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'm reading a book called soccernomics. There is data for Home/Away wins in case a penalty is awarded or not awarded in football (soccer) games. Data is as follows:<pre><code>| Result | Pen. Not Awarded | Pen. awarded | Total ||---------- |----------------- |------------- |------- ||... | How to find statistical significance? | stats | 2017-04-28T04:35:33.297 |
[
{
"message": "I am training a residual data with negative values through ANN. So I partition my data with 20 values for testing. But what I get in my MAPE is a negative value. Here is my data:<pre><code>ACTUAL PREDICT ABS ERROR MAE0.75580171 -0.007975448 0.763777158 1.010552303-0... | Compute MAPE with negative actual values | stats | 2017-04-28T04:49:57.367 |
[
{
"message": "I have two data sets ( source and target data) which follow the different distribution. I am using MMD - that is a non-parametric distance distribution- to compute marginal distribution between the source and target data. source data, Xstarget data, Xtadaptation Matrix A*Projected data, Zs = A'*Xs... | Maximum Mean Discrepancy (distance distribution) | stats | 2017-04-28T15:45:42.560 |
[
{
"message": "I'd really appreciate your help. Let's say I am using a mini-batch size of 4 playing an Atari game in the RL context. I understand that weights are updated only every 4 frames. But what does the RL agent do during the 3 extra frames? Does it do nothing and just wait? Does it take random actions? D... | Does the RL agent take no action during mini-batch? | stats | 2017-04-28T20:13:35.457 |
[
{
"message": "Let $X$ be a non-negative random variable, and let $Y \\sim \\chi^2_n / n$ (so that $E(Y) = 1$). $X$ and $Y$ are independent. Note that $X$ and $X\\cdot Y$ have the same mean, while $X\\cdot Y$ has larger variance. Is it true that for every $t > E(X)$, $$\\Pr(X > t) < \\Pr(X\\cdot Y > ... | Tails of products of random variables | stats | 2017-04-29T09:56:05.910 |
[
{
"message": "Let's say I'm simulating the result of a tournament where 4 teams play each other, for a total 6 games. They get, say, 1 point for winning and 0 points for loosing.I want to get a sense of the end distribution. For example, the probability that team B finishes at least third.The sample space is fi... | Convergence concept for MonteCarlo(?) simulation of a tournament | stats | 2017-04-30T11:47:20.367 |
[
{
"message": "I was wondering if I am understanding the following two points correctly:FIRST, I think a Likelihood function for $\\mu$ of a normal with a known $\\sigma$ can be turned into the sampling distribution of $\\bar{x}$ (sample mean), only using a scaling factor (a multiplicative constant applied to li... | (R code provided) one-on-one correspondence bet. shapes of sampling distribution and Likelihood function | stats | 2017-04-30T21:30:49.193 |
[
{
"message": "I have an object detection algorithm for which I would like to plot an ROC curve. For this, I need the values of the fall-out corresponding to values of recall.The false positive rate, or fall-out, is defined as$$\\text{Fall-out}=\\frac{FP}{FP+TN}$$In my data, a given image may have many objects. ... | How can I calculate the false positive rate for an object detection algorithm, where I can have multiple objects per image? | stats | 2017-05-01T10:45:23.913 |
[
{
"message": "I am fairly new to this, sorry if I am not clear.I have two models with logY. The first model has a slightly bigger sample than the second model and accounts for 4 main drivers (and some control variables). In the first model:<pre><code>X1 = significantX2 = significantX3 = significantX4 = insignif... | Variable becomes insignificant after including variable in multiple regression | stats | 2017-05-01T13:44:23.393 |
[
{
"message": "I have the following problem. I have 70 people, with a bunch of variable-data on each of them. What I also have, are 3 dissimilarity matrices, wherein the dissimilarity between each person and every other person is already computed. The goal is to cluster these people. 2 are euclidean distance mat... | Multiple paired distances in a single clustering application | stats | 2017-05-01T15:23:38.657 |
[
{
"message": "I have a time series regression that, given a set of lagged values, predicts all of the values from one step ahead to a given horizon. I'm trying to calculate the MASE for this, but am having a problem understanding how to apply it.My understanding is that the MASE is the ratio of the MSE to a sca... | Multi-input, multi-output time series regression loss using MASE | stats | 2017-05-01T17:52:35.963 |
[
{
"message": "<br>I found GANs very very powerfull and start reading the papres around it. This is the algoritm used in <a href=\"https://arxiv.org/abs/1406.2661\" rel=\"nofollow noreferrer\">The original paper to describe the steps of updating Descriminator and Generative parts of the network.I underestand tha... | Why update the D ascending in Generative Adversarial networks? | stats | 2017-05-01T18:25:37.760 |
[
{
