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've been learning machine learning through <a href=\"https://www.coursera.org/learn/machine-learning\" rel=\"nofollow noreferrer\">Andrew Ng's Coursera. I've completed Andrew's homework on SVM, but it felt wishy washed and I'm having hard time taking it from 0 to finish. Say you calculated the SV... | SVM: How to get predicted output from SVM with Gaussian / RBF Kernel? Andrew Ng's course svmPredict | stats | 2017-08-22T19:28:16.920 |
[
{
"message": "Is there a difference between methods for classification that are using the \"raw-signal\" as features and methods that are extracting features?For example, there are methods which are based on calculating the correlation of signal <code>a</code> and <code>b</code> if the correlation is high enoug... | How to distinguish Methods for Classification | stats | 2017-08-22T23:39:31.483 |
[
{
"message": "My question is if we have three models e.g. linear regression, polynomial regression and smoothing spline, what would be the expected values of their RSS (training and test) be if the true relationship is 1) linear and 2) cubic.Let's say the data set is 1000.Thanks in advance.",
"role": "user"... | RSS of different models given true relationship between X and Y | stats | 2017-08-23T01:49:41.073 |
[
{
"message": "I am trying to determine what the appropriate post hoc testing for a one way repeated measure between subject ANOVA. Would it be appropriate to use a Tukey test in this scenario?",
"role": "user"
},
{
"message": "Well, appropriateness of the test depends upon the comparisons to be made... | post hoc testing for a one way repeated measure between subject ANOVA | stats | 2017-08-23T02:30:33.050 |
[
{
"message": "Say I'm constructing a GAM for a response variable <code>R</code> in terms of predictors <code>A</code>, <code>B</code>, <code>C</code>, and <code>D</code>. Something like this (in quasi-R-code):<code>R ~ s(A) + s(B) + s(C) + s(D)</code>Before I construct this model, I check for colinearity by cal... | GAMs with many slightly correlated predictors | stats | 2017-08-23T11:58:40.690 |
[
{
"message": "I have with me two data matrices each of dimension n x p where n is the number of rows of observations and p = 2 is the number of variables. Each data matrix yields a covariance matrix using the standard sample covariance estimate. My aim is to determine, in a visual manner, if the two covariance ... | Using ellipses, how can I visually compare two estimated covariance matrices in the presence of sampling uncertainty? | stats | 2017-08-24T08:07:48.757 |
[
{
"message": "I plot Score (y variable) against Year (x variable) and I want to be able to show that there is an increase in the score as the year increases. The scatter plot indeed indicates this but I would like to get a p-value for this by way of an appropriate hypothesis test on this slope. I believe that a... | Creating a simulation to find a p-value for a slope, is this valid? | stats | 2017-08-25T08:57:27.167 |
[
{
"message": "I'm using ANOVA F-Value from Scikit-learn (<a href=\"http://scikit-learn.org/stable/modules/generated/sklearn.feature_selection.f_classif.html#sklearn.feature_selection.f_classif\" rel=\"nofollow noreferrer\">link) to find importance of features in a machine learning task. I have numeric feature a... | What value of ANOVA F-Value is significant | stats | 2017-08-25T15:21:07.697 |
[
{
"message": "I'm running a multiple linear regression on 2 years of daily sales data. When running against the daily data, I get a correlation of 84%, but when summarized to weekly totals, the correlation over the same period drops to 68% with the same underlying inputs/output. How/why would this be?Further, h... | Why would correlation for daily data be higher than weekly data? | stats | 2017-08-25T18:46:21.577 |
[
{
"message": "how do combination of regression model and time series for better predictive? for prediction of consumation of energy data. previously just use linear regression model for consumation energy but it is not enough for prediction",
"role": "user"
},
{
"message": "Since the question is ver... | how to cmpound the regression model with time series? | stats | 2017-08-26T20:01:48.663 |
[
{
"message": "I'm having a hard time checking an equality in <a href=\"https://arxiv.org/pdf/1511.01707.pdf\" rel=\"nofollow noreferrer\">https://arxiv.org/pdf/1511.01707.pdf. It is unnumbered, immediately before (24), on page 13. Any help would be appreciated. Here is some simplified notation and a simplified ... | weights versus shifted log-weights | stats | 2017-08-26T20:38:26.290 |
[
{
"message": "There are a certain number of houses spread randomly across a city. We have addresses and GPS coordinates for each house. How can we select a geographically representative, fixed-size sample out of the houses in the selection? To illustrate with an example, say we have about 100 houses on a map li... | Given a set of addresses, pick a geographically even subset for sampling | stats | 2017-08-27T01:19:09.553 |
[
{
