.stack.imgur.com/NUqpT.png\" rel=\"nofollow noreferrer\">Now I have to classify <code>leaf</code> nodes to...
Which is the Recommended variants of neural network for tree like data structures?
stats
2017-11-22T14:09:56.840
[ { "message": "I'm confused by the formula for the commission-error and the omission-error as it was stated a bit differently in a paper I've read, compared to the one I'm giving below (maybe the authors changed that because of the context of a change detection, not a casual classification).Are these the correct...
Formula for the omission and the commission errors
stats
2017-11-22T19:44:00.353
[ { "message": "I am somewhat a beginner to time series, so please bear with me. I was taught in class that when you difference a series too much times, the variance will increase, but I am also taught that I should difference the series at lag 1 until the mean of the series on the plot is a horizontal line. Befo...
Time Series Stationary but Variance Increases
stats
2017-11-23T02:23:30.983
[ { "message": "I am currently investigating the impact of uncertainty on investment dynamics. I have an unbalanced panel data set (approximately 100,000 observations). To study the relation between investment and uncertainty I use the following equation: where the dependent variable indicates the growth rate (c...
Does it make sense to have the dependent variable in growth rates or rather in levels?
stats
2017-11-23T14:47:30.877
[ { "message": "Consider a sample of size $n=8$ from the $\\operatorname{Uniform}(\\theta,\\theta+4)$ distribution where $\\theta&gt;0$. Consider two estimators of $\\theta$:$$T_1=\\bar{X}$$ $$T_2=5\\bar{X}$$ (where $\\bar{X}$ denotes the sample mean). By comparing the corresponding MSEs, establish wh...
Likelihood Function. comparing estimator MSE
stats
2017-11-23T23:16:17.327
[ { "message": "This is a question of terminology. Sometimes I see people refer to deep neural networks as \"multi-layered perceptrons\", why is this? A perceptron, I was taught, is a single layer classifier (or regressor) with a binary threshold output using a specific way of training the weights (not back-prop)...
Multi-layer perceptron vs deep neural network
stats
2017-11-24T06:12:13.587
[ { "message": "Let's say our data set contains 1 million examples, i.e., $x_1, \\ldots, x_{10^6}$, and we wish to use gradient descent to perform a logistic or linear regression on these data set.What is it with the gradient descent method that makes it inefficient?Recall that the gradient descent step at time $...
Why is gradient descent inefficient for large data set?
stats
2017-11-25T04:54:38.620
[ { "message": "I'm studying methods for time series analysis, using gretl. I have <a href=\"https://files.fm/f/eh6644kk\" rel=\"nofollow noreferrer\">this time series. <a href=\"https://i.stack.imgur.com/x2f3q.png\" rel=\"nofollow noreferrer\">I used TRAMO and X12-ARIMA to detect probable outlier, but I found no...
Outlier in differentiated series
stats
2017-11-25T11:20:39.013
[ { "message": "<a href=\"https://i.stack.imgur.com/0qKEz.png\" rel=\"nofollow noreferrer\">Where has the author got the blue 3 from, in line 2 of the code shown?", "role": "user" }, { "message": "The variance of a standard logistic is $\\frac{\\pi ^ 2}{3}$ so to convert from that scale onto a standar...
Converting an odds ratio to a standardised mean difference, so that it can be used in a meta-analysis
stats
2017-11-26T00:33:20.797
[ { "message": "Whenever we have a multiclass prediction the classifier generates a vector output. Per the definition of a <a href=\"https://en.wikipedia.org/wiki/Jacobian_matrix_and_determinant\" rel=\"nofollow noreferrer\">Jacobian we are actually taking Jacobian steps towards a local minimum - so should it tec...
Shouldn't it be Jacobian Descent?
stats
2017-11-27T16:42:44.967
[ { "message": "In the preface to Coxeter's well-known Introduction to Geometry, he writes<blockquote> \"Geometry is useful not only in algebra, analysis, and cosmology, but also in kinematics and crystallography (where it is associated with the theory of groups), in statistics (where finite geometries help in...
geometric methods in the design of experiments
stats
2017-11-28T02:25:26.547
[ { "message": "I am doing an experiments where changing a parameter I am obtaining different number of FalsePositive, FalseNegative... and so on.I am using this parameter tuning as threshold tuning to obtain FPR and TPR to build a ROC curve.However, the problem is so easy tha it gets most of the time the point n...
