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 have been googling for a list of practical applications of Recurrent Neural Networks for some time, but did not find a reasonable reference list.Most of the things are about text generation which seems to be rather for fun/academic research. I do not have anything against text generation. I am l... | (Practical) Applications or RNN | stats | 2017-09-22T07:50:31.387 |
[
{
"message": "I have this case where the data look like that<pre><code>Trial Person 1 person 21 4.7. 3.82 7.1. 6.33 5.4. 4.5</code></pre>I want to see if there is variations WITHIN each person measurements. I want to do this in R. I found the test that supposed t... | what is the analytical test to run in case of 1 measure for three groups | stats | 2017-09-22T08:16:45.987 |
[
{
"message": "This is my first time working with regularized regression so I apologize if the answer to this is obvious. I am planning on using GLMnet to run a regularized logistic regression on my data set using glmnet. Previously I have been using unregularized logistic regression and have evaluated my model/... | Building final model in glmnet after cross validation | stats | 2017-09-22T08:40:58.920 |
[
{
"message": "I have been working on a set of data which contains information on the width, age, weight of statues and relate them to the price (I am not actually working on that, but I cannot disclose the topic of my work).I came up with the following regression:$Price = -9 -width + 4 log10(age) + 8 height$th... | In a regression is the Y-intercept a measure of unaccounted biases? | stats | 2017-09-22T12:50:36.023 |
[
{
"message": "One common measure used to compare two or more classification models is to use the area under the ROC curve (AUC) as a way to indirectly assess their performance. In this case a model with a larger AUC is usually interpreted as performing better than a model with a smaller AUC. But , according to ... | Comparisson of two models when the ROC curves cross each other | stats | 2017-09-22T13:42:24.237 |
[
{
"message": "I have collected this empirical data, and would like to know which function describes this data (3 curves) at best.I have try non linear fit in R, but not good fit.How can I discover the relation between y and x in R?<a href=\"https://i.stack.imgur.com/n6nOg.png\" rel=\"nofollow noreferrer\">The d... | Which function fits this data? | stats | 2017-09-23T18:11:47.763 |
[
{
"message": "I have made a model with continuous and categorical(binary) predictors, with the dependent variable being continuous.Can I create an interaction variable between 2 binary predictors and add it to the model while excluding the 2 predictors it came from?It seems to me it would be valid in the sense ... | Interaction between Binary Predictors in Multiple Linear Regression? | stats | 2017-09-23T18:33:14.417 |
[
{
"message": "I want to perform One-way analysis with permutation test. In this <a href=\"https://rcompanion.org/rcompanion/d_06a.html\" rel=\"nofollow noreferrer\">link, I found some instructions how to proceed in R. In that tutorial, the example data set has equal sample sizes by factor: <a href=\"https://i.s... | Stacking layers of permutation: Calculating Monte Carlo p values using other Monte Carlo p values | stats | 2017-09-24T23:10:01.120 |
[
{
"message": "In causal inference, the consistency assumption states that there are no multiple versions of treatment. Specifically, for a potential outcome unit $Y_i$ and a binary treatment vector $\\mathbf{Z}$, $$Y_i(\\mathbf{Z})=Y_i(\\mathbf{Z'}) \\ \\ \\forall \\ \\mathbf{Z},\\mathbf{Z'}:\\mathbf{Z}=\\mathb... | In causal inference in statistics, how do you interpret the consistency assumption in mathematical terms? | stats | 2017-09-25T04:11:11.453 |
[
{
"message": "I am trying to implement the Nelder-Mead algorithm for optimising a function. The <a href=\"https://en.wikipedia.org/wiki/Nelder%E2%80%93Mead_method\" rel=\"noreferrer\">wikipedia page about Nelder-Mead is surprisingly clear about the entire algorithm, except for its stopping criterion. There it s... | Stopping criterion for Nelder Mead | stats | 2017-09-25T07:36:52.810 |
[
{
"message": "Besides LDA (Latent Dirichlet allocation), are there other ways or methods to detect a topic or category from a sentence?For example, all the categories or tags from news websites can be used to train a classifier to predict the topic for a new sentence or article or a paragraph. Are there any kno... | Topic detection for a sentence or an article using Machine learning | stats | 2017-09-25T21:25:21.407 |
[
{
"message": "I'm using <a href=\"https://arxiv.org/pdf/1206.1901.pdf\" rel=\"nofollow noreferrer\">Hamiltonian Monte Carlo (HMC) implementation in <a href=\"http://edwardlib.org/\" rel=\"nofollow noreferrer\">Edward, a probabilistic programming library built on top of TensorFlow. One of the hyper-parameters of... | How to set step-size in Hamiltonian Monte Carlo? | stats | 2017-09-25T21:49:51.913 |
[
{