"message": "I am analyzing some data in R using the lmer function provided in the lme4 package. The experiment involves assigning a number of students to different trials of exam questions, and everone is assigned to the same three blocks of questions. The response of interests are Correct and RT, and I am co... | Nested random effects model in lme4 | stats | 2017-08-27T17:36:20.370 |
[
{
"message": "I'm reading Introduction to Statistical Learning. It mentions on page 166 for KNN modeling that a success rate of 11.7% is more than double that of random guessing. My question is, first what is the success rate of random guessing and why is the success rate for KNN so low and yet better than othe... | Why is the success rate low and yet still better than random guessing? | stats | 2017-08-27T23:46:57.200 |
[
{
"message": "I try to train a linear SVM using package e1071, with cost=10 on the following data: <pre><code>x <- matrix(c(-0.97, -0.69,-1.14,-0.93,0.26,1.14,0.76,1.32,- 0.79,1.04,-.80,-.97,-1.09,-1.09,0.63,1.09,0.92,1.49,-0.52,0.34),10,2)colnames(x) <- c(\"X1\",\"X2\")y <- c(-1,-1,-1,-1,1,1,1,1,1,-1)... | Does SVM perform poorly with too few observations | stats | 2017-08-28T09:05:42.757 |
[
{
"message": "Using machine learning techniques, is it possible to analyse Employee Check in-Check Out time over a period of time and cluster them. <br><br>1. An employee can check-in/checkout any number of times in a day.<br>2. They have a defined roster schedule. <br>3. Employees may go to different buildings... | Cluster Employees based on multiple Check in-Check out time in a day | stats | 2017-08-28T11:50:13.980 |
[
{
"message": "I am looking at learning curves (<a href=\"https://github.com/dennybritz/cnn-text-classification-tf\" rel=\"nofollow noreferrer\">CNN for text classification, which is based on <a href=\"http://arxiv.org/abs/1408.5882\" rel=\"nofollow noreferrer\">this paper) and trying to play with regularization... | Overfitting on the loss graph, but not the accuracy graph | stats | 2017-08-28T17:42:50.860 |
[
{
"message": "I was reading the Rubin: Causal inference and Angrist, J.D. and Pischke: most harmless econometrics. Both of them are great textbooks. During my reading, I have the following question: what is the correct interpretation of the coefficient of a covariate variable (rather than the treatment variable... | What is the interpretation of the coefficient of a covariate control variable in a multiple linear regression | stats | 2017-08-29T04:24:48.703 |
[
{
"message": "I'm doing a predictive modeling for predicting anomalies in the sensors data. For this I'm using the twitter AnomalyDetection package in R. We are getting ton of data from sensors for every day. For every 5 sec we get a one data point from sensor. we are averaging this data over 2 min. We have a o... | How to fit Anomaly Detection model to imbalanced time series data(Zero Inflected time series data)? | stats | 2017-08-29T05:38:13.330 |
[
{
"message": "I'm experimenting with Keras (Tensorflow backend) and Variational Autoencoder.My loss function is the classical one, i.e, the sum of reconstruction error and KL divergence. When I provide my model with validation data, Tensorboard shows a 'validation_loss', computed on validation data. I'm wonderi... | Variational Autoencoder and validation loss | stats | 2017-08-29T08:41:50.547 |
[
{
"message": "I am wanting to determine whether components of Friendship Quality (measured by a scale) are related to a reduction in fear (multiple DVs). By components I mean that the Friendship scale I'm using is made up of 6 subscales. I have already conducted a 2 x 2 multivariate analysis of covariance as I ... | Several linear regressions? | stats | 2017-08-29T09:55:56.693 |
[
{
"message": "Background: When introducing exponential families in class today, my professor said that the cumulant generating function in the definition is essentially a normalizing constant, or a renormalization term after applying an exponential tilt.This sounded to me a lot like the partition function from ... | Are the Boltzmann distributions an exponential family? | stats | 2017-08-29T22:18:13.293 |
[
{
"message": "In Goodfellow et al.'s Deep Learning, the authors write on page 222:<blockquote> \"... the model family being trained either (1) excluded the true data-generating process - corresponding to underfitting and inducing bias, or (2) matched the true data-generating process, or (3) included the gen... | Relationship between bias, variance, and regularization | stats | 2017-08-29T23:16:20.010 |
[
{
"message": "I used - library(e1071) which was able to predict all(10) of my classes in a single run. Now, why do people go for one Vs one and one Vs many approach? What is the benefit of those approaches?Is it only library(e1071) that can do multi-class classification ?Would the output or accuracy changes if ... | When SVM can do Multi-class Classification itself, why do people still use one Vs one or One Vs Many Classification? | stats | 2017-08-30T00:20:44.270 |
[
{
"message": "I have read in literature several times a distinction being made between Bernoulli assignments and completely randomized assignments in assigning treatment (1) vs control (0) to units in a study. I was wondering if anyone could point me in a direction to distinguish between the two. What is the di... | For treatment assignment, what is the difference between Bernoulli assignment vs. completely randomized assignment? | stats | 2017-08-30T02:13:48.007 |