AUC with incomplete ROC curve
stats
2017-11-28T13:37:29.143
[ { "message": "Following scenario:I trained an object detector (Viola Jones) on images of 8 subjects and evaluated on three other subjects (the test set) and achieved recall and precision values of roughly 82% and 80% respectively.I trained Viola Jones on images of 14 subjects (including the above mentioned 8) a...
Test error increase with larger training set size
stats
2017-11-28T15:15:17.193
[ { "message": "I have a question regarding forecasting with my ARIMA model. Let's say we have found ARIMA(1,1,1) as the best model based on AIC or BIC.Now, if I want to estimate the value of (t+1) I can substitute in the equation the values of y(0) and e(0). Ok, so I would like to predice now for the horizon t=2...
ARIMA - Forecasting - Future Errors?
stats
2017-11-28T19:43:40.600
[ { "message": "I understand that a stochastic process or function is considered a Gaussian process if sampling from it at any point some set of times yields a set of observations that match a Gaussian random variable, and an other way to view this is that it can be described by a mean function with some kind of ...
Is a function describable by a Gaussian process smooth?
stats
2017-11-29T15:04:21.653
[ { "message": "I'm working on a <a href=\"https://github.com/Sergio0694/NeuralNetwork.NET\" rel=\"nofollow noreferrer\">CNN library for a university project and I'm having some trouble implementing the backpropagation through the max pooling layer.<blockquote> Please note that the whole thing was built from scr...
SGD learning in CNN gets stuck when using a max pooling layer (x-post from DataScience)
stats
2017-11-29T20:10:41.487
[ { "message": "I performed assays looking at the toxicity of several insecticides against a insect. To do this, plant leaves were sprayed with insecticides, placed in small cages, and individual insects were exposed to the plant leaves. I assessed the mortality of the individual insects at two time points: one a...
Repeated measures analysis with only two measurement intervals
stats
2017-11-30T18:16:49.030
[ { "message": "I am a newbie to Data science.I have learned about clustering algorithms(especially K-means algorithm)and I would like to implement this algorithm(using Euclidian distance metric) to segment image on basis of <code>RGB</code> values of the image so that I could find clusters of most similar colour...
Where can I find Image(RGB) data to implement K means agorithm?
stats
2017-12-01T04:45:10.673
[ { "message": "In reinforcement learning, is a policy always deterministic, or is it a probability distribution over actions (from which we sample)? If the policy is deterministic, why is not the value function, which is defined at a given state for a given policy $\\pi$ as follows$$V^{\\pi}(s) = E\\left[\\sum_{...
Is a policy always deterministic in reinforcement learning?
stats
2017-12-01T19:47:09.357
[ { "message": "Apropos of a follow-up question to <a href=\"https://stats.stackexchange.com/a/260105/67822\">this post, I tried to prove to myself that I understood the notation in the <a href=\"https://static1.squarespace.com/static/58851af9ebbd1a30e98fb283/t/58902fbae4fcb5398aeb7505/1485844411772/SVM+Explained...
Manually finding the bias term in classification SVM in R
stats
2017-12-01T20:48:10.657
[ { "message": "I have a problem of text classification with only one text description column as predictor. The classes runs into 1500+ categories. Can someone suggest which algorithm will work best for this text classification problem with so many classes.", "role": "user" }, { "message": "Classic, ...
Text Classification with Huge Classes
stats
2017-12-02T08:34:21.347
[ { "message": "I have a binary dependent variable whose probability depends on a continuous independent variable, i.e., age. I have fit these into a logistic regression model and have the coefficients for the same. The problem is that I have 3 such curves (for 3 different groups - categorical) and I need to show...
How to compare logistic regression curves?
stats
2017-12-02T13:52:50.497
[ { "message": "We know that mean deviation and standard deviation are two different things but why are both of them equal to Range/2?Range ($R$) = Highest value - lowest value Mean deviation ($\\text{MD}$) = average absolute distance from the meanStandard deviation ($\\text{SD}$,$s_n$) $=\\sqrt{\\frac{\\sum_{i=1...
Why does Mean deviation = Standard deviation = Range/2?
stats
2017-12-02T16:17:52.793
[ { "message": "The code below generates a set of test data consisting of a series of \"signal\" probabilities with binomial noise around it. The code then uses 5000 sets of random numbers as \"explanatory\" series and calculates the logistic regression p-value for each.I find that the random explanatory series ...