"message": "How does the parameter estimation/Training of a logisticregressuib really work? I'll try to put what I've got so far. The output is y the output of the logistic function in form of a probability depending on the value of x :$$P(y=1|x)={1\\over1+e^{-\\omega^Tx}}\\equiv\\sigma(\\omega^Tx)$$$$P(y=0... | Understanding the Logistic Regression and likelihood | stats | 2017-09-26T07:00:13.423 |
[
{
"message": "From what I understand, type II and type III ANOVA should give the same result irrespective of the order of the factors in the formula because they calculate:<pre><code>Type II: SS(A | B) for factor A. SS(B | A) for factor B. SS(A:B|A,B) for the interaction. Type III: SS(A | B, A:B)... | Why does Type II/III ANOVA on cumulative link model (R-package ordinal) give different results depending on factor order? | stats | 2017-09-26T12:02:10.303 |
[
{
"message": "I'm trying to train a regression tree with some very large data I have: approx 3Tb.I'm using scikit-learn and of course there is no way I can load that amount of data on memory. Doing some online research I found that some scikit-learn algorithms have a partial_fit method which can be used for thi... | Incremental learning with decision trees (scikit-learn) | stats | 2017-09-26T12:25:57.063 |
[
{
"message": "Can anyone explain why, for an independent two-sample t-test assuming unequal variances, R's <code>t.test</code> function uses the label \"Welch Two Sample t-test,\" when it appears to use Satterthwaite's 1946 formula for the degrees of freedom (d.f.) calculation?Specifically, I accessed the body ... | R's t.test() unequal variance degrees of freedom | stats | 2017-09-26T22:48:29.663 |
[
{
"message": "I have a random process that follows a normal distribution. It's parameters are mean = 35 units, std.dev. = 8 units. I've seen from the <a href=\"https://en.wikipedia.org/wiki/Normal_distribution\" rel=\"nofollow noreferrer\">wiki entry for the normal distribution that there is a formula to calcul... | What are the units of entropy of a normal distribution? | stats | 2017-09-27T01:52:43.527 |
[
{
"message": "Apologies in advance for any vagueness in the question. Please let me know if clarification is needed.If a control group has a 33% payback rate on a loan, and an experiment finds that a treatment group had an 8% increase in probability to pay back a loan, can I simply do .33*.08 to extrapolate wha... | Treatment vs control extrapolation of results | stats | 2017-09-27T13:53:43.920 |
[
{
"message": "I am training a neural network to play tic-tac-toe. The input is the board (a vector of 9 doubles) and the output is a vector of Q-values (9 doubles).The input vector is analyzed as follows: If a cell in the input vector is below -0.5 the cell is occupied by the Nought. If the cell is over 0.5 it ... | Can a single neural network be trained to play both sides of a board game? | stats | 2017-09-28T09:32:29.350 |
[
{
"message": "I know that two normal distributions can be subtracted and get a new distribution with a mean of $\\bar{x} = \\bar{x}_1-\\bar{x}_2$ and a standard deviation of $\\sigma = \\sqrt{\\sigma_1^2 + \\sigma_2^2}$. Does someone know if the same applies for the subtraction of two skewed (in my case Gumbel)... | Mean and Standard deviation of Gumbel distributions subtraction | stats | 2017-09-28T09:43:57.797 |
[
{
"message": "First of all sorry for the sloppy terminology, but I am right looking for the name of a statistical concept. I was asked to calculate the \"turnover\" of the Facebook friends commenting on my posts, so I am looking for an indicator that has high value if always the same let's say 10 friends are co... | Variance of set of subsets | stats | 2017-09-28T14:53:47.787 |
[
{
"message": "I have a huge data set (4-5 million entries). The data is indexed by 10 values <code>(v1, v2, ..., v10) = IDENTIFIER</code>.The Identifier is not unique, there are many repetitions. The indexes are numbers, letters or dates.Does there exist any tool or algorithm or idea to find some correlations w... | Finding hidden data pattern in big data set | stats | 2017-09-28T17:28:21.530 |
[
{
"message": "I am creating a multilevel model to measure change over time in risk behaviors over 25 months. The risk behaviors are calculated as how many behaviors from a list of 22 that people report doing or not doing in any given month. However, because of logic statements, participants may or may not be as... | Using random effect to account for different number of items in survey mean | stats | 2017-09-29T21:20:40.000 |
[
{
"message": "I have a time series data and I applied the first difference operator to make it stationary. When I plot the partial autocorrelation function of this differenced time series, I find peaks with value >1 and less than <-1 at certain lags.1)Should I consider these lags for my analysis?2)I am using... | what does it mean if the partial auto correlation function of a time series have a value >+1 or <- 1? | stats | 2017-09-30T14:10:21.697 |
[
{
"message": "I am doing a classification and I have this question about using linear discriminant analysis (LDA) just for dimension reduction:Shall the LDA be applied on whole feature matrix including train and test data and then (after reducing the dimension of data) do the partitioning of feature matrix to p... | LDA as the dimension reduction before or after partitioning | stats | 2017-09-30T14:42:12.790 |