[
{
"message": "I'm going thru the Cousera's DeepAI course (Week3 video 1 \"Neural Networks Overview\") and Andrew Ng is explaining how each layer in a neural network is just another logistic regression, but he doesn't explain how it makes thing more accurate. So in a 2 layer network, how does calculating logist... | If each neuron in a neural network is basically a logistic regression function, why multi layer is better? | stats | 2017-08-30T14:10:26.390 |
[
{
"message": "I was recently reading Efron's Simultaneous Inference paper (2008), in which he points out that FDR analysis is robust to splitting the tests into multiple mutually exclusive families of test, performing the analysis on these subsets, and then combining the results (see Sec 5. Are separate analyse... | Why bother with Benjamini-Hochberg correction? | stats | 2017-08-30T15:18:10.607 |
[
{
"message": "We are given two normal populations A & B with means $\\mu_1$, $\\mu_2$ and standard deviations of $\\sigma_1$, $\\sigma_2$ respectively, as well as a subject X. Our purpose is to determine which population X is more likely to belong assuming that each population is equally likely to occur. ... | How to Quantify Likelihood | stats | 2017-08-30T15:21:04.987 |
[
{
"message": "I was looking through the various cost function(deviances) in GBM's implementation of R and got confused by the cost function. I had always thought that the cost function for bernoulli would be log likelihood or something that approximates log likelihood. However, it seems different in the R sourc... | Understand the cost function in the GBM implementation of R | stats | 2017-08-31T03:45:22.067 |
[
{
"message": "I have a dataset on which I'm trying to estimate Weibull distribution CDF as population's survival function.My question is about gathering data points on which CDF will be estimated. I'm going to establish death rates of my subjects after 1, 2, ..., 28 days. Right now, when establishing the death ... | End of observation window for estimating Weibull distribution | stats | 2017-08-31T08:14:17.760 |
[
{
"message": "As I understand the inclusion of the GARCH term, $\\sigma^2$, in a GARCH model allows for an infinite number of time series terms, $\\epsilon^2$, to influence the conditional variance. Is this the case? How does this characteristic enable the GARCH model to be more parsimonious than the ARCH model... | GARCH vs ARCH models - which is more parsimonious? | stats | 2017-08-31T17:21:36.837 |
[
{
"message": "The proof for the MSE version appears not to depend on $T$ being a sufficient statistic. I provide a minimal version here:Let $\\hat\\theta,T$ be observable random variables, and let $\\theta \\in \\mathbb R$ be fixed.Define $\\theta^+ \\colon T \\to \\mathbb R$ with $\\theta^+(t) = E[\\hat\\theta... | Why does the MSE version of Rao-Blackwell theorem require $T$ to be a sufficient statistic? | stats | 2017-09-01T10:14:55.860 |
[
{
"message": "Alright, I posted this same question over at MSE, <a href=\"https://math.stackexchange.com/questions/2395394/solving-ptrue-of-finding-counterpart-pairs-in-2-sets-with-constraints-involvin\">https://math.stackexchange.com/questions/2395394/solving-ptrue-of-finding-counterpart-pairs-in-2-sets-with-c... | Solving P(TRUE) of finding counterpart pairs in 2 sets with constraints involving the Universal Genetic Code | stats | 2017-09-01T17:50:28.373 |
[
{
"message": "The field of model selection is well known - e.g. AIC, BIC, MDL and such.However, I cannot find what people do after the modeling part is done, i.e. once I've chosen a specific model for my set, I need to estimate the model's parameters, don't I?In most model selection criteria, Maximum Likelihood... | Parameter estimation after model selection | stats | 2017-09-03T07:51:26.807 |
[
{
"message": "I have a probability question dealing with conditionality. This one is a bus example:Li = # people on the bus leaving the ith stopBi = # people that board the bus at the ith stopBus arrives at stop 1 empty.P(Bi=0) = 0.5, P(Bi=1) = 0.4, P(Bi=2) = 0.1Prob of a person leaving bus = 0.2The question i... | Conditional Probability question (bus example) | stats | 2017-09-03T20:04:01.540 |
[
{
"message": "I'm a newbie to machine learning so forgive me if the answer to this question is obvious.I have been working on a binary prediction problem using logistic regression. Using a selection of categorical and continuous I have been able to predict accuracy on a testing set with an AUC of about $0.7$. I... | Imputing missing values on a testing set | stats | 2017-09-04T14:59:14.227 |
[
{
"message": "I perform a experiment on which the measured results are codes into two variables:$y_1 \\in {-1,0,1}$ and $y_2 \\in {-1,0,1}$.While $-1$ and $1$ are opposite result, $0$ is coding a bad (uncertain) measurement, and is very unlikely, so in fact both of $y_1, y_2$ are almost binary.How do I check th... | Correlation measure between binary variables | stats | 2017-09-04T16:05:47.680 |
[
{