Why am I not getting a uniform p-value distribution from logistic regression with random predictors?
stats
2017-12-03T22:20:02.360
[ { "message": "I have data on the mean assembly costs for the first <code>n=36</code> days of production. It is assumed that the following data follows a Normal distribution:<pre><code>AC &lt;- c(345.35, 346.25, 351.65, 341.75, 347.00, 288.95, 342.50, 330.35, 326.85, 341.25, 329.55, 327.85, 329.00, 363.50...
Sample mean Margin of Error and C.I
stats
2017-12-04T03:01:32.943
[ { "message": "In Machine Learning, for linear regression we plot a graph for coefficient and cost function to look at the global minimum. How to plot the same graph in case of multivariate linear regression with multiple coefficient and cost? Is it possible to visualise for multiple features?", "role": "use...
Machine Learning - gradient descent
stats
2017-12-04T10:37:51.597
[ { "message": "Let's say I have an MA(4) model, and I find that theta 4's 95% confidence interval contains 0. Thus, I set theta 4 to 0, and now my AICc decreased. Can I call my new model an MA(3)?", "role": "user" }, { "message": "Iterate to a minimally sufficient model incorporating as necessary ARM...
Can a time series model be truncated?
stats
2017-12-05T05:36:29.227
[ { "message": "Is it necessary to find the 'maximum likelihood estimates' of prior dirichlet parameters after finding their initial values through the 'method of moments ' to find posterior probabilities through bayesian analysis (using dirichlet -multinomial conjugate pairs)? If yes, I need to know an easy wa...
Maximum likelihood estimation of a Dirichlet distribution multivariate parameters
stats
2017-12-05T08:06:30.617
[ { "message": "According to these equations in wikimedia:<a href=\"https://i.stack.imgur.com/4Ridn.png\" rel=\"nofollow noreferrer\">each gate has two weight matrices:W,U respectively,but according this:<a href=\"https://i.stack.imgur.com/JIXMM.png\" rel=\"nofollow noreferrer\">from:<a href=\"http://colah.github...
Does each gate have one, or two matrices in LSTM?
stats
2017-12-05T08:45:19.867
[ { "message": "How to test if these two samples are from the same distribution? (These are tweets located near some tourist attractions.<a href=\"https://i.stack.imgur.com/r7l3a.png\" rel=\"nofollow noreferrer\"><a href=\"https://i.stack.imgur.com/djsdx.png\" rel=\"nofollow noreferrer\">If yes, is there a simple...
How to test if these two samples are from the same distribution?
stats
2017-12-06T04:42:30.267
[ { "message": "Premise: I know next to nothing about survival analysis, I just started. I have a vector of failure times for some machines. Most of the machines (3362 vs 2694) are still running today, so I know they haven't failed, and the failure time is at some unknown time in the future. If I'm not mistaken, ...
Fit a Weibull distribution to...right-censored data?
stats
2017-12-06T17:08:13.090
[ { "message": "I'm a biologist, so for most of you my question is gonna be the dumbest one. I made an experiment with triplicates and performed anova and tukey's test, but the later was not significant. What I would like to know is if I perform a T-test between to groups of samples (different treatments) I will ...
T-test of two groups of a 15 groups experiment
stats
2017-12-06T17:44:15.713
[ { "message": "The data are from book ratings done by users. Users were split into three experimental groups <code>(A/B - test)</code>. Goal is to understand if users show any difference in rating books between these groups. Carrying out t-test sounds like the first approach to understand the differences. Since ...
T-Test using means vs without means - correct approach
stats
2017-12-06T17:45:09.277
[ { "message": "I have been reading up on the diff-in-diff estimator (following MHE). However, my lecturer said something that confused me:Say I have panel data of hospitals in low-income neighbourhoods and a variable for patient's health outcome. Now a new policy is introduced such that some hospitals are privat...
Difference-in-Differences
stats
2017-12-06T19:09:47.407
[ { "message": "I am interested in the current state of the art for selecting initial seeds (cluster centers) for K-means. Googling leads to two popular choices:random selection of initial seeds, and,using the KMeans++ selection technique: <a href=\"http://www.cs.duke.edu/courses/cps296.2/spring07/papers/kMeansPl...