"message": "Why I am getting different predictions for manual polynomial expansion and using the R <code>poly</code> function?<pre><code>set.seed(0)x <- rnorm(10)y <- runif(10)plot(x,y,ylim=c(-0.5,1.5))grid()# xp is a grid variable for plotingxp <- seq(-3,3,by=0.01)x_exp <- data.frame(f1=x,f2=x^2)... | Why I am getting different predictions for manual polynomial expansion and using the R `poly` function? | stats | 2017-05-01T18:41:36.527 |
[
{
"message": "I'm reading a textbook and I see this question:<a href=\"https://i.stack.imgur.com/cSeY7.jpg\" rel=\"nofollow noreferrer\">So there are 200 women, and the DF is 196, implying that the equation for DF is $n - k - 1$. There are 3 variables: bp, age, and type so $k == 3$.What's the intuition behind t... | Why are the Degrees of Freedom for multiple regression n - k - 1? For linear regression, why is it n - 2? | stats | 2017-05-01T20:54:57.440 |
[
{
"message": "I am trying to understand the logic behind forward-backward selection (even though I know that there are better methods for model selection). In forward model selection, the selection process is started with an empty model and variables are added sequentially. In backward selection, the selection ... | Forward-backward model selection: What is the starting model? | stats | 2017-05-02T15:08:11.957 |
[
{
"message": "I am have been wondering why people use Gaussian processes (GP) to model an unknown (sometimes deterministic) function. For instance consider an unknown function $y=f(x)$. We have three independent observations from this function :$$\\big(x_1,y_1); \\big(x_2,y_2); \\big(x_3,y_3) $$To learn the und... | Gaussian process and Correlation | stats | 2017-05-02T18:10:58.083 |
[
{
"message": "When we train a model, we usually use pairs of $(x_n,\\ label_n)$ as training data. In my case, I have pairs of $(x_n, \\ label_n)$ and also pairs of $(x_n,\\ wrong\\_label_n)$, where both $label$ and $wrong\\_label$ come from the same set of labels. Note: the wrong labels are known, not noise.Is ... | Training a model on samples with both correct and wrong (non-noise) labels | stats | 2017-05-03T10:26:25.923 |
[
{
"message": "I am using the <code>forecast</code> package in R to do ARIMA forecasting with <code>auto.arima()</code> function by Professor Hyndman.I have 27 months of sales data (June 2014 to August 2016), I'm using the first 21 months as training set, and the rest 6 months as test set.<pre><code>dataset <... | Validating ARIMA(1,0,0)(0,1,0)[12] with manual calculation | stats | 2017-05-03T12:32:39.493 |
[
{
"message": "Why do we need adjustment when applying Ljung-Box test over residuals? The following is from the Multivariate Time Series Analysis by R. Tsay. <pre><code>m1 = VAR(data.ts,p=2)resi=m1$residuals ### Obtain the residuals of VAR(2) fit.mq(resi,adj=18) ## adj is used to adjust the degrees of freedom.</... | Why do we need adjustment when applying Ljung-Box test over residuals? | stats | 2017-05-04T11:16:18.010 |
[
{
"message": "This question <a href=\"https://www.quora.com/What-is-an-intuitive-explanation-of-Monte-Carlo-simulations\" rel=\"nofollow noreferrer\">https://www.quora.com/What-is-an-intuitive-explanation-of-Monte-Carlo-simulations gives intuitive explanation for monte carlo : <blockquote> Another example I ra... | Is my interpretation of monte carlo correct? | stats | 2017-05-04T18:20:32.440 |
[
{
"message": "I would like to visualize a 2000*100 matrix to find how different variables change based on values.Can you suggest a way doing it using R or Matlab?I have data from patients who use an ECG device every night and through the night, the machine records several different variables as critical points.... | visualize a multi column matrix | stats | 2017-05-04T20:41:53.527 |
[
{
"message": "I am taking a look at :<a href=\"http://pages.cs.wisc.edu/~jerryzhu/cs731/kde.pdf\" rel=\"nofollow noreferrer\">http://pages.cs.wisc.edu/~jerryzhu/cs731/kde.pdfWhere they define the following loss function for kernel density estimates $$J(h) = \\int \\hat{f_n}^2(x)dx -2\\int\\hat{f_n}(x)f(x)dx$$wh... | Leave one out cross validation in kernel density estimation | stats | 2017-05-04T20:58:55.727 |
[
{
"message": "I have a covariance matrix and mean values(OMEGA) for a multidimensional Gaussian distribution (3-dim) as follows (respectively),<pre><code>COVAR = 1.0e-12 * 0.2498 -0.4832 0.2140 -0.4832 0.9543 -0.4456 0.2140 -0.4456 0.3245</code></pre... | If a multivariate Gaussian distribution is truncated what will be the new distribution? | stats | 2017-05-05T07:18:56.483 |
[
{
"message": "I want to think about $R^2$ as (in the context of forecasting with different models):$$\\frac{\\text{explained variance}}{\\text{total variance}} = 1 - \\frac{\\text{unexplained variance}}{\\text{total variance}} $$Total variance is calculated using:$$\\text{total variance} = \\frac{1}{n}\\sum_{i=... | Confusion about the meaning of unexplained variance in R2 interpretation | stats | 2017-05-05T09:47:21.960 |
[
{
"message": "When I run the least absolute deviation regression using command 'lad' from the 'L1pack' package, I get the following result but cannot determine the significance levels for each coefficients.<pre><code> Call: lad(formula = co[, 12] ~ co[, 2] + co[, 3] + co[, 5] + co[, 7] + co[, 8] + co[, 9] ... | least absolute deviation regression's coefficient significance levels | stats | 2017-05-05T17:47:47.867 |