"message": "<a href=\"https://i.stack.imgur.com/173mp.jpg\" rel=\"nofollow noreferrer\">I measured the speeds snails fell off in a high-speed aquarium, where current was created by me opening a valve to different degrees, leading to the speeds that snails could fall-off at being set and not continuous. The sn... | Calculating if there's a significant difference between the difference of two sets of groups | stats | 2017-09-04T19:47:06.140 |
[
{
"message": "If there is no focus on NHST and P-values, then are power analyses even necessary? What if someone were to focus solely on effect sizes and confidence intervals (I know that p-values and CIs share similar statistical theories) so if someone could explain this, I'd appreciate it.",
"role": "use... | Is statistical power relevant if there is no focus on significance/hypothesis testing? | stats | 2017-09-04T22:33:38.183 |
[
{
"message": "A given, unknown function takes as arguments a random number, a finite numerical sequence and a numerical value, and outputs a numerical result. Known is a set of triples of sequence, value and result. What test tests the null hypothesis that the function ignores the sequence?",
"role": "user"... | What test has this null hypothesis? | stats | 2017-09-05T19:20:40.270 |
[
{
"message": "Let's say we have $k$ vectors each containing $n$ non-negative integers (counts), and we know that each of those vectors are distributed by a Poisson, each with a very different mean. I am wondering whether there is a way to normalize each of those $k$ vectors such that each of resulting $k$ vecto... | Normalizing (or standardizing) Poisson data | stats | 2017-09-05T23:33:56.820 |
[
{
"message": "I'm just starting out learning about ANOVA, I'm having trouble understanding how to check for homogeneous variance assumptions.<br>One source I have seems to be looking at box-plots, and another looks at residual vs fitted plot. But I'm not sure what they are looking at exactly.<br>For example, he... | ANOVA - Homogeneous variance, what to look for in a boxplot | stats | 2017-09-06T01:17:32.820 |
[
{
"message": "I have a dataset within which I have a particular response variable that I'm interested in and numerous predictor variables. All variables are nominal and have as many as 15 possible values. When I cross tabulate any given predictor variable with the response variable, I get many cells with 0 coun... | Is there an alternative to Cramer's V for computing effect size when chi-squared is inappropriate | stats | 2017-09-06T02:45:52.640 |
[
{
"message": "In forecasting, to solving for the nonlinear trend exponential smoothing can you just choose any value of ϕ or is there a way to solve for it?",
"role": "user"
},
{
"message": "You can see how several different $\\phi$ values compare at predicting. For example, you can compare one-step... | How to solve or choose the smoothing parameter phi in solving for the Nonlinear trend exponential smoothing? | stats | 2017-09-06T06:46:46.460 |
[
{
"message": "I have some model $\\vec{d}=A\\vec{s}+\\vec{n}$ $\\vec{s}=(s_1,s_2)^T$ is a vector of two signals with a gaussian pdf prior with a zero mean and a diagonal covariance matrixA is a matrix the mixes the signals$\\vec{n}$ is a noise 3 component vector with a gaussian pdf with zero mean and unit matri... | Bias from a simulation | stats | 2017-09-06T17:58:46.140 |
[
{
"message": "Consider the following very simple example:<pre><code>set.seed( 1 )SimData <- data.frame( X = runif( 1000, 0, 1 ) )SimData$Y <- rnbinom( nrow( SimData ), mu = 100*sin( SimData$X*2*pi )+100, size = 10 )plot( gam( Y ~ s( X ), data = SimData, family = nb( link = log ) ) )</code></pre>Here is th... | Strange effective degrees of freedom (smoothness) selected for smooth component in GAM model with mgcv | stats | 2017-09-07T10:32:20.847 |
[
{
"message": "I've got some crowdsourced data rating avatar images for various emotion & personality traits, and based on previous work by a fellow postdoc I'm trying to analyze inter-rater reliability on a per-image basis: I want to show that some images are less agreed-upon than others, so I need to compu... | Inter-rater Reliability (Krippendorf's Alpha) for raters of a single observed unit? | stats | 2017-09-07T15:49:06.800 |
[
{
"message": "Suppose I have 100 people each of whom are given 100 randomly sampled emails to decide whether an email is a spam or not (each person gets a different set of 100 emails, so each email will be looked at by only one person). Each person then will have a proportion -- the proportion of emails labeled... | Check outliers in a set of proportions | stats | 2017-09-07T19:16:12.553 |
[
{
"message": "I am trying to identify scales in a query material consisting of 60000 respondents and 47 ordinal variables. For this purpose my idea is to perform a maximum likelihood exploratory factor analysis to identify underlying factors. These factors are then seen as constructs/indices for which I want to... | Correct procedure to calculate McDonald's Omega in R using the psych package | stats | 2017-09-08T11:50:15.393 |
[
{