Methods of initializing K-means clustering
stats
2017-12-06T21:38:46.943
[ { "message": "Here's the scenario: I have many different time series I would like to forecastI've been through the process of making a seasonal ARIMA model for many of the time series just as part of explorationEach of the time series also have a set of static (read: do not change over time, but vary by series)...
Time series analysis on series with static variables
stats
2017-12-06T22:24:29.193
[ { "message": "One of the primary differences I've seen stated between Q-learning, as a model-free algorithm, and Value Iteration, as a model-based algorithm is that Value-Iteration requires a \"model of the environment\" in that it incorporates knowledge of how to transition from one state to another (which I'v...
Q-learning vs. Value Iteration
stats
2017-12-07T11:06:06.677
[ { "message": "Just like we have a lower bound for the variance of unbiased estimators (Cramér-Rao), I was wondering if we have an upper bound for their convergence rate. Why do I keep seeing root-n convergence? Is it impossible to go faster than that? Why?", "role": "user" }, { "message": "It certai...
Upper bound of convergence rate for unbiased estimators?
stats
2017-12-07T15:59:17.767
[ { "message": "The r output I would get is just the summary of a fitted model. For example:<pre><code>fitmodel = lm(formula = response ~ categorical + predictor)summary(fitmodel)</code></pre>I'm also given a $t_{0.25}$ value. The categorical variable has 2 possible values (\"yes\" and \"no\"). So, from the outpu...
95% confidence interval for the difference between two values from a categorical variable given some r output
stats
2017-12-07T18:36:50.397
[ { "message": "I am running a model in which I want to explain my dependent variable with the racial/ethnic diversity in a person's residential area. Diversity is measured with 4 continuous variables. Each one of these variables gives me the percentage of the total population of a racial/ethnic group in the resi...
Help with interpretation of output
stats
2017-12-07T18:50:53.473
[ { "message": "In Keras and tensorflow there is a loss function called binary crossentropy. When i use that the output neurons will only produce 0 and 1. I see that in the code of keras, binary cross entropy is linked to <code>sigmoid_cross_entropy_with_logits</code> in tensorflow, and from there I assume it goe...
How does binary-crossentropy decide the output
stats
2017-12-08T16:11:46.507
[ { "message": "I am attempting to use the 'scam' R package to carry out posterior simulation.I am relying on<a href=\"https://stats.stackexchange.com/questions/190348/can-i-use-bootstrapping-to-estimate-the-uncertainty-in-a-maximum-value-of-a-gam/191489#191489\">Can I use bootstrapping to estimate the uncertaint...
Posterior Simulation of a shape constrained additive model (SCAM)
stats
2017-12-08T18:13:18.773
[ { "message": "Some background: I was applying for an entry level business analyst position, and I was completely lost with some of these questions. These questions were from the practice test. I'm not sure how I did on the actual test, but if I were to encounter this in future, I would like to be prepared. Any ...
What is the underlying math needed to answer the following questions:
stats
2017-12-08T22:17:18.730
[ { "message": "If I have a normal regression model<pre><code>y_t = βx_t + ε_t</code></pre>and want to add a y_(t-1), would this be proper?<pre><code>y_t = ρΔy_(t-1) + βx_t + ε_t</code></pre>or would I need to also add the lagged x, like this?<pre><code>y_t = ρΔy_(t-1) + βx_t + θΔx_(t-1) + ε_t</code></pre>", ...
If I add a lagged dependent variable, do I need to add the lagged independent variables too?
stats
2017-12-09T11:41:42.627
[ { "message": "I have data for 200 subjects and am creating a neural network to classify (binary state) for each subject. I am doing so in Matlab and have to divide up my data into training, validation, and testing sets. Originally, I created a 6-fold cross-validation method wherein I tested on a different set o...
What would be the best way of setting train/validation/test indices when dealing with classification of independent subjects?
stats
2017-12-09T19:36:09.767
[ { "message": "I'm trying to solve a homework problem and I'm not getting the answer I expect.The problem is from Pattern Classification by Duda,Hart,Stork (problem 3.47)<blockquote> Consider $\\mathcal{D} = \\left\\{\\begin{pmatrix}1\\\\1\\end{pmatrix},\\begin{pmatrix}3\\\\3\\end{pmatrix},\\begin{pmatrix}2\\\...