[
{
"message": "I am using <code>scikit-learn</code>. I use the following to center the predictor features:<pre><code>X = sklearn.preprocessing.StandardScaler().fit_transform(X) </code></pre>I will use the following code to create the polynomial features:<pre><code>poly = PolynomialFeatures(degree=2)poly.fit_tr... | Calculating the polynomial features after or before centering the data? | stats | 2017-05-05T20:17:17.080 |
[
{
"message": "I need to obtain some sort of \"average\" among a list of variances, but have trouble coming up with a reasonable solution. There is an interesting discussion about the differences among the three Pythagorean means (arithmetic, geometric, and harmonic) in this <a href=\"https://stats.stackexchange... | "Averaging" variances | stats | 2017-05-05T23:10:26.280 |
[
{
"message": "From the question below, I require a regression model for the first part. To get the coefficients of regression, I used the correlation provided and the standard deviations to compute the co-variance.I then computed the slope by dividing the Co-variance with the variance of the independent variabl... | Performing regression given correlation, standard deviations and mean | stats | 2017-05-06T02:38:40.010 |
[
{
"message": "My variable represents the outcome of a mock-election, between three different parties(so categorical). My hypothesis is that with the information presented to the subjects, a majority will vote for party A. A simple frequency table shows that indeed most subjects (75 percent) voted for party A. D... | Significant majority | stats | 2017-05-06T11:17:08.720 |
[
{
"message": "\"Most applications of the SOM are based onregular arrays of nodes. Sometimes one uses rectangular arrays ofnodes for simplicity. However, the hexagonal arrays are visuallymuch more illustrative and accurate, and are recommended.Whatever regular architectures are used, it is advisable to selectthe... | Lengths of principal components to determinate SOM grid | stats | 2017-05-06T12:44:44.087 |
[
{
"message": "Fundamental questionWhen you do PCA (or any dimensionality reduction), what is \"the number of dimensions\"? I always thought that the thing you measure (ie, the variable) is the number of dimensions: eg, if you measure the length, width, height of a box, that's 3 dimensions (3 variables); if you ... | When you do PCA (or any dimensionality reduction), what is "the number of dimensions"? | stats | 2017-05-06T14:39:47.307 |
[
{
"message": "Expected Prediction Error in a linear model is defined as follows:$E[\\sum_i (y^*_i-\\hat{y_i})^2] = E[\\sum_i (y_i-\\hat{y_i})^2] + 2\\sum_i Cov(y_i,\\hat{y_i})$where $y_i$ are the training values, and $y^*_i$ are the test values (Proof <a href=\"http://amstat.tandfonline.com/doi/abs/10.1080/0162... | Minimizing Expected Prediction Error | stats | 2017-05-06T21:02:07.307 |
[
{
"message": "I am working on a project where I need to analyze the relationship between two variables (correlation, regression, anything that helps to understand what is the nature of the relationship).From the following source I understood I should first calculate skewness and if the skewness value is over +-... | When should I perform transformation when analyzing skewed- data? | stats | 2017-05-07T01:23:41.047 |
[
{
"message": "Hi I have a slight problem understanding somethingVariable X is a 0/1 dummy Where 1 = variable x is highThe hypothesis is that: If variable X is high; individuals are happier.This is true in my complete sampleThen the sample was split in 2 (District A and District B) The hypothesis holds for Distr... | Interpretation of a regression result | stats | 2017-05-07T10:18:30.850 |
[
{
"message": "In biological investigations, you need to control many different variables, but there are obviously some variables which we don't bother monitoring even if they are easy, such as age. I've been wondering why we control variables and why we leave some out. It always seems like there is going to be ... | Is controlling variables important in deducing a statistically significant correlation? | stats | 2017-05-08T05:52:07.890 |
[
{
"message": "I am using K-Means in order to cluster a population based on 5 variables into 2 groups. I am then using both tSNE and PCA to visualise the outcome to somehow better understand the separation.What is confusing me is that PCA shows a reasonably nice separation of the data whilst tSNE does not show t... | PCA vs tSNE after k-means clustering: some separation on the PCA plot but no separation on the tSNE plot | stats | 2017-05-08T09:42:08.603 |
[
{
"message": "This empirical study I am trying to replicate (ch5 Becker et al (2015) : Selecting Volatility Forecasting Models for Portfolio Allocation Purposes) has used 2500 in-sample-period's actual daily returns to calculate one-step-ahead DCC GARCH covariance matrix. I have been able to do this successfull... | Rolling period volatility forecasts | stats | 2017-05-08T11:16:55.827 |
[
{
