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": "Let's say I have a model which separates two classes with an SVM. Let's take a point from each of the classes. If two points have lower distance can this be interpreted as 'The model assumes these points are 'd' similar to each other ( low distance = high similarity )'. If yes, to what degree and ... | Can SVM distance be used as a measure of similarity? | stats | 2017-10-26T20:54:27.490 |
[
{
"message": "Recently, I came across an <a href=\"http://rsos.royalsocietypublishing.org/content/2/8/150266\" rel=\"nofollow noreferrer\">article that claims shorter titles of scientific articles tend to result in a greater number of citations, implying concise titles are better. While this sounds plausible, t... | Looking at the top X% of a population | stats | 2017-10-27T03:17:24.867 |
[
{
"message": "My Multiple Linear Regression equation is (I had log-transformed swim beach E. coli and canal E. coli for the MLR since the data were not normal): (LN)Swim Beach E. coli = 2.4 + 0.43 * Reservoir Level Change (in/day) + 0.29 *(LN) Canal E. coliI'm now trying to use that equation to predict swim bea... | Multiple linear regression back-transformations | stats | 2017-10-27T15:45:16.200 |
[
{
"message": "Given a point $x$ lying on the surface of a n-sphere $S$, what is an efficient way of randomly sampling points $x_k \\in S$ such that their distance from $x$ is at most $r$? ($\\|x-x_k\\| < r$)Can this be done uniformly?I have efficient ways of converting cartesian coordinates to n-spherical ... | How to sample uniformly points around a neighborhood of a point lying on a n-sphere? | stats | 2017-10-27T17:57:11.333 |
[
{
"message": "How can I deal with the Reinforcement learning problem with a fixed length episode but no terminal state?Can I use the same method as the normal reinforcement learning with terminal state?",
"role": "user"
},
{
"message": "You must define the states to match the learning objective you ... | How can I deal with the Reinforcement learning problem with a fixed length episode but no terminal state? | stats | 2017-10-27T22:53:42.907 |
[
{
"message": "I have been given two tasks 1.) predict future sales, 2.) explain what factors influence sales.The way I am solving the prediction part is to use forecasting as taught by <a href=\"http://otexts.org/fpp2/\" rel=\"nofollow noreferrer\">Rob Hyndman. This seems straight forward to me. What is more di... | What model is best for explaining variation? | stats | 2017-10-28T19:57:08.337 |
[
{
"message": "I want to model a stock's volatility with a proxy variable. Consider a standard GARCH(1,1) model:$$\\sigma^2_t=a+b \\sigma^2_{t-1}+c r^2_{t-1}.$$Classically, $r_{t}$ is the return of the stock at time $t$. Instead of return of stock, I want to use a proxy variable. Let define it as $p$. So the mod... | Volatility modelling with proxy variable using rugarch package in R | stats | 2017-10-29T08:14:15.113 |
[
{
"message": "<a href=\"https://en.wikipedia.org/wiki/Negative_binomial_distribution\" rel=\"nofollow noreferrer\">Negative binomial (NB) distribution is defined on non-negative integers and has probability mass function$$f(k;r,p)={\\binom {k+r-1}{k}}p^{k}(1-p)^{r}.$$ Does it make sense to consider a continuous... | Continuous generalization of the negative binomial distribution | stats | 2017-10-29T22:47:34.977 |
[
{
"message": "I'm trying to predict the prices of Airbnb's given some of their attributes using a very simple linear regression model.Despite obtaining a median absolute error of around 24 euros on the training and testing set which I'm happy with, when I plot the residual error there's a lot of large outliers.... | Dealing with outliers with Linear Regression | stats | 2017-10-30T09:55:41.760 |
[
{
"message": "I'd like to classify a set of 3d images (MRI). There are 4 classes (i.e. grade of disease A, B, C, D) where the distinction between the 4 grades is not trivial, therefore the labels I have for the training data is not one class per image. It's a set of 4 probabilities, one per class, e.g.<pre><cod... | Multilabel Classification with scikit-learn and Probabilities instead of Simple Labels | stats | 2017-10-30T17:00:36.873 |
[
{