[
{
"message": "(1) Confidence intervals<br>(2) Posterior probability intervals<br>(3) Fiducial intervals<br><br>Is there some conventional term that encompasses these three sorts of intervals, but does not include prediction intervals? All of them are BLANK intervals. Fill in the blank.",
"role": "user"
},... | Terminology in interval estimation | stats | 2017-10-01T01:25:40.027 |
[
{
"message": "QuestionIn normal GD the weights are updated for every row in the trainingdataset while in SGD the weights are updated only once for the minibatch based on cummulative dLoss/dw1, dLoss/dw2 . Is myunderstanding correct?Does updating weights only once for m examples based on cumulativedLoss/dw1, dLo... | What is the difference in "weight update process" in gradient descent vs Stochastic gradient descent? | stats | 2017-10-01T09:24:26.617 |
[
{
"message": "I have a pretty small data set with (approx 150 obs) that I'm using to predict both a binary outcome variable and a continuous. Right now, I'm using nested cross validation as follows:Outer loop is 20 times repeated 5-fold CV to produce 100 performance metrics. Each inner loop is 10-fold CV to tun... | Get CI and p-values for cross validated performance measures (AUC, rho) | stats | 2017-10-01T16:42:59.757 |
[
{
"message": "So I have the following problem and I want to discuss it with you to see if I am thinking correctly.Data description:I have recurrent data from clinical trial. The data has a specific <code>mtest</code> that is performed each year to indicate disease degree <code>scale</code>. The <code>mtest</cod... | Prediction with accelerated failure time in r for clinical data | stats | 2017-10-01T17:30:36.577 |
[
{
"message": "I am having a really hard time taking concepts of probability space, experiment, random variables and stitching them together to make a robust understanding of the probability theory. So every probability theory starts with an experiment. According to Wikipedia \"In probability theory, an experime... | Concepts of Probability all messed up | stats | 2017-10-01T19:46:12.633 |
[
{
"message": "When increasing the value of the latent variable k for LDA (latent Dirichlet allocation), how should perplexity behave:On the training set?On the testing set?",
"role": "user"
},
{
"message": "The original paper on LDA gives some insights into this:<blockquote> In particular, we compu... | How should perplexity of LDA behave as value of the latent variable k increases? | stats | 2017-10-02T03:00:04.393 |
[
{
"message": "I try to understand interactions in multiple linear regression and especially how to plot them and there is one uncertainty that emerged I hope somebody can rule out for me. So if you have done the MLR and the interaction term is significant and you now want to do the post hoc test. We have to do ... | question regarding plotting interaction effects | stats | 2017-10-03T17:16:19.667 |
[
{
"message": "I am trying to compute mutual information for 2 vectors. I made a general function that recognizes if the data is categorical or continuous. It's really difficult to find simple examples of this calculation and I have only found theoretical implementations (e.g. <a href=\"https://stats.stackexcha... | How to correctly compute mutual information (Python Example)? | stats | 2017-10-03T20:09:47.283 |
[
{
"message": "I need to test the effect of X on Y through M. Based on knowledge, I know X does not have direct effect on Y. X has to act on Y through some mediator(s). In this case, do I still need to estimate the direct effect of X on Y (c') in my model? Is it ok if I only estimate a (effect of X on M) and b (... | c' in mediation analysis | stats | 2017-10-03T20:15:09.730 |
[
{
"message": "What is the value of $a$ and $b$ that minimizes the $L_1$ and $L_2$ norm, respectively?$$ \\min_{a} \\mathrm{E} \\left| X - a \\right|$$I was told that median is the solution. How do you solve it? Why can't it be the mean instead?$$\\mathrm{E} (X - b) ^ 2$$I was told that mean $\\mu$ is the soluti... | Why is median the solution to absolute difference, but mean is the solution to squared difference? | stats | 2017-10-05T01:26:41.690 |
[
{
"message": "I have some questions about pre-tests and post-tests:Can I have different items (questions) for pre-test and post-test? Or is it necessary to have the same item?Can post-test be used as a summative assessment?Can post-test be used to evaluate if the students have achieved the desired learning outc... | Pre-test and Post-test | stats | 2017-10-05T06:51:15.527 |
[
{
"message": "In all the (regression) random forest papers I've read, when it comes the time to gather the predictions of all the trees, we take the average value as the prediction.My question is why do we do that?Is there is a statistical justification for taking the average?EDIT: To clarify the question, I kn... | Why do we take the average for regression Random Forest predictions? | stats | 2017-10-05T11:00:15.450 |
[
{