"message": "Reading <a href=\"https://github.com/tensorflow/magenta/blob/master/magenta/reviews/GAN.md\" rel=\"nofollow noreferrer\" title=\"here\">here, I found:<blockquote> If the discriminator wins by too big a margin, then the generator can’t learn as the discriminator error is too small.</blockquote>Th... | GAN: why is too-good discriminator supposed to provide "small error"? | stats | 2017-05-08T11:30:36.750 |
[
{
"message": "In my bivariate regression model, I log-transformed the dependent variable. and the mean is now 2.77. and I got -0.186 for coefficient.Could anyone tell me the interpretation of 2.77 here? and how can it compare with -0.186?",
"role": "user"
},
{
"message": "Before going into the detai... | What does average of log-transformed variable mean? | stats | 2017-05-08T12:09:48.490 |
[
{
"message": "I'm not sure about the right terminology, but here goes.I have a questionnaire measure (30 likert-items) that has been traditionally divided into five six-item factors. Each factor has two different types of items, which represent two different approaches to formulate the questions (basically, one... | (solved: method factor) Does low cross-type covariances (compared to within-type cross-factor) imply a bad measure? | stats | 2017-05-08T13:35:49.747 |
[
{
"message": "We have an equation with $\\alpha =0$ therefore the simple linear regression is: $$ Y_i=\\beta X_i+u_i$$ and the question was. Derive the OLS $\\beta $ and provide comments on its variance. In this situation should I have derived the OLS the same way as for a regression with intercept? to obtain $... | Is the derivations of OLS different if we do not have an intercept? | stats | 2017-05-08T16:36:19.443 |
[
{
"message": "SVM with gaussian kernel (RBF kernel) have infinite VC-dimension and the VC-dimension for SVM with polynomial kernels is very big too. Thus, I wonder how is possible that SVM have good generalization performances. In SRM (structural risk minimization) as larger is the VC dimension as larger is the... | Structural risk minimization in SVMs | stats | 2017-05-08T16:39:02.910 |
[
{
"message": "I am trying to select a regression model for datasets with a right-skewed outcome and where \"outliers\" are present (where outliers are very high values due to the nature of the data). The data are time-sensitive so for model building I am splitting the dataset in train and test sets based on tim... | Error metric for regression with right-skewed data and outliers | stats | 2017-05-08T18:04:38.990 |
[
{
"message": "Will the estimates and odds ratios change for an independent variable if it is by itself vs if there are other independent variables? I would think that it would change since thinking of it as an equation $y=x$ (one variable) is different than $y=x+z+q$ (3 variables).",
"role": "user"
},
... | Logistic Regression with Multiple Independent Variables vs One Independent Variable | stats | 2017-05-08T21:29:38.340 |
[
{
"message": "I was searching regarding Poisson process and dat lay out for recurrent event. After diving into heap of literature its better that I should ask to someone. What steps should we take to write parametric maximum likelihood for recurrent event for Poisson process for Weibull PH model when covariates... | Regression method for Poisson Process | stats | 2017-05-08T22:47:47.217 |
[
{
"message": "<a href=\"http://mlg.eng.cam.ac.uk/zoubin/papers/iMGPE.pdf\" rel=\"nofollow noreferrer\">A paper that I am reading mentions the likelihood for a squared-exponential-kernel Gaussian Process with no data. In particular, when the kernel function is:$$F(x_i, x_{i'}) = v_0\\exp\\Big(-\\frac{(x_i - x_{i... | Likelihood for a Gaussian Process with no data | stats | 2017-05-09T09:37:17.423 |
[
{
"message": "Suppose that I have a multivariate random walk:$X_{t+1} = X_t + \\epsilon_t$ where $\\epsilon_t \\sim N(0,\\Sigma)$Estimating the covariance matrix $\\Sigma$ is straightforward from first differences $X_{t+1}-X_t$ using the sample covariance.Instead if I would like to estimate the covariance direc... | Estimating Covariance Matrix of Innovations of Multivariate Random Walk | stats | 2017-05-09T18:18:33.200 |
[
{
"message": "I would like to evaluate the predictive performance of my mixed effects logistic regression model using package lme4 (glmer). My model is as follows: <code>glmer(R0A1~MP_Scaled+MPHW_Scaled+HW_Scaled+YP_Scaled+AG_Scaled+SS_Scaled+PR_Scaled+SR_Scaled+(1|Animal_ID)+(1|Year),data=males, family=binomia... | K-fold cross validation for hierarchical data sets in a mixed effects framework (glmer) | stats | 2017-05-09T20:54:01.563 |
[
{
"message": "I am new to statistical significance testing and i am wondering how the confidence level is set.If for example I am conducting a test to prove that my method is better than an existing one, and i fail to reject the null hypothesis with a confidence interval of 95%, is it allowed to go back and low... | Adjusting the confidence level after the experiment | stats | 2017-05-09T21:56:14.417 |
[
{
"message": "I read about a so-called \"Kahn Pseudo Normal\" distribution in a <a href=\"http://www.hpmuseum.org/forum/thread-7440-post-65971.html\" rel=\"nofollow noreferrer\">forum post.It says when $U$ is uniformly distributed over $[0,1]$, then $\\log(1/U-1)$ is approximately normal distributed, that is<bl... | Kahn Pseudo Normal distribution | stats | 2017-05-09T23:46:29.413 |