"message": "I'm doing partial least squares regression (PLSR), using the df below, to investigate how to predictors (catchment characteristics) influence the dependent (nitrogen in the river). In this data.frame, all predictors are areal percentage (percent of the variable in the study area) except hydrology ... | Magnitude and direction of relationship between predictors and dependent in regression | stats | 2017-10-31T04:58:29.987 |
[
{
"message": "I have a time series, non-stationary with diff(1). Here the tests:<pre><code># Augmented Dickey-Fuller Test Unit Root / Cointegration Test # The value of the test statistic is: -5.0157 # KPSS Unit Root / Cointegration Test #The value of the test statistic is: 0.3134 # Phillips-Perron Unit Root / C... | Arima forecasting = 0 (for any t > 2) | stats | 2017-10-31T09:41:52.247 |
[
{
"message": "In Freedman's Statistics (chapter 2), the author uses Berkeley's admission statistics (that 44% men and 35% women were admitted to graduate programs in general) to illustrate Simpson's paradox: the difference in overall admission rate per gender could be explained by different application rates to... | Intuition needed when using weighted average to explain Simpson's paradox | stats | 2017-10-31T13:19:42.630 |
[
{
"message": "I don't quite get how random forests feature selection works. I know this idea of looking at how much the tree nodes that use the feature reduce impurity (say Gini). I need a more detailed explanation for the case of one tree and then for random forests. Please, would you mind explaining it to me?... | Random forests feature selection | stats | 2017-10-31T13:51:56.127 |
[
{
"message": "I am constructing classification trees for the first time, so I'm quite new to this use of R.I have observations of behaviours and incoming data that has to be classified as one of these behaviours. Using the rpart package, I was able to construct a tree:<pre><code>Tree <- rpart(formula = behav... | Classification in R - seperate category for uncertain classifications | stats | 2017-10-31T15:08:02.753 |
[
{
"message": "Imagine I have <code>X_train</code>, <code>y_train</code> and <code>X_test</code>, <code>y_test</code>.I was studying neural networks and so I came up with the following strategy, however I don't know whether it is considered overfitting or not.Create Neural Network number 1, call it NN1.a.) Train... | Does this strategy work or is it considered overfitting? | stats | 2017-10-31T16:07:43.127 |
[
{
"message": "I have some data which had to be logged and differenced once to induce stationary. I ran the Johansen test for cointegration and found that it is present in my data set.Does this fact tell me that using a VECM is more appropriate than using a VAR, despite of data now no longer being I(1)?",
"... | Does existance of Cointegration mean that VECM is preferred to VAR? | stats | 2017-10-31T16:43:30.487 |
[
{
"message": "Please forgive my ignorance, however I would like to explain this problem and get some advice on how to approach it.Let's say that I have the following training inputs, where <code>word</code>, <code>x</code>, and <code>y</code> are the data, and <code>class</code> is the classification that the d... | What is the best machine learning approach for this problem? | stats | 2017-10-31T17:27:34.383 |
[
{
"message": "A simultaneous confidence band denotes the probability $$p \\big(\\hat{f}(x) - w(\\hat{f}(x)) \\le f(x) \\le \\hat{f}(x) + w(\\hat{f}(x)) \\ \\ \\forall x \\big)=1-\\alpha$$where $f$ a function of $x$, $\\hat{f}$ and estimator for the value of $f$ at $x$, and $w(\\hat{f}(x))$ an estimated interva... | Is there a Bayesian analogue to a simultaneous confidence band? | stats | 2017-10-31T20:55:08.367 |
[
{
"message": "According to the table of conjugate distributions on <a href=\"https://en.wikipedia.org/wiki/Conjugate_prior#Table_of_conjugate_distributions\" rel=\"nofollow noreferrer\">Wikipedia, the hypergeometric distribution has as conjugate prior a beta-binomial distribution, where the parameter of interes... | beta-binomial as conjugate to hypergeometric | stats | 2017-10-31T21:30:08.077 |
[
{