"message": "I was thinking about a problem and I did not know how to search for relevant theory behind it so hopefully someone can help me. Suppose you are playing a game, where someone thinks of an object and he types its name and sends it to you so you can find out which object he is thinking of. However, e... | Random "words" game | stats | 2017-10-05T16:56:02.383 |
[
{
"message": "I am trying to grasp what is the meaning of getting unexpected negative values for some percentiles of a mixture distribution. Let the distribution function pdf be:\\begin{equation}f(x) = (1-p)\\cdot \\delta(x) + p\\cdot \\lambda e^{-\\lambda\\,x} \\cdot H(x)\\end{equation}where $p$ is the probabi... | Percentiles of mixture distribution: negative values? | stats | 2017-10-05T18:52:15.530 |
[
{
"message": "I am reading mixed opinions comparing bayesian A/B testing and frequentist ones.Basically my understanding is the following; consider the case of A/B testing with binary outcomes (<a href=\"https://www.evanmiller.org/bayesian-ab-testing.html#mjx-eqn-binary_ab_pr_alpha_b\" rel=\"nofollow noreferrer... | Bayesian vs frequentist A/B testing: in which sense they are equivalent with uniform priors? | stats | 2017-10-06T15:17:58.377 |
[
{
"message": "I have one question from econometric class which asks to find the probability distribution of the following: $$X_c = X ({1_{\\{|X|>c\\}}}-{1_{\\{|X|\\le c\\}}}) $$where $X \\sim N(0,1)$ and $c > 0$. I am not even sure what $X_c$ is referring to. Does anyone have any idea? Thanks!",
"role... | How to determine the distribution iof this transformed variable $X_c = X ({1_{\{|X|>c\}}}-{1_{\{|X|\le c\}}})$ | stats | 2017-10-07T02:59:16.067 |
[
{
"message": "I'm wondering how I could compute a p-value for this kind of analysis.Let's say I've 5 boxes. Each box is made with the same 100 cases (numbered 1 to 100). In each of these 5 boxes some cases are black and some are white. In general most of the cases are white. The number of black cases is not equ... | compute p-value number of occurrence in different samples | stats | 2017-10-08T22:32:39.670 |
[
{
"message": "I have a time series that I want to predict (using Neural Network, but is not important). On top of using the info at previous values ($t-1$, $t-2$, ...etc) I want to use another variable: the hour of the day.Stupid MethodOne way would be to map:$00:00 \\rightarrow 0 $$01:00 \\rightarrow 1$....and... | how to encode classes so that they reflect sequential correlation between them | stats | 2017-10-09T14:31:49.577 |
[
{
"message": "Consider, for example, that I demand that every farmer gives me 10 of their best apples from each of the tens of apple orchards that I own. I detest worms in my apples, but know that some will worm their way into some of them in any case. The farmers know exactly how many of their apples contained... | Testing mean difference between multiple (small) samples and their populations | stats | 2017-10-09T18:05:33.590 |
[
{
"message": "I have a dataset with ~800K samples, ~300 features and I'm trying to predict a binary outcome. I've started with sklearn's <code>SGDClassifier</code> (using log loss and l1 penalty), and I got a nice 0.67 auc score on my validation set; now I'm trying to improve this.I have a reason to believe tha... | Regressors vs. conditioning variables in glmtree | stats | 2017-10-10T09:06:07.020 |
[
{
"message": "Nowadays, in the scientific domain, increasingly, people in the top position argue against doing post-hoc analysis and they advise against collecting a bunch of data and just make up a story after data collection and report the significant findings. In psychology, which is my field, recently some ... | Is publishing work based on post hoc analysis problematic? | stats | 2017-10-10T11:34:10.060 |
[
{
"message": "Suppose I have collected some data, where each datum is an interaction of an agent with an environment. From this, I then train a neural network to learn a dynamics model, and to predict the next state $s_{t+1}$ given state $s_t$ and action $u_t$.What I want to do now is, for any given initial st... | Training an agent to move to a goal location | stats | 2017-10-10T15:08:59.393 |
[
{
"message": "In a survival analysis, is it possible to use a likelihood based measure like AIC to compare the fit obtained from a Cox model and a parametric regression model? I have seen different views, from (1) no you can't to (2) finding a variety of published papers that do so!While the more I think about ... | Comparison between Cox regression and parametric regression using AIC | stats | 2017-10-10T16:14:52.487 |
[
{
"message": "Background: My background is in statistics, but I have very little experience in working with time series data, so please go easy on me if I'm not making sense :)Case Study: Let's suppose I would like to forecast honey output in the next quarter. I have data about historical honey outputs as well ... | Time Series: making use of extraneous data | stats | 2017-10-11T04:22:30.197 |
[
{
"message": "I've estimated a parameter $\\theta$ of a linear model as $$\\hat\\theta = \\frac{2 \\sum x_i^2 Y_i}{\\sum x_i^4}$$Where $Y_i$ is the response variable. I was wondering how does one find the variance of this estimator given normally distributed error terms with mean 0?I've gotten to$$ V(\\hat\\the... | Variance of an estimator? | stats | 2017-10-11T08:01:05.890 |