Expectation maximization when support of likelihood is parameterized
stats
2017-12-10T20:50:02.713
[ { "message": "What is the use of Hidden layers in Neural Networks? How do we know the role of each hidden layer?", "role": "user" }, { "message": "Neural networks are universal function approximators. To approximate any function, you need to be able to model it in a non-linear way. If you consider N...
Hidden layers in Neural Networks
stats
2017-12-11T05:33:56.437
[ { "message": "I have expected frequencies in each category as shown below:<a href=\"https://i.stack.imgur.com/I2rld.png\" rel=\"nofollow noreferrer\"><a href=\"https://i.stack.imgur.com/esHnW.png\" rel=\"nofollow noreferrer\">So my initial data: category - and number of observation of it.There are too many obse...
Alternative to Chi-squared test to check if categorical distribution in two sets are the same
stats
2017-12-11T07:25:58.337
[ { "message": "I've been exploring a number of tools for forecasting, and have found Generalized Additive Models (GAMs) to have the most potential for this purpose. GAMs are great! They allow for complex models to be specified very succinctly. However, that same succinctness is causing me some confusion, specifi...
Generalized additive models (GAMs), interactions, and covariates
stats
2017-12-11T19:31:11.050
[ { "message": "Lasso regularization has the nice property of creating coefficient sparsity. Generalizing to Lp regularization, is it possible to regularize a logistic regression with p &lt; 1? I would like to control the sparsity, possibly at the expense of performance. Is there a way to do this in Python? Sciki...
Lp regularization with p < 1?
stats
2017-12-11T23:43:34.383
[ { "message": "I'd like some help with an issue that might seem easy but I'm stuck in my analysis. I'm working with R on a dataframe containing 15 variables: 14 numerical or Integer and 1 factor. I'd like to do some clustering on my dataframe but here is the issue: Usually, when I'm working with factor variables...
Clustering with numerical variables and one non numerical
stats
2017-12-12T09:42:37.997
[ { "message": "Suppose I fit a GARCH(1,1) model with Student-$t$ innovations of the standardized residuals using BIC selection. My mean model is ARMA(0,0). What can I do when the standardized residuals are still correlated?", "role": "user" }, { "message": "Try changing the model specification. The m...
What to do if a GARCH model selected by BIC has correlated residuals?
stats
2017-12-12T11:14:20.193
[ { "message": "As the title suggest, i have a little problem grasping the main difference between markov and semi-markov processes. Anyone up for the challenge? :)", "role": "user" }, { "message": "I will discuss only Markov processes on finite or countable state spaces. My answer is based off of <a ...
Difference between a markov process and a semi- markov process
stats
2017-12-12T14:21:18.773
[ { "message": "I have the following datasets of several variables:hourly data of the year 1990hourly data of the year 2000hourly data of the year 2010Now, I was planning to select and estimate a linear regression model based on the dataset of the year 1990 and then validate/check its accuracy by applying the mo...
Cross-validation for time series regression model
stats
2017-12-12T17:35:52.787
[ { "message": "I have an Arima(1,1,1) model with <a href=\"https://www.otexts.org/fpp2/regarima.html\" rel=\"nofollow noreferrer\">predictors <code>var1+var2+var3</code>, but am struggling with how to write the equation. The problem is that on all of the sources I see a variation of the following is given.$$\\le...
Formula for an ARIMA(1,1,1) solving for y
stats
2017-12-13T17:01:25.117
[ { "message": "Suppose I want to generate $X_1, \\ldots, X_n$ Bernoulli random variables such that:$$Corr(X_i, X_j) = \\rho$$for all $i \\neq j$.I am wondering what method I might be able to use (I will be trying to do this in R). I am thinking of using Couplas, but could anyone guide me how to implement this? T...
How to generate Bernoulli random variables with common correlation $\rho$?
stats
2017-12-14T03:34:32.940
[ { "message": "I know that Random forest uses Bagging, but how does ensemble give a single prediction in <code>sklearn</code> Bagging vs Random forest?Also, I do not understand why in Bagging you not need to choose a tree estimator, while not in RF? other than this, are the other steps the same?wht are main impl...
Difference between Random forest vs Bagging in sklearn
stats
2017-12-14T04:08:21.013
[ { "message": "The common case for a Monte Carlo simulation is, if we want to run our simulation for $N$ steps, we define a delta $\\Delta,$ such that $N/\\Delta = n$ tells us the frequency with which we measure/evaluate quantities of interest during the MC run. For instance, say $N=1000,$ and we want to measure...