"message": "I am using the lme4 package with R and would like to allow the intercept to vary with my fixed effects to allow for a proper fit, so basically I assume my random effects would follow this:(1 | g1/g2) with the alternative (1 | g1)+(1 | g1:g2) In my case my full model would be:<pre><code>lmer(signa... | If I have a Linear mixed effects model (lmer) that allows for the Intercept to vary among g1 and g2 within g1. Can g2 also be a fixed effect? | stats | 2017-11-01T07:13:41.513 |
[
{
"message": "I'm in the middle of reading a book <a href=\"http://otexts.org/fpp2/\" rel=\"nofollow noreferrer\" title=\"Forecasting: Principles and Practice\">Forecasting: Principles and Practice and simultaneously trying to code \"by hand\" all the things, for better understanding.I've found something that I... | Estimation of AR($p$) model by `lm` versus `arima` in R: different results | stats | 2017-11-01T10:52:03.453 |
[
{
"message": "I want to know how to understand whether my dataset, which I have plotted below using Excel, contains seasonality. Specifically:How to detect seasonality on viewing the chartHow to detect seasonality from dataset (for coding purpose)If seasonality identified, how to remove the seasonality and mak... | How to detect seasonality from plotted data without using tools or libraries | stats | 2017-11-01T11:31:07.960 |
[
{
"message": "Can anyone enlighten me with the equation structure for the following basic theoretical (although common) scenario:Sales, $S$, are related to \"Advertising\", $A$, such that when $A$ is small $S$ grows exponentially, and when $A$ is large, $S$ grows more slowly until at some point any increase in ... | Basic structure of linear regression equation for s-shaped response curve | stats | 2017-11-01T13:28:43.860 |
[
{
"message": "When performing a hypothesis test of a difference of two proportions, does one change the integrity of the problem when changing the scale? To clarify: I want to test the difference in proportions of maintenance errors per hour of maintenance for two sets of years, say A = [1990-2000] and B = [200... | Changing the scale in a hypothesis test of proportions | stats | 2017-11-01T14:32:08.617 |
[
{
"message": "When performing a hypothesis test of a difference of two proportions, does one change the integrity of the problem when changing the scale? To clarify: I want to test the difference in proportions of maintenance errors per hour of maintenance for two sets of years, say A = [1990-2000] and B = [200... | Changing the scale in a hypothesis test of proportions | stats | 2017-11-01T14:32:08.617 |
[
{
"message": "Let $\\bf X$ be the <code>p</code>-variate dataset. I want to modify the data to <code>p</code>-variate data $\\bf Y$ so that its variables satisfy precisely a given <a href=\"https://stats.stackexchange.com/a/22520/3277\">SSCP (or covariance, or correlation) matrix $\\bf R$: $\\bf Y'Y=R$, and the... | Ways to modify data minimally while the variables to follow the desired covariances | stats | 2017-11-01T15:16:46.117 |
[
{
"message": "I have some unlabeled 1D (i.e. time-domain) signals (real neuron measurements) that I would like to classify in 3 classes. I would like to use a ConvNet to do this. However, as far as I know, ConvNets are trained in a supervised fashion. I've done some research and I've found <a href=\"https://arx... | Unsupervised training of CNN | stats | 2017-11-02T00:38:23.447 |
[
{
"message": "The background of my question is that for e.g. the White heteroskedasticity test or the Breusch-Godfrey (LM) autocorrelation test, we are generally only interested in the R-squared of the \"auxiliary\" regression. However, the only way of computing said R-squared that I am aware of involves derivi... | Is there a way to calculate R-squared in OLS without computing the coefficients? | stats | 2017-11-02T03:10:32.083 |
[
{
"message": "If I have a data set containing multiple users' data with features $X$ and some class (let's assume binary for simplicity) that I want to classify, $Y$. A user can generate multiple \"events\" and $X$ as well as $Y$ might not be the same for each event. Each \"event\" is a discrete moment in time ... | How do I handle correlated data points in classification problem where users generate multiple events? | stats | 2017-11-02T10:18:38.613 |
[
{
"message": "I'm trying to think about WAIC under a multivariate model scenario. Suppose I have one model composed of two relationships:<pre><code>y1 ~ xy2 ~ y1</code></pre>This is one model. Now, I have a second model<pre><code>y1 ~ xy2 ~ y1 + x</code></pre>I would like to construct a WAIC to compare the firs... | Scaling WAIC for Multiple Endogenous Response Variables | stats | 2017-11-02T10:44:33.597 |