[
{
"message": "It's common in many applications to interact a set of numeric variables with a factor variable. The factor variable is a convenient abstraction for what is actually a matrix of dummy variables. For example, say I've got a $N\\times 3$ matrix $X$ and a 3-level factor $fac$. In R I could generate... | matrix form of dummy expansion? | stats | 2017-10-11T17:07:37.087 |
[
{
"message": "So, I have some data.. and a parameterized Hawkes process which I estimate parameters for via maximum likelihood... the residuals ( the compensator aka the dual-predictable projection) are good in that they both have nearly 1 for mean and variance and have almost no remaining autocorrelation. The ... | Hawkes processes: interpretation of maximum likelihood estimates disagreeing with moment estimator estimates? | stats | 2017-10-11T19:51:40.887 |
[
{
"message": "I am new to this website, to r, and to mixed effect models so apologise in advance if I exhibit a degree of ignorance. I am looking for help of how to fit a model for an experiment that I have done. I am familiar (to an extent) with the lme4 package. So I'd like to use the lmer().My experimental d... | Split plot in time mixed-effect model in R | stats | 2017-10-12T03:33:14.993 |
[
{
"message": "At Mathematics Stack Exchange, user940 provided a general formula to calculate the variance of the sample variance based on the fourth central moment $\\mu_4$ and the population variance $\\sigma^2$ (<a href=\"https://math.stackexchange.com/questions/72975/variance-of-sample-variance\">1... | Unbiased Estimator of the Variance of the Sample Variance | stats | 2017-10-12T09:50:40.280 |
[
{
"message": "There exist several implementations of the GBDT family of model such as:GBMXGBoostLightGBMCatboost. What are the mathematical differences between these different implementations?Catboost seems to outperform the other implementations even by using only its default parameters according to <a href=\"... | Mathematical differences between GBM, XGBoost, LightGBM, CatBoost? | stats | 2017-10-12T11:43:11.330 |
[
{
"message": "I am doing a sports analytics (Sabermetrics) project and wish to investigate the effect of jetlag on MLB players. Currently I am performing analysis on the individual player level rather than the team level. I have a set of players and their stats in non-jetlag games, and I also have their stats w... | Analysing and presenting results of many t-tests | stats | 2017-10-13T18:11:23.267 |
[
{
"message": "Recently, I came across a publication using a level/tile/contour plot to illustrate the relationship between two continuous variables and a continuous response (with the input variables on the x and y axes and the response plotted as a color). This struck me as a very intuitive way to plot this ty... | Level plot for continuous x continuous interaction with continuous response | stats | 2017-10-13T21:28:13.997 |
[
{
"message": "So ive been struggling with the concept of null hypothesis and getting it laid out properly. I have a question for class that deals with it and I was wondering if im on the right path. The question is:a. Write the null and alternative hypotheses for a test of whether the marketing campaign was su... | Null Hypothesis Help | stats | 2017-10-14T20:56:40.877 |
[
{
"message": "I have the following plot in time series and would like to extrapolate it to derive a value in X[n+20], for instance. I tried poly fitting it but extrapolation does come out correct that way. Any proposed approaches? <a href=\"https://i.stack.imgur.com/U049N.png\" rel=\"nofollow noreferrer\">The ... | Extrapolation of Time Series in Python | stats | 2017-10-15T01:58:05.757 |
[
{
"message": "I have a regression model and used some independent variables to estimate dependent variables.Now I am trying to evaluate the model performance by using percentage bias (p_bias) and Model efficiency (ME). Now I am confused here: In my result percentage bias is 146 while I am getting ME of 4.3. Is ... | Interpret Model error result. | stats | 2017-10-15T07:26:51.233 |
[
{
"message": "According to English wikipedia, there are <a href=\"https://en.wikipedia.org/wiki/Statistical_noise\" rel=\"nofollow noreferrer\">Statistical noise and <a href=\"https://en.wikipedia.org/wiki/Noise_(electronics)\" rel=\"nofollow noreferrer\">Random noise (e.g., white noise). However, I've never se... | What is the difference between "random noise" and "statistical noise"? | stats | 2017-10-16T03:25:52.260 |
[
{
"message": "I was wondering if anyone can point me to anywhere or in the right direction.Which approach is the best for tackling a nested classification problem.So we want to classify species of animal say etc.We have split this into three layers - cellular level, organ level, organism level.So we have differ... | Nested classifications | stats | 2017-10-16T07:48:32.887 |
[
{
"message": "I was wondering if anyone can point me to anywhere or in the right direction.Which approach is the best for tackling a nested classification problem.So we want to classify species of animal say etc.We have split this into three layers - cellular level, organ level, organism level.So we have differ... | Nested classifications | stats | 2017-10-16T07:48:32.887 |