"message": "Feigl & Zelen (Biometrics, 1965) gave data on the survival times in weeks of 33 patients suffering from a form of cancer. They also provided the values of two explanatory variables, white blood cell (wbc) counts in thousands, and a factor AG (ag) coded as 1 = positive and 2 = negative. The dat... | Why is a Gamma family GLM needed to analyse this data? | stats | 2017-09-08T12:13:24.903 |
[
{
"message": "When determining the size of a sample for each strata how should this be calculated? Do we compute the sample size based on the total population and then stratify based on the percentage of each strata or do we consider each strata as a different population and calculate the sample size individual... | How to calculate sample size for stratified sampling | stats | 2017-09-08T12:57:11.750 |
[
{
"message": "I'm writing my own implementation of a neural network to test my knowledge, and while it seems to run okay, it converges such that the output is always the mean value (0.5 since I'm using logistic output activation) regardless of the input, and nothing I do seems to change anything. There are a f... | Neural network always returns same result | stats | 2017-09-10T20:03:23.773 |
[
{
"message": "When implementing dropout (or dropconnect) - do you need to account for the case that every node in a layer is dropped?Even though this is a very small chance, what is the correct approach to take in this scenario? Pick a new random set to drop out or set all the inputs to the next layer to be zer... | Dropout, what if all the nodes are dropped | stats | 2017-09-10T22:09:20.970 |
[
{
"message": "What is an example of such a function in 2D and in high dimension space? <a href=\"https://i.stack.imgur.com/5jBJL.png\" rel=\"nofollow noreferrer\"> This image is from CS231n stanford course.",
"role": "user"
},
{
"message": "Build a <a href=\"https://en.wikipedia.org/wiki/Quadratic... | Is there any example of function with high condition number? | stats | 2017-09-10T22:19:24.490 |
[
{
"message": "According to <a href=\"https://www.statlect.com/fundamentals-of-probability/legitimate-probability-mass-function\" rel=\"nofollow noreferrer\">this and <a href=\"https://www.statlect.com/fundamentals-of-probability/legitimate-probability-density-functions\" rel=\"nofollow noreferrer\">this, we can... | Check if pmf/pdf is valid | stats | 2017-09-11T11:41:26.387 |
[
{
"message": "My understanding of SVM is that it's very similar to a logistic regression (LR), i.e. a weighted sum of features is passed to the sigmoid function to get a probability of belonging to a class, but instead of the cross-entropy (logistic) loss function, training is performed using the hinge loss. Th... | Why is it wrong to interpret SVM as classification probabilities? | stats | 2017-09-11T14:50:52.230 |
[
{
"message": "My boss wants me to evaluate a rules based model that a former employee designed. The problem is that I'm not sure what type of model it is or how to evaluate its performance.The model shows which types of products a certain demographic of customers is likely to purchase.Here is how the model wo... | What is the name for this type of model? | stats | 2017-09-11T15:16:45.847 |
[
{
"message": "I am involved in an engineering project. We concern ourselves with a manufacturing process in which mechanical parts are processed. Every time a part is processed we get a set of time series data. A <a href=\"https://en.wikipedia.org/wiki/Time_series\" rel=\"nofollow noreferrer\">time series is so... | Is a "cycle" always ending where it started? | stats | 2017-09-12T08:04:37.013 |
[
{
"message": "I am trying to identify outliers from a simple time series (<code>ts1</code>; see below) and subsequently fit an ARIMA model on the adjusted ts (w/o the outliers). Appologies, if the questions below are beginner's questions.I have a question concerning the fitted values for the tsoutliers package ... | Fitted values of tsoutliers from R | stats | 2017-09-12T12:57:25.100 |
[
{
"message": "I designed a model for my dissertation which has 7 predictors based on existing theories. After data selection, I got a sample size of 126 and I thought I was okay since the data is cross sectional. After running the regression I obtained the following result:As you can see (i) the $R^2$ is -3.3% ... | Regression result shows small $R^2$ fit and large p value? | stats | 2017-09-12T22:13:53.540 |
[
{
"message": "This is my example in Python. As you can see, RidgeCV, which performs cross-validation and picks the best alpha to use, picks the model with the smallest R squared as the best model... Why?This is my <code>X</code>:<pre><code> X = np.array([[ 5., 8., 3., 4., 0., 5., 4., 0., 2., ... | Why the best model is the one with the smallest R squared? Ridge Regression | stats | 2017-09-13T10:06:30.063 |
[
{
"message": "For the sake of clarity, I'll input my questions in (1.), (2.) and so on. They are all related but honestly I don't have a sufficient grasp of the concepts so that I can formulate/compact everything in one question. So please forgive me for that.As so many people, I am starting <a href=\"https://w... | Questions regarding linear regression as we change the parameters (related to Andrew Ng's course) | stats | 2017-09-13T10:54:55.587 |
[
{