Logarithmic sampling in Monte Carlo instead of linear
stats
2017-12-14T13:19:28.147
[ { "message": "I am validating a credit risk model. I did a k fold validation to check the stability of the estimates. The estimates of the model are quite stable but the variables now have a high P value(above 0.1) in the 5 folds that were created. The variables had a very low P-value during development. Can i ...
P Value interpretation in K fold Validation
stats
2017-12-15T11:32:20.127
[ { "message": "I have a data set that includes seven patients.Each patient is administered one of two different treatment modalities over follow-up. Several metrics were calculated at each visit, and I now wish to compare these.Patients attended a baseline visit, then 6 weekly follow-up visits. So each patient h...
Statistical analysis of repeated measures
stats
2017-12-15T14:54:36.117
[ { "message": "The derivation of the prediction interval for the linear model is quite simple: <a href=\"https://stats.stackexchange.com/questions/9131/obtaining-a-formula-for-prediction-limits-in-a-linear-model?noredirect=1&amp;lq=1\">Obtaining a formula for prediction limits in a linear model .How to derive th...
Derivation of confidence and prediction intervals of predictions for probit and logit (and GLMs in general)
stats
2017-12-15T16:08:36.077
[ { "message": "I have a large number of times series (think of the order of 10k), one data point per day (think of the order of 100 days), so I have about 1M data points in total. (One of the things that I will try is a vector autoregressive model, but for now I wanted to start with something simpler. Simple reg...
How to deal with large number of times series?
stats
2017-12-16T16:14:33.933
[ { "message": "Would a compound poisson process result in a histogram that isn't the same as that of a regular poisson process? How would I fit such a histogram without knowing the rate?", "role": "user" }, { "message": "You wouldn't draw a histogram of a <a href=\"https://en.wikipedia.org/wiki/Poiss...
Histogram for a compound poisson process
stats
2017-12-17T22:20:36.127
[ { "message": "In Tensorflow's implementation of <a href=\"https://github.com/tensorflow/models/blob/master/research/slim/nets/resnet_utils.py\" rel=\"noreferrer\">ResNet, I find they use variance scaling initializer, I also find xavier initializer is popular. I don't have too much experience on this, which is b...
What's the difference between variance scaling initializer and xavier initializer?
stats
2017-12-18T01:07:39.383
[ { "message": "I have profit (loss) data series with some significant skewness and kurtosis. Is there a way to transform this data to a normal distribution so that I can use the gaussian procedure for the test of hypothesized mean being zero? I am very new to data transformation - tried log with constant additi...
How to transform profit loss data to normal distribution
stats
2017-12-18T11:52:08.960
[ { "message": "Given a set of data with their frequency in a data set,like: $$x_1, f_{x_1}, x_2, f_{x_2}, x_3, f_{x_3}, \\cdots, x_n, f_{x_n}$$, where $f_i$ is the frequency of value $x_i$ in a data set $\\{x_i\\}$.The definition of frequency here is: $$f_i =\\frac{n_i}{N} =\\frac{n_i}{n_1+n_2+n_3+\\cdots}$$If ...
Deciding which points to be used for density estimation
stats
2017-12-18T13:33:51.003
[ { "message": "I'm measuring genetic diversity from every individual in a sample using two different types of genetic information. These types of genetic information have different properties, and mutate independently of one another, yet will always be inherited together when an individual reproduces. Should I c...
Are two different ways of measuring an individual statistically indepent?
stats
2017-12-18T18:22:00.437
[ { "message": "I keep getting different out-of-bag error estimates from the <code>caret</code> package, depending on how the estimates are computed. I can't seem to nail down exactly where the discrepancy is coming from.Consider a simple random forest model using the built-in <code>mtcars</code> dataset:<pre><co...
Inconsistent Out-of-bag error estimates
stats
2017-12-18T19:19:07.897
[ { "message": "I would like some advice on what statistical analysis to use to test my hypothesis. I am using R. My setup is as follows (in .csv format, first line is header):<pre><code>id,time,group,outcome1,t1,control,3.41,t2,control,3.22,t1,treatment,3.42,t2,treatment,4.23,t1,control,3.33,t2,control,3.14,t1,t...