[
{
"message": "I have a dataset consisting of pairs of points, $(x_i,y_i)$. Visually, I see that the points are not completely smeared, but that $x$ seems to exert some control on $y$. In fact, I suspect that $y$ is a function of $x$ plus some noise. But I have not idea of the shape of this function. Is there a ... | Is $Y$ a function of $X$ (without knowing the shape of the function)? | stats | 2017-10-16T12:52:53.870 |
[
{
"message": "The project I'm working on attempts to explain why an NGO is present (1=present,0=not present) in some countries (15) but not others. As I'm working with country-level data, my sample size is naturally limited to the number of existing countries (193). Moreover, many countries criminalize the exis... | Logistic regression with small number of cases | stats | 2017-10-16T16:20:19.123 |
[
{
"message": "I know this has been already asked, but I am quite confused about the interpretation of logit regression estimates if I have interacted variables (continuous and binary ones).I run the following regression:<pre><code>model <- glm(elected ~ treat + factor(School) + factor(Race) + ... | How to interpret logistic regression coefficients with interactions between binary and continuous variables? | stats | 2017-10-17T03:00:30.940 |
[
{
"message": "If there is a <br>0.3% chance of living through 2017,<br>0.2% chance of living through 2018,<br>0.15% chance of living through 2019,<br>0.05% chance of living through 2020, and<br>0% chance of living through 2021.<br><br>Is the Probability of being dead in 2019 equal to:<br>0.3*0.2*0.85<br>= 0.051... | Probability over a period of time | stats | 2017-10-17T06:37:07.877 |
[
{
"message": "This is more of an interpretation question than anything. I have run a GLMM with two fixed factors (both of which have two levels) and two random factors. The outputs from the model are as such:<pre><code>Fixed effects: Estimate Std. Error z value Pr(>|z|) (Intercept) ... | Both variables of my GLMM output are significant. Don't know how to interpret it? | stats | 2017-10-18T09:02:14.273 |
[
{
"message": "The <code>pwr.r.test</code> in R which uses the arctanh transformation (Fisher's $z$ transformation) relates inversely with the correlation coefficient. That is, if $r$ is high then $n$ is low. <pre><code>pwr.r.test(n=NULL, r=.7, sig.level=0.01, power=0.99, alternative=\"two.sided\")</code></pre>... | Shouldn't the pwr.r.test on correlation estimate higher n for a higher rho value? | stats | 2017-10-18T09:43:28.510 |
[
{
"message": "I am trying to figure out how many significant figures I should report after doing a linear regression in Excel.I have a dataset of 740 entries.I use 75% of them as a training set for the regression and 25% as the testing set. Each set is determined randomly.I do a first regression I come up with ... | Regression Model Replicates: Precision VS Significant Figures | stats | 2017-10-18T11:00:06.947 |
[
{
"message": "I have an numerical, continous variable as my dependent variable, namely CDS. My independent variable is categorical, namely different time intervals after a downgrade. Unfortunately my data does not have a normal distribution nor are the variances homogenous. Therefore I have to use a non-paramet... | Corporate Finance experiment, non-parametric test | stats | 2017-10-18T13:54:29.530 |
[
{
"message": "I was given a set of data and was asked to use Stata to perform matching by using propensity scoring method. Since I only learned probit and logit model when facing binary dependent variable in my introductory Econometrics model, I only thought about using probit and logit model to get the propens... | What are the models used for propensity scoring? | stats | 2017-10-18T22:25:10.977 |
[
{
"message": "So I have two datasets from two different groups (blackbirds and song thrushes), with the same 4 variables (Foraging, Singing, Alarm, Aggressive). I've been struggling to find a good way to compare the data in these different sets, the sampling that was conducted is called scan sampling, so it's j... | Most appropriate tests for two data set comparisons in R | stats | 2017-10-19T08:12:49.487 |
[
{
"message": "Experiment: You are given a large population of real numbers. For simplicity take the whole numbers from -n to n. Take two independent random samples x and y of size k and sort them (each one individually). Compute the linear regression $y=a+bx$. Question: what are the expected values for a and b?... | linear regression, symmetry of model does not lead to symmetry of coefficients | stats | 2017-10-19T08:47:43.820 |
[
{
"message": "I am a novice in statistics and understand more the concepts than what is going on \"under the hood\", so please excuse and naivety. I am trying to prove whether a R² value for a specific regression model is \"statistically significantly\" better than another one.Here is a basic background of the ... | Proving statistical significance for regression R² values | stats | 2017-10-19T12:42:13.917 |
[
{