"message": "Imagine, you are solving a multiclass classification problem with highly imbalanced class. The distribution of the classes is such that, you observed the majority class 99% of the times in the training data. Your model has 99% accuracy after taking the predictions on test data. Which of the follow... | Classification problem and Associative rule mining | stats | 2017-09-13T17:08:20.253 |
[
{
"message": "I want to figure out adjusted expenditure (AE) as a proportion of income (Y) for different income bands and family compositions. The adjustment is taking mortgage (M), pension (P) and child & education (K) related expenditure away from total expenditure (E). My variables are Y, E, M, P, K, ma... | Help with the functional form of my model? | stats | 2017-09-13T17:53:50.490 |
[
{
"message": "I'm facing an optimization problem I'll have to run (with a variety of different hyperparameters) and I'd like some tips on how best to optimize it. I have a function $f$ which I can only evaluate in a noisy fashion, that is, there is a random variance to it. I have some 7 variables in group \"A\"... | Min-max stochastic function of few variables | stats | 2017-09-13T22:18:43.820 |
[
{
"message": "According to WMD <a href=\"http://proceedings.mlr.press/v37/kusnerb15.pdf\" rel=\"nofollow noreferrer\">paper, travel cost or Euclidean distance between word pairs is calculated the way shown in the figure below. <a href=\"https://i.stack.imgur.com/RZIyb.png\" rel=\"nofollow noreferrer\">Is this d... | Word Mover's distance calculation between word pairs of two documents | stats | 2017-09-13T22:30:34.360 |
[
{
"message": "Stats textbooks almost always tell us a significant interaction is necessary if we want to test the simple main effects[1]. But why? Is this again a way to control the error rate? If so, significant interactions are not indeed a must-have-first, since we can control error rates using, say, Bonferr... | Why simple effects requiring a significant interaction? | stats | 2017-09-14T01:35:58.967 |
[
{
"message": "On R, I have created a mixture distribution via a convex combination of a standard normal distribution, and a normal distribution with mean -3, variance 1 (i.e. subtracting 3 from a standard normal distribution).In doing so, I have observed that the difference between absolute values of the upper ... | Quantiles in mixture distributions - mathematical explanation | stats | 2017-09-14T04:16:21.650 |
[
{
"message": "I'm working with a panel data from a quasi-experimental study with the following characteristics1) Unbalanced covariates between the control and the treatment group (according to Hotelling's T-squared test), though I've read that it's not cause for concern (<a href=\"https://www.ncbi.nlm.nih.gov/p... | How to analyse unbalanced panel data with attrition and defiers? | stats | 2017-09-14T14:45:52.307 |
[
{
"message": "I know the differences between training, validation and test data. Just to be clear\"training data\" is used to make multiple models with different hyperparameters\"validation data\" is used to choose one of these models\"test data\" is used to ascertain how well the chosen model is really doingor... | What is data called that is fed into a model? | stats | 2017-09-15T09:09:46.077 |
[
{
"message": "Suppose i have the following two variables<pre><code> var1 var2 0 -869 5000 3593 10000 8055 15000 12517 20000 16979 25000 21441 30000 25903 35000 ... | Visualising the contents of three variables | stats | 2017-09-15T10:39:14.547 |
[
{
"message": "I am asking a high level question on what is the model \"type\" for unlock a cell phone using fingerprint / face. It seems to me supervised learning cannot be used, because we do not have labeled data. Is it a \"anomaly detection\"? Where we model the normal patterns of a authenticated user and re... | What statistics / machine learning model is used to unlock cell phone with fingerprint / face? | stats | 2017-09-15T13:43:39.433 |
[
{
"message": "For the perceptron algorithm, what will happen if I update weight vector for both correct and wrong prediction instead of just for wrong predictions? What will be the plot of number of wrong predictions look like w.r.t. number of passes? The algorithm of perceptron is the one proposed by Rosenblat... | Update weight vector regardless of correctness for perceptron algorithm | stats | 2017-09-15T20:57:52.610 |
[
{
"message": "If a network is trained using ANN classifier, how can we know which feature was most important for predicting the target variable? I mean: How to create a \"feature ranking\" among the features (from high importance value to low)? I have seen some literature about decision trees/AdaBoost but I am ... | How to rank Feature importance for ANN classifier? | stats | 2017-09-16T08:29:31.203 |
[
{
"message": "I would like to perform PCA on my data set (n=179). My result currently ends up with only one factor. I do not really know how to proceed further since I wanted to do Cluster analysis afterwards but I think with only one factor it is not possible.",
"role": "user"
},
{
"message": "Firs... | PCA with 9 variables | stats | 2017-09-16T09:41:27.133 |
[
{