[
{
"message": "I been trying to automate, using python, a PCA which is achieved using SPSS.This is my code:<pre><code>import numpy as npdata = np.genfromtxt('input.csv', delimiter=';', usecols=range(0, 6))data = data.Tdata /= np.linalg.norm(data)corrmat = np.corrcoef(data)eigenvalues, eigenvectors = np.linalg.ei... | How to calculate "factor coordinates" for PCA in Python, to match SPSS output? | stats | 2017-05-10T14:49:34.000 |
[
{
"message": "i have two different weather forecasting systems. Each system returns values between 0 and 30 degrees. In addition i have a grounded truth set containing the real temperature values. Now i want to find the optimal mix of both systems using an optimization (i.e minimize):$$ \\sum_{d=1}^D \\big|t_d-... | Optimization of Mean Absolute Error with regularization | stats | 2017-05-11T11:49:17.100 |
[
{
"message": "Suppose I have the covariance and correlation matrices for several variables. I know one of the variables is almost a linear combination of the others. Is there any characteristic about the corresponding row in the covariance (correlation) matrix that I can use to pick out this variable?",
"ro... | Know which variables are linear combinations of others from covariance (correlation) matrix | stats | 2017-05-11T15:20:20.207 |
[
{
"message": "I want to compare two Weibull distributions fitted to two different datasets. Both datasets have a distribution that resembles the Weibull so the idea was to compare the fitted Weibull distributions to conclude whether the difference in the distribution of the two datasets is statistically signifi... | Compare two Weibull distributions | stats | 2017-05-11T18:01:45.553 |
[
{
"message": "I am estimating the probability for an event to happen based on certain criteria prior to the event. The event either happens or does not happen (1 or 0). I have a few hundred thousand such pairs of 1) prior estimation in % and 2) 1/0 (happens/does not happen).My question is: What is the best scie... | How to see how good my probability estimations are? | stats | 2017-05-11T20:40:25.057 |
[
{
"message": "X and Y are continuous variables.I have found a relationship between X and Y.Now I want to know if that relationship is characteristic of all of X. Is it possible to somehow examine that relationship at different points along X?In actuality, X was entered on the final step of a hierarchical regres... | How can I check if the relationship between X and Y holds at various points along X? | stats | 2017-05-12T00:32:48.343 |
[
{
"message": "X and Y are continuous variables.I have found a relationship between X and Y.Now I want to know if that relationship is characteristic of all of X. Is it possible to somehow examine that relationship at different points along X?In actuality, X was entered on the final step of a hierarchical regres... | How can I check if the relationship between X and Y holds at various points along X? | stats | 2017-05-12T00:32:48.343 |
[
{
"message": "I've read that Random Trees do not require cross validation as it's implicitly integrated into the forest growing algorithm.I'm using Scikit's ExtraTreesRegressor on about 15K rows and 300 columns, split into 85% training data and 15% test data.The test results I obtain are quite satisfying but va... | Cross validation in ExtraTreesRegressor | stats | 2017-05-12T09:46:58.013 |
[
{
"message": "How are the implied values and their standard errors calculated here? Thank you in advance.<a href=\"https://imgur.com/a/3dMdx\" rel=\"nofollow noreferrer\">http://imgur.com/a/3dMdxEditWe have this production function with $\\alpha+\\beta<1$.$Y=K^{\\alpha}H^{\\beta}(AL)^{1-\\alpha-\\beta}$$Y$ o... | Calculating implied values of a model | stats | 2017-05-12T18:01:49.770 |
[
{
"message": "I am doing my undergraduate thesis, and I wonder if I need to do the Cronbach's alpha from my data set, or if I should use the Cronbach's alpha from the commercial questionnaire I will use for this paper. What is the standard way to approach this?",
"role": "user"
},
{
"message": "The ... | When to calculate Cronbach's alpha for a paper? | stats | 2017-05-13T01:19:39.440 |
[
{
"message": "I am trying to understand gradient descent algorithm by plotting the error vs value of parameters in the function. What would be an example of a simple function of the form y = f(x) with just just one input variable x and two parameters w1 and w2 such that it has a non-convex(has multiple minima) ... | Non-Convex Loss Function | stats | 2017-05-13T03:23:46.863 |
[
{
"message": "After trying to do som e cross validation i got some models that fitted the data fairly good but predicted them horribly (eg. fitted = [10001.543,10034.324,104023.23..], true value = [10001,543,10034,104023] and predicted = [10.22,9.44,11.323...])For you who is a bit more experienced than i am, Ho... | prediction vs fitted values | stats | 2017-05-14T20:13:01.147 |
[
{
"message": "Currently, I designed a neural network with one hidden layer, with cross entropy cost function and softmax activation function to predict the outcome of a tennis game.The input is a matrix, where each row is a training data, each column is a variable. These features are having very different units... | How do I standarize input data for a neural network? | stats | 2017-05-15T05:02:30.393 |