Hypothesis testing with control and treatment group - which statistical analysis to use?
stats
2017-12-19T03:41:31.647
[ { "message": "Sorry, but I'm confused about when to categorize within and between groups variables. Update: I think that I was confused by the \"within\" and \"between\" terms. What I really want to do is confirm if the scenario described below constitutes a repeated measures design or not.The scenario:<br>I co...
Question about between and within groups (repeated measures design)
stats
2017-12-19T08:25:38.260
[ { "message": "I'm interested in to know a bit more on what the scale parameter of the <code>dccfit</code> <code>fit.control</code> option is about.Here is the code for the model I am estimating: Specifications: <pre><code>xspec = ugarchspec(mean.model = list(armaOrder = c(1, 0)), variance.model = list(garchOr...
Scale parameter in fit.control option from “dccfit” rmgarch function
stats
2017-12-19T12:05:20.287
[ { "message": "I was reading <a href=\"https://www.analyticsvidhya.com/blog/2016/04/complete-tutorial-tree-based-modeling-scratch-in-python/\" rel=\"nofollow noreferrer\">this article.In it, when referring to Ensemble Learning, this was stated:<blockquote> It can be theoretically shown that the variance of the ...
How can it be shown that the variance of combined predictions is 1/n
stats
2017-12-19T14:00:14.150
[ { "message": "Imagine I have a bag of n labeled marbles. I would like to pick a single random marble out of the bag x number of times. Every time I pick a marble, I place it back in the bag. How do I calculate the probability that I will only pick p distinct marbles?In my case, I have 90 labeled marbles, 550 se...
How to calculate the probability of picking a certain number of distinct marbles out of a bag, given a certain number of selections?
stats
2017-12-20T04:27:11.617
[ { "message": "This may be a simple question, but my data (once transformed) passes normality, however does not pass homoscedasticity. Can I look at the residuals to see if they pass this? or am I over looking this?", "role": "user" }, { "message": "Since you mention residuals I assume you are talkin...
Can I use residuals for transformation?
stats
2017-12-20T05:19:40.110
[ { "message": "I use Bayesian random effects models [$y_i \\sim bernoulli\\_logit(\\beta + \\alpha_{subj})$ $\\alpha_{subj} \\sim normal(0, \\gamma)$], the $y$ outcome is binary. Part of the subjects have two observations, part of the subjects have only one observation.I experience that when I use ($y_i, subj_i...
Estimate a parameter from subset of the data, other parameters from all data
stats
2017-12-20T14:18:54.123
[ { "message": "These days I'm using a lot (and discovering) nice ways to use k-means' clustering. For example, clustering word embeddings (word2vec vectors) to find synonyms or clustering doc vectors (doc2vec) to classify topics. But for these tasks I always need to specify the number of clusteres (the 'k'). Is ...
An algorithm similar to (or based on) K-means that do not require the 'k' number of clusters
stats
2017-12-20T21:52:22.150
[ { "message": "I have a posterior distribution of Dirichlet form with new parameters (alpha1, x1), (alpha 2, x2) and (alpha 3, x3) and the posterior mode of each dependent variable as the Bayes estimator. I wish to find the Bayes credible interval/Bayes credible region of the posterior to know the uncertainty in...
The Bayes credible interval / Bayes credible region of the posterior distribution of a multinomial Dirichlet conjugate pairs
stats
2017-12-21T09:51:03.160
[ { "message": "I have rental prices of the houses, the distribution is a bit skewed (1.84 by scipy.stats.skew).Fig. 1: <a href=\"https://i.stack.imgur.com/19ZGn.png\" rel=\"nofollow noreferrer\">I run XGBRegressor on non-transformed data (1.) and on log-transformed target variable (2.). In 2. I also exponentiat...
non-linear regression: Residual Plots and RMSE on raw and log target variable
stats
2017-12-21T13:05:17.483
[ { "message": "$X$ is a multivariate Gaussian, <a href=\"https://stats.stackexchange.com/questions/29860/confidence-interval-of-multivariate-gaussian-distribution\">whose confidence region I can derive. $Y$ is a function of $X$, specifically $Y = (x_1, x_2 - b x_1^2 + 100b, x_3, \\dots, x_n)$. I can use change-o...
Apply change-of-variable technique to derive confidence region of twisted gaussian?
stats
2017-12-21T17:02:57.080