"message": "What can be said in general about the rate of convergence of EM algorithm? For example, if I let the parameters to be $\\theta$, starting point to be $\\theta^0$, and the optimal solution is $\\theta^*$, so that $||\\theta^t-\\theta^*||<\\alpha||\\theta^0-\\theta^*||$, what can be said about $\... | Rate of convergence of EM algorithm? | stats | 2017-09-16T11:58:18.510 |
[
{
"message": "Let me set the context for the idealized question below: The search for extraterrestrial intelligence (SETI) has been listening for radio waves from extraterrestrial sources for half a century, with only negative results. Assume that our own radio broadcasts over the past half century have reach... | Bayesian inference on Binomial process under different assumptions | stats | 2017-09-16T16:53:30.020 |
[
{
"message": "This question is about how to interpret LM test in VAR. For example, under VAR with lag 1, the LM test shows <pre><code>lags----LM-stat----Prob1-------34.73------0.00432-------21.76------0.1508</code></pre>Oh! auto-correlation in lag 1! So, I rerun VAR with 1 more lag. Then the result of LM test u... | LM test interpretation in VAR - a joint hypotheses test? (In EViews) | stats | 2017-09-17T01:34:05.563 |
[
{
"message": "I have a data set I have been asked to provide an alternate analysis for in which 34 mothers answered a psychological questionnaire. The authors have currently conducted an exploratory analysis regressing each of the tool's four sub scales against 9 predictor variables (e.g. infant gestational age... | Multivariate analysis using multi-level models as described by Gelman | stats | 2017-09-17T03:36:02.057 |
[
{
"message": "I want to write down following group count operation. I am creating variable in dataset called countpd equal to count of observation points grouped by variables countid and day. i stands for observation point number. Is logic in the attached equation correct?$countpd_i=\\sum_{i=1}^n \\mathbb{1}_{B... | Formal notation of group count | stats | 2017-09-17T07:03:54.973 |
[
{
"message": "I've had an idea of a training scheme for multiple machine learning models, and want to know if it makes sense or it already has a name. The idea is to train models kinda like a swarm mind (I was watching <a href=\"https://youtu.be/Eu-RyZt_Uas?t=791\" rel=\"nofollow noreferrer\">this video when th... | Iterative swarm training of multiple models | stats | 2017-09-17T08:36:01.007 |
[
{
"message": "I'm currently working on the exercises of the book 'Applied Predictive Modeling' by Kuhn and Johnson (using R and caret) and am stuck at the issue of 'Calibrating Probabilities'.Exercise 12.3 shows a problem linked to openly available data on churning:<pre><code>library(C50)data(churn)table(churnT... | Calibrating Probabilities worse than Original Model even though better performance on calibration curve? (in R / Caret) | stats | 2017-09-17T10:07:59.713 |
[
{
"message": "When you have a time series that contains both trend and seasonal components, I learned that either seasonal decomposition (e.g., forecast the deseasonalized series, then add back the seasonal factor to obtain forecasts of the original series) or Holt-Winters methods (additive or multiplicative) c... | Seasonal decomposition or Holt-Winters methods for forecasting? | stats | 2017-09-18T03:33:36.780 |
[
{
"message": "The code from this paper on <a href=\"http://www.manaalfaruqui.com/papers/naacl15-retrofitting.pdf\" rel=\"nofollow noreferrer\">Retrofitting Word Vectors with Semantic Lexicons works really well. The method works with the output of any embedding model. I am trying to understand the mathematics. H... | Explanation of Mathematics for Retrofitting Word Vectors | stats | 2017-09-18T07:02:56.970 |
[
{
"message": "Virtually any database we want to make predictions using machine learning algorithms will find missing values for some of the characteristics.There are several approaches to address this problem, to exclude lines that have missing values until they fill with the mean values of the characteri... | Methods to work around the problem of missing data in machine learning | stats | 2017-09-18T15:41:34.237 |
[
{
"message": "What is the correct mathematical expression for computing Jensen-Shannon divergence between multiple probability distributions? I found the following expression on <a href=\"https://en.wikipedia.org/wiki/Jensen%E2%80%93Shannon_divergence\" rel=\"nofollow noreferrer\">Wikipedia, but I did not find ... | Jensen-Shannon Divergence for multiple probability distributions? | stats | 2017-09-18T16:52:58.023 |
[
{
"message": "Suppose I have a simple linear model with two variables and their interactions:$y = \\beta_0 + \\beta_1 x_1 + \\beta_2 x_2 + \\beta_3 x_1 x_2 + \\beta_4 x_1^2 + \\beta_5 x_2^2 + \\epsilon$where the $\\beta_i$ can, of course, be estimated by OLS. Assume that the standard Gauss-Markov assumptions of... | Approximating interactions in OLS | stats | 2017-09-18T21:10:26.170 |
[
{
"message": "The Baum-Welch algorithm can estimate the parameters for a given structure of a HMM. However, how to determine the structure, specifically the number of hidden states?Ideas so far:Trial and error, examination of the quality of fit, then increasing or decreasing the number, adopting the CV.Use RNN,... | HMM with unknown number of hidden states | stats | 2017-09-19T07:44:12.537 |