[
{
"message": "I have several independent variables & one dependent variable for a regression model.One of these IVs have a much better curve fit (with the DV) as quadratic regression.I was thinking about transforming the IV (by squaring it) and then adding both the IV and its squared value in the multiple l... | Can I include a quadratic regression in a linear model? | stats | 2017-05-15T20:37:50.630 |
[
{
"message": "Recently, I was tasked with a sample size calculation for a study in which the outcome is to be modeled using a Poisson regression (i.e. a generalized linear model). For quick and simple calculations of this nature, I often use PASS, a statistical software package dedicated to power/sample size ca... | Sample Size for Poisson Regression | stats | 2017-05-15T21:15:22.387 |
[
{
"message": "I've just started with machine learning. I managed to build logistic regression model with 10 features. All features are feature scaled and centered around 0. Train/test ratio is around <code>0.3</code>.My code in Python:<pre><code># Training setimputer_train = Imputer(missing_values='NaN', strate... | Logistic regression - Empty test sample doesn't return probability of 0.5 | stats | 2017-05-16T08:51:09.723 |
[
{
"message": "I have data from an experiment with three groups A, B and C (categorical variable) and I want to show that the groups are homogenous regarding the distribution of the age (discrete variable) of the participants in the three groups.Which test do you recommend to use? Would it be ok to report that I... | Test of independence of a discrete variable and a categorial variable | stats | 2017-05-16T10:52:23.777 |
[
{
"message": "In the case of supervised classification, we wish to predict the label of unseen observation $x\\in\\mathcal{X}$ by assigning it to some label $y \\in \\mathcal{Y}$. Specifically, we want to find label $y^*$ as follows:$$\\begin{split}y^* &= \\underset{y\\in\\mathcal{Y}}{\\text{arg max}\\;} \\... | In courts, should we assume that $\Pr(Y=y)$ is constant, for all $y \in \mathcal{Y}$? | stats | 2017-05-18T04:14:47.143 |
[
{
"message": "I have been given a task to solve using a neural network and I think that using a neural network is the wrong algorithm to use. The idea is simple: given at most 3 diagnoses, predict which medication(s) a health professional will prescribe. The main issue is that each diagnosis can have many valid... | Neural networks that predict more than one class as being correct | stats | 2017-05-18T04:39:17.490 |
[
{
"message": "I would like to know if it is possible to use items with different scales to compute a single variable. For example for the variable \"authonomy\" I would like to include 4 items for the variable computation. Three questions are with yes/no answer, e.g., \"Are you able to choose your methods of wo... | Is it possible to compute a variable using items with different scales? | stats | 2017-05-18T10:50:19.173 |
[
{
"message": "I refer you to Breiman's paper <a href=\"http://projecteuclid.org/euclid.ss/1009213726\" rel=\"nofollow noreferrer\" title=\"Statistical Modeling - A Tale of Two Cultures\">Statistical Modeling - A Tale of Two Cultures where he illustrated some examples of descriptive modelling. Under section 11.1... | Purpose of leave-one-out cross-validation in descriptive modelling | stats | 2017-05-19T05:18:48.027 |
[
{
"message": "I have a time series that deals with rainfall. It is a period of 10 years (daily resolution), and covers climate variables.I'm going to feed the data into an Artificial Neural Network to predict the rainfall variable (PP).As what I've been reading, MAPE's formula involves dividing by the actual ob... | Is MAPE a good error measurement statistic? And what alternatives are there? | stats | 2017-05-19T08:17:06.500 |
[
{
"message": "If I have two binary variables, I can determine the similarity of these variables quite easily with different <a href=\"https://www.ibm.com/support/knowledgecenter/SSLVMB_20.0.0/com.ibm.spss.statistics.help/syn_proximities_measures_binary_data.htm\" rel=\"nofollow noreferrer\">similarity measures,... | Similarity measures for more than 2 variables | stats | 2017-05-19T10:09:56.807 |
[
{
"message": "I am optimizing the XGBoost. I would like to know if I need to tune L1 or L2. They seem to be useful in linear models to avoid overfitting, but I am working with trees (so I take care of max depth to avoid overfitting). My dataset is multiclass.",
"role": "user"
},
{
"message": "It is ... | Do L1 and L2 needed in trees optimization? | stats | 2017-05-19T13:56:44.773 |
[
{
"message": "I'm new to data science, and am working on projects to develop my skills. I'm currently working on the <a href=\"https://datahack.analyticsvidhya.com/contest/practice-problem-loan-prediction-iii/\" rel=\"nofollow noreferrer\">Loan Prediction practice competition offered by Analytics Vidhya.The goa... | Need help with Feature Engineering | stats | 2017-05-19T18:03:18.270 |
[
{