"message": "It is often recommended to subsample randomly if class sizes are unbalanced in classification - especially when classification accuracy is used. My question however: How often should the subsampling be done? For instance, if I subsample 10 times and then average classification accuracy over these ... | How often to subsample for classification? | stats | 2017-10-19T17:08:19.290 |
[
{
"message": "Let $(X_1,X_2,...,X_n)$ be a random sample from a uniform distribution on the interval $(-\\theta,\\theta)$, where $\\theta$ is an unknown positive number.A particular sample of size $5$ gives values $0.87,-0.43,0.12,-0.92$ and $0.58$.How can I draw a graph of the likelihood function $L(\\theta)$ ... | How to draw the Likehood Function against the parameter? | stats | 2017-10-20T09:29:40.147 |
[
{
"message": "I am studying neural network. I read a lot about mini-batch gradient descent. So now, I was implementing it in TensorFlow.But I have some questions regarding the matrix formulation of the problem/vectorization.NotationFirst some notation $w_{ij}^l$ is the weight on the connection connecting node $... | mini batch matrix form of neural network | stats | 2017-10-20T10:50:48.493 |
[
{
"message": "My goal is to analyse vegetation cover data. The way the data collection works is that you throw a quadrat (0.5m x 0.5m) in a sample plot and estimate the percent cover of the target species. Here is an example:<pre><code>df <- structure(list(site = structure(c(1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1... | Zero inflated beta regression using gamlss for vegetation cover data | stats | 2017-10-20T14:10:01.540 |
[
{
"message": "On the lecture notes provided by my tutor, the caliper matching is introduced under the methods of nearest neighbour matching. Basically, on the slide, it says the nearest neighbour matching lacks common support restriction, as all units matched to their nearest neighbour no matter how far away. B... | Will impose a caliper help to reduce the bias or reduce the variance? | stats | 2017-10-21T23:01:19.467 |
[
{
"message": "Problem: Im unsure if I understood Nesterov OptimizationIm writing about Nesterov Optimization, but the notation im using seems different from the references below. I have done it using some books as guides.Would someone please clarify?Let $\\epsilon$ be the learning rate, $w$ each weight of the n... | Trying to write Nesterov Optimization - Gradient Descent | stats | 2017-10-22T00:14:02.940 |
[
{
"message": "I want to do predictions of missing data MAR. I do the simulations by generating normal data with 1 y and some x. after that I remove the data: Proportion of missing value from 5%, 10% to 50%. I use imputation mice. I would to ask, how much imputation should I do for each of the missing data propo... | MAR Assumption missing data | stats | 2017-10-22T06:51:30.177 |
[
{
"message": "I am using a multi-layer perceptron with 2 hidden layers to solve a binary classification task on a noisy timeseries dataset with a class imbalance of 80/20. I have 30 million rows and 500 features in the training set. The dataset is structured, ie, not images. My original features were highly rig... | Final layer of neural network responsible for overfitting | stats | 2017-10-22T18:16:35.620 |
[
{
"message": "The Ward's method is taking distance as how much the sum of squares will increase when we merge them.$d(u,v) = \\frac{|u||v|}{|u|+|v|}{|m_u-m_v|}^2$Please refer to Page 3 of link below.<a href=\"https://www.google.co.kr/url?sa=t&rct=j&q=&esrc=s&source=web&cd=2&cad=rja&u... | Hierarchical clustering Ward's method. The missing rationale in derivation | stats | 2017-10-23T12:52:55.473 |
[
{
"message": "I would like to calculate some measure of volatility or noise for stationary time series data. This can be a measure for a single time series or a relative measure comparing multiple time series together. Let's assume a Dickey-Fuller test has already been conducted, and all the time series do not ... | Measure of volatility for time series data? | stats | 2017-10-23T16:52:07.873 |
[
{
"message": "I'd like to use TensorFlow to model a very basic function. Here, I'm trying to model x^2 (x squared). If I can get this to work, I should have no trouble getting more complicated examples to work. But for some reason, I'm stuck.I mean, it's correct for 0^2, 1^2, and 2^2, but nothing else.<pre><cod... | Using TensorFlow regression to learn x^2 results in a constant for most input values | stats | 2017-10-23T19:19:46.407 |
[
{
"message": "Let's say I implement an algorithm that shuffles a deck by simply swapping any 2 cards. How many times do I need to swap in order to have an even number of chances for any order.Assume the following pseudocode:<pre><code>for n=0: n<num_iterations: r1 = random(52) r2 = random(52) swap(card[r1... | How many swaps to shuffle a 52 card deck? | stats | 2017-10-23T19:57:44.487 |
[
{
"message": "I have a dataset that includes in situ measurements of:Dependent variable- growth rates (continuous)Independent variable - temperature (continuous)Independent variable - food concentration (continuous)and I want to test the effect of food concentration on growth rates, while accounting for the dif... | Can I run a two-factor ANCOVA analysis with two continuous independent variables? | stats | 2017-10-23T20:38:42.650 |