[
{
"message": "I'm looking into using a Gaussian copula to model correlation between two r.v. in a Monte Carlo simulation. I opt for the Gaussian copula as 1) I understand it and 2) it's the most easy one to explain to senior management.However when reading literature on the subject I got confused. When I read [... | Implicit assumptions Gaussian copula | stats | 2017-09-19T11:08:49.483 |
[
{
"message": "Suppose 2 washing machines A & B are rated as 3.5 and 4.0 (out of 5) respectively, vs another 2, C & D, that are rated as 4.2 and 4.7 respectively. Can I make some useful inference based on the differences among these average ratings on some portal like Amazon? In other words, can I say th... | Are average online ratings of products (say out of 5) assumed to be on a linear scale as understood by the user? | stats | 2017-09-19T14:06:25.487 |
[
{
"message": "I am doing a image classification with CNN using Keras. The training process was so far so good. But when it comes to the prediction, I couldn't figure out to extract correct prediction results out of numpy array from predict(x). It is binary classification task but I used softmax layer at the end... | Showing prediction output in Keras | stats | 2017-09-19T15:44:43.487 |
[
{
"message": "I have data where for a specific threshold, I calculate what percentage of values meet a certain criteria. I want to calculate whether there is a statistically significant trend when I increase the threshold and there is a corresponding increase in the response variable. To give an example, I have... | Which regression to use on percentage as a response variable for ordinal dependent variable? | stats | 2017-09-19T21:29:42.190 |
[
{
"message": "For example, suppose I am concerned with two Bernoulli RVs and want to test the alternative $p_1 < p_2$ against the null $p_1 \\geq p_2$. I take some samples from each distribution, and discover that the empirical proportions satisfy $\\hat{p_1} < \\hat{p_2}$, but the test doesn't reject the... | Does it affect the guarantees of a test to take more samples if the test fails to reject, then perform it again? | stats | 2017-09-20T15:06:55.593 |
[
{
"message": "Given $N<\\infty$, $0<q<1$ (arbitrarily close to 1) and $\\epsilon>0$ (arbitrarily small)one can construct an example of a one parameter family of distributions$P_\\theta$, $\\theta\\in[0,1)$, on the unit circle (viewed as a group, namely theunit interval with addition modulo 1) such t... | Failure of Maximum Likelihood Estimation | stats | 2017-09-20T15:12:47.310 |
[
{
"message": "I am working on an \"object recognition\" project. I have 3 types of objects. I am always able to detect them but unable to correctly classify them using an SVM. Very often, for example, an \"unknown\" object is misclassified as object 1 with very high certainty.My SVM only contains 3 classes actu... | What classifier allows me to classify: object 1, object 2, object 3, none of those 3? | stats | 2017-09-20T20:03:49.620 |
[
{
"message": "I understand that Imbens has several papers on IPW, but was wondering if there was a default text one would recommend to understand IPW. For example, where does the estimator:$$\\tau = \\frac{1}{N^T}\\sum_{i=1}^N \\frac{W_iY_i}{e_i(X_i)} - \\frac{1}{N^C}\\sum_{i=1}^N \\frac{(1-W_i)Y_i}{1-e_i(X_i)}... | What is the standard literature on Inverse Probability Weighting Estimators? | stats | 2017-09-21T07:41:32.423 |
[
{
"message": "I have an experiment with two groups under different conditions where a single dependent variable is measured repeatedly at multiple times. It seems the right parametric test to use here is <a href=\"https://statistics.laerd.com/spss-tutorials/mixed-anova-using-spss-statistics.php\" rel=\"norefer... | Non-parametric test equivalent to mixed ANOVA? | stats | 2017-09-21T09:21:40.103 |
[
{
"message": "In MNL model, given the different alternative choices, we estimate the probability of choice across different options.E.g. using the fishing data, we can use the following calculations to estimate the probability across 4 alternatives for each individual choices.<pre><code>Fish <- mlogit.data(F... | Estimation of Demand and Substitution in Case of Multinomial Logit Model | stats | 2017-09-21T16:33:56.720 |
[
{
"message": "I want to build something that can classify tweets (from my timeline or lists) by topic. I can of course provide a dataset of tweets pre-classified for each variant, but then the software should be able to learn from that and apply that logic to new, future tweets.Variant A) Take all tweets of a t... | Machine learning to classify tweets into topics – Where to start? | stats | 2017-09-21T17:11:19.097 |
[
{
"message": "I'm reading <a href=\"http://amzn.to/2kxP1vO\" rel=\"noreferrer\">Marin's and Robert's Bayesian Essentials with R to work on the foundations of my understanding of Bayesian analysis. In the first chapter, about normal models, I'm having some trouble working the posterior distribution by myself.For... | Help with Bayesian derivation of normal model with conjugate prior | stats | 2017-09-21T20:51:08.307 |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.