"message": "Given a pseudo-random number generator of standard normal distribution, I generate a matrix $(z_{t,n})_{(t,n)=(1,1)}^{(T,N)}$ of samples. I computed the mean of the cumulative sum, i.e., $\\displaystyle s_t = \\frac1N\\sum_{n=1}^N\\sum_{s=1}^tz_{s,n} $. The expected standard deviation of $s_t$ sho... | Is cumulative sum large deviation an alarm for bad normal pseudo-random number generator? | stats | 2017-05-19T18:51:15.367 |
[
{
"message": "At first, this question is less about programming itself but about some logic behind the CNN architecture. I do understand how every layer works but my only question is: Does is make sense to separate the ReLU and Convolution-Layer? I mean, can a ConvLayer exist and work and update its weights by ... | CNN Architecture | stats | 2017-05-21T10:19:57.043 |
[
{
"message": "I am analyzing data from a cluster randomized cross over trial. There are 9 clusters and 3 periods in the data. The clusters are dental clinics and in each period different patients are sampled. I have three interventions (control, treatment1, treatment2).Each cluster receives all three interventi... | Analysis of a cluster crossover design | stats | 2017-05-21T18:22:19.107 |
[
{
"message": "My lab uses what our PI calls \"modified Bland–Altman plots\" to analyze regression quality. I'd like to know what the generally used name is for these plots.A <a href=\"https://en.wikipedia.org/wiki/Bland%E2%80%93Altman_plot\" rel=\"nofollow noreferrer\">Bland–Altman plot compares the difference ... | Proper name for "modified Bland–Altman plot" | stats | 2017-05-22T04:52:03.243 |
[
{
"message": "Alright, I am training an xgboost model, that should give the probability of questions being duplicates (having the same intent). My train dataset is 70 MB; each column has a question pair and a boolean saying if the questions are duplicates (1 - duplicates, 0 - no); the set has 40% duplicates. I ... | Xgboost making bad predictions | stats | 2017-05-22T16:22:40.073 |
[
{
"message": "I have run a logit model such that $Y$ ~ $X$, where $X$ is a categorical variable with 4 alternatives. I have dummy coded $X$ so I can perform regression, this means that category 1 is the base category. I would like to compare the probability of each alternative $X$ including the base category. T... | Logit model probabilities categorical variable | stats | 2017-05-23T08:46:34.127 |
[
{
"message": "I have some linguistics categorical data to analyse. There are 5 speakers (M1-M5), and they read out certain words. The words are 200 in number, but speakers only read out the words if they understand its meaning. They are shown in random order with other filler words. The speakers produce sounds ... | Which test to use for statistical significance? | stats | 2017-05-23T09:45:45.233 |
[
{
"message": "I was wondering, if I perform linear OLS regression with stationary (verified) time series $y_t$ on $x_{1t}$,$x_{2t}$:can the residuals be non-stationary?it is not part of a list of Gauss-Markov assumption that the residuals of the OLS linear regression must be stationary so we usually don't need... | Non stationary residuals from stationary regression | stats | 2017-05-23T11:07:34.583 |
[
{
"message": "I am trying to hand calculate the standard error for the a path in a moderated mediation model where the moderator modifies the a path. For example:Mediator = X + Moderator + X*MI gather that the a path would be calculated like so (with coefficients from the above model): X + (X*M * Moderator)How ... | Calculating SE for a path in Moderated Mediation | stats | 2017-05-23T15:52:10.483 |
[
{
"message": "Suppose we are building an \"early warning system\", that will output a risk score every month over 1 year, say Jan. to Dec..The tricky part is that number of available variables/columns will be different (increase over time). For example, at beginning (Jan.), we only have $5$ features/columns for... | How to build a model (or a set of models) when number of independent variables (features) are changing over time? | stats | 2017-05-23T17:26:51.113 |
[
{
"message": "Suppose we are building an \"early warning system\", that will output a risk score every month over 1 year, say Jan. to Dec..The tricky part is that number of available variables/columns will be different (increase over time). For example, at beginning (Jan.), we only have $5$ features/columns for... | How to build a model (or a set of models) when number of independent variables (features) are changing over time? | stats | 2017-05-23T17:26:51.113 |
[
{
"message": "I have a few multiple sequence alignments and a few groups (let's say N) of unaligned sequences. I would like to learn the emission and transition probabilities from the multiple sequence alignments, to build with these distributions a profile HMM and then to produce with the Viterbi algorithm N m... | Produce Multiple Sequence Alignments using Profile HMMs | stats | 2017-05-23T17:39:30.630 |
[
{
"message": "Least Squares Approximation (LSA) for Unifed Lasso (Wang, Leng 2007) mentions Least Angle Regression (LAR) several times. Here's a <a href=\"http://www.stat.nus.edu.sg/~stalc/LSA.pdf\" rel=\"nofollow noreferrer\">direct link to the paper.Specifically, in Section 4 they say: <blockquote> All studi... | How are Least Angle Regresson (Efron 2004) and Least Squares Approximation for United Lasso (Wang, Leng 2007) related? | stats | 2017-05-23T19:39:27.157 |