[
{
"message": "I have a script that scans text files and searches for keywords related to cryptography. And I'm scanning source code files. A lot of the times, I get back some evidence of cryptography like \"AES_encrypt\", but sometimes it can be a false positive, e.g. the keyword \"crypt\" in the string \"crypt... | What kind of classifier should I be using? | stats | 2017-10-24T03:32:50.167 |
[
{
"message": "It is a replica of my question at <a href=\"https://stackoverflow.com/questions/46895017/is-there-a-specific-reason-why-r-glm-does-not-return-warnings-while-anovaglm\">https://stackoverflow.com/questions/46895017/is-there-a-specific-reason-why-r-glm-does-not-return-warnings-while-anovaglmI was adv... | Is there a specific reason why R GLM does not return warnings, while anova(glm) does? | stats | 2017-10-24T08:50:46.653 |
[
{
"message": "I'm aggregating several large surveys with similar/same questions, but from different years. While the questions are often similar in consecutive years and within eras, few questions were asked in every year that the survey was taken. Unfortunately, imputation is not an option for most of the vari... | Finding predictive power of variables with many missing values | stats | 2017-10-24T11:20:34.643 |
[
{
"message": "I've been working with Convolutional Neural Networks (CNNs) for some time now, mostly on image data for semantic segmentation/instance segmentation. I've often visualized the softmax of the network output as a \"heat map\" to see how high per pixel activations for a certain class are.I've interpre... | Why is softmax output not a good uncertainty measure for Deep Learning models? | stats | 2017-10-24T12:58:52.483 |
[
{
"message": "I'm analyzing employee performance at a call-center. I'd like indicate whether a particular employee's conversion (success) rate is significantly different from the average/expected conversion rate. Some factors for consideration:there is a wide range of events for each employee. i.e. some employe... | Choosing a significance test for employee performance | stats | 2017-10-25T03:06:10.997 |
[
{
"message": "<a href=\"https://i.stack.imgur.com/FJHMe.jpg\" rel=\"nofollow noreferrer\">My model is ARIMA(0,1,1).And diagnostics are ok.but cant get clear values for the forecasting in r.",
"role": "user"
},
{
"message": "Your model says that differences in the observations are MA(1):$$ y_t-y_{t-1... | how to get forecast like zig zag type | stats | 2017-10-25T05:52:02.387 |
[
{
"message": "I am fairly new to statistics, so please forgive me for using probably the wrong vocabulary. I have a dataset of locations with measurements of soil carbon <code>SOC1mTHA</code>. I want to study the predictors that best explain <code>SOC1mTHA</code>, among 15 potential predictors. I have used the ... | Model selection with nonlinear predictor | stats | 2017-10-25T11:15:19.897 |
[
{
"message": "Let's say I have a set P of positive examples and a set N of negative examples.Prior to feeding this dataset to a SVM for training, should I remove duplicates in those sets?Intuitively, I don't think that showing several times the same example adds much information. While I understand it could cha... | Should we remove duplicates when training a SVM? | stats | 2017-10-26T06:13:16.270 |
[
{
"message": "I have collected linguistic data from one participant over seven months (one text a month) to explore lexical and syntactic development in second language writing. Her written samples were coded for type-token ratio (TTR) and dependent clause per clauses ratio (DC/C).TTR: (0.652, 0.579, 0.616, 0.5... | What statistical test should I use when the sample size is small (n=7)? | stats | 2017-10-26T07:58:54.243 |
[
{
"message": "Let $X_1,\\,X_2,\\ldots,\\,X_n$ be $n$ independent random variables, where $X_i\\sim\\text{N}(\\mu_i,\\,\\sigma_i^2)$, for all $i\\in\\{1,\\ldots,\\,n\\}$. Consider the $n$-dimensional random vector<br>$$\\boldsymbol{Y}_n=\\left(X_1,\\,X_1+X_2,\\ldots,\\,X_1+\\cdots+X_n\\right)^T$$I learned that $... | Efficiency of the command pmvnorm in R | stats | 2017-10-26T12:56:06.487 |
[
{
"message": "<a href=\"https://en.wikipedia.org/wiki/Likelihood_function#Example_1\" rel=\"noreferrer\">Example 1 of the wikipedia article on the Likelihood Function suggests that given the likelihood function $\\mathcal{L}(\\theta | X)$, we can find the probability of $\\theta$ given $X$, $p(\\theta|X)$.Is th... | Can you use Bayes theorem to transform a likelihood function into a probability of the parameters, given the data? | stats | 2017-10-26T13:48:19.647 |
[
{
"message": "Let us suppose we have following data<pre><code>x y1 52 43 54 45 7</code></pre>I would like to do Quantile regression in excel, I have found following information about given method<a href=\"https://i.stack.imgur.com/BB14U.png\" rel=\"nofollow noreferrer\">based on this informatio... | Estimation of quantile regression by hand | stats | 2017-10-26T17:21:30.147 |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.