[
{
"message": "In R, the function <code>chisq.test</code> has an option <code>simulate.p.value</code>. In the help page little explanation is provided but it reports to <a href=\"http://www.jstor.org/stable/pdf/2984263.pdf?refreqid=excelsior%3Aa75f32ab2d89a004c081ce5799393341\" rel=\"nofollow noreferrer\">Hope (... | Simplified Monte Carlo procedure in Chi square test | stats | 2017-05-24T01:15:07.290 |
[
{
"message": "I see that if I repeatedly try following 2 commands, the biplots remain the same: <pre><code>pc <- prcomp(iris[-5], scale=TRUE)biplot(pc)</code></pre>and:<pre><code>pc <- princomp(iris[-5], cor=TRUE)biplot(pc)</code></pre>However, if I try following code of robust PCA (taken from help text o... | Why robust PCA is giving varying output and how to stabilize it? | stats | 2017-05-24T07:14:49.120 |
[
{
"message": "I am currently writing a seminar paper where I among other things conduct a Wilcoxon rank-sum test. The sample size is very small, so I don't have any significant results. My professor thought it might be interesting to calculate the sample size that would be sufficient for a 5%-signifance level a... | Sample size calculation Wilcoxon rank-sum test | stats | 2017-05-24T12:35:44.427 |
[
{
"message": "I have trouble picking an appropriate statistical evaluation method for my experimental data.A number of reliable participants perform a binary categorization task over n phrases. For each data point I end up with $x$ \"0\" votes, and $(n-x)$ \"1\" votes. Now I need a measure that helps me decide ... | Method for evaluating categorization task | stats | 2017-05-24T20:42:27.353 |
[
{
"message": "I observe things so that, during an observational session, I develop a probability density function $f(x)$ describing the likelihood that $x$ is equal to different real numbers. I have $n$ of these observed probability function $[f_1,f_2,\\dots,f_n]$. All of these observations seem equally valid t... | Combine three equally likely observed PDFs describing carrot sizes in a carrot farm | stats | 2017-05-25T03:23:04.207 |
[
{
"message": "I have monthly price data for a commodity from 2007 to 2017. You can find it in the following link:<a href=\"https://drive.google.com/open?id=0BxRCOgKAL4itcUZlOExrUmVOanc\" rel=\"noreferrer\">https://drive.google.com/open?id=0BxRCOgKAL4itcUZlOExrUmVOancI need to forecast it using Seasonal ARIMA mo... | Seasonal ARIMA Modelling in R | stats | 2017-05-25T13:19:47.547 |
[
{
"message": "I am a PhD student. I have a data set (waiting time in minutes between tweets) which looks almost symmetrically to the naked eye. I've tried a couple of distribution fits to this data and the closest I can get is a cauchy distribution with a p value = 0.02. I'd like to see if the data is a reason... | How to fit a data against a Laplace / Double Exponential Distribution (and check GoF) | stats | 2017-05-25T15:59:08.137 |
[
{
"message": "Main Question:I am wondering why my completion time data for trials is not as skewed as the completion time for the tasks that makeup the trial? Details:I am comparing two user interfaces on task completion time. The participants were given a set of tasks to complete with UI-A and the same set of ... | Trial Completion time is not right skewed but it should be | stats | 2017-05-25T17:49:30.477 |
[
{
"message": "To gain an understanding of BPTT, I'm attempting to derive the formulas for BPTT by hand, but keep getting stuck. Here's what I have so far.Forward Pass 1$a_0 = x_0 * u_0$$b_0 = s_{-1} * w_0$$z_0 = a_0 + b_0$$s_0 = func_0(z_0)$ (where $func_0$ is sig, or tanh)Foward Pass 2$a_1 = x_1 * u_1$$b_1 = s... | How to derive BPTT algorithm | stats | 2017-05-25T19:06:50.123 |
[
{
"message": "On homework assignment I was asked to match different r values (namely $1$, $0.7$, $0.4$, $0$, $-0.4$, $-0.7$, $-1$ and \"r value not defined\") with some graphs. Among the graphs there were funny looking ones (can be found below) and the \"weird\" shape, I think, hints at the \"not defined\" opti... | Does the correlation coefficient, r, for linear association always exist? | stats | 2017-05-25T23:14:24.570 |
[
{
"message": "For my class project I am comparing various tree-based ensemble methods such as bagging, boosting, random forest, and AdaBoost against my data set and I can't quite determine my methodology. I know that I would like to initially explore the parameter space for each model; varying parameters such a... | How to validate a model when first exploring model hyperparameter space? | stats | 2017-05-26T21:42:38.607 |
[
{
"message": "I have a bunch of data (over a million cases) with a few variables. One of these variables classifies the data into one of two groups: premature and mature. I want to develop some statistical technique/function so that when I am given new cases whose group is unknown (premature or mature), I can u... | What is the best statistical method for assigning cases to one of two groups? | stats | 2017-05-27T12:57:41.807 |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.