[
{
"message": "I'd like to get statistical support for hypotheses concerning the effects of independent variables $D,CF,CT,P,H,LA,LP$ on $C$. For regressor sets $\\{D,CF,CT,P,LA,LP\\}$ and $\\{D,CF,CT,H,LA,LP\\}$ all the independent variables are statistically significant: <pre><code>Call:clogit(C ~ D + CF + CT ... | Can it be considered as a statistical support for my hypothesis? | stats | 2017-11-02T10:52:05.213 |
[
{
"message": "I have some trouble with a specific time series. The time series itself is pretty short: Only 73 observations that look like this:<a href=\"https://i.stack.imgur.com/dnxDN.jpg\" rel=\"nofollow noreferrer\">First problem: Detrend or not?First I need to find out if the time series has a unit root or... | Detrending or not and should I always take log first? | stats | 2017-11-02T13:48:09.487 |
[
{
"message": "I'm working on a Kaggle problem (the problem closed some time ago, but doing it for self-study/practice) where the output is clearly affected by both the year and the month. <a href=\"https://i.stack.imgur.com/hQqGm.png\" rel=\"nofollow noreferrer\">The original datetime data provides year/month/d... | Best practice for encoding datetime in machine learning | stats | 2017-11-02T16:19:52.383 |
[
{
"message": "I am currently dealing with a proof of Pauline Barrieu`s Paper \"Assessing Financial Model Risk\" (page 19).At one point she applys the l'Hospital rule on a limit equation. We have some cumulative distribution function $F$ and its derivation $f$ as a density function given. I just can`t follow tha... | How to simplify the derivation of the inverse cdf yielded from l'Hospital rule? | stats | 2017-11-02T18:49:09.070 |
[
{
"message": "I have some data that look like this: <pre><code>dist <- c(125,12,26,21,52,123)exists <- c(0,1,0,0,1,0)df <- cbind(dist, exists)</code></pre>Basically its a bunch of observations of whether connections exist at different distances. I'd like to fit to this data some kind of probability fun... | Binomial probability for a continuous variable | stats | 2017-11-02T22:24:58.240 |
[
{
"message": "In <a href=\"https://youtu.be/wIGPUCTD7z8?t=6m36s\" rel=\"nofollow noreferrer\">this precise moment of this lecture:$(X_1, X_2)$ are the log returns of companies $X_1$ and $X_2,$ respectively. Then \"we create an identically distributed copy\"...$$(X_1, X_2) \\underset{id}{=} (X_1', X_2')$$to def... | Concept of "identically distributed copy" in Kendall's tau | stats | 2017-11-04T15:15:00.990 |
[
{
"message": "BackgroundI have a fairly small image set (about 300 images) and I need to detect rectangular plates present in these images. Each of the images are annotated, but some examples are clearer than others due to lighting conditions (after pre-processing). The articles which I've read on supervised le... | Are there rules of thumb for selecting images for a supervised learning training set? | stats | 2017-11-04T18:42:40.950 |
[
{
"message": "I'm learning about ensemble method (aka bootstrapping?). Specifically I'm using the statisticalModeling package but I'm not sure that matters. Here is some code:<pre><code>library(statisticalModeling)lm_mtcars <- lm( mpg ~ cyl + hp, data = mtcars)</code></pre>If I look at <code>summary(lm_mtc... | Can I use bootstrapping to improve prediction error of simple linear model? | stats | 2017-11-04T20:22:30.420 |
[
{
"message": "I have written an ANN algorithm. And after several iterations my weights grow largely and there's this error which says the value of them is overflowing and therefore the outputs are NaNs. Does it make sense to scale weights for each layer to avoid them from growing very large by dividing them by ... | ANN: Weights grow very large, can I scale them? | stats | 2017-11-04T23:54:31.893 |
[
{
"message": "The question I'm looking at involves evaluating:$$ E[\\frac{(n-1)}{(n-1+X_n)}] $$ for n >= 2Xn is a random variable with a negative binomial distribution, equivalent to Binomial(p, -n).How would I go about evaluating this expectation? I've never dealt with taking the expectation of a function whic... | Expectation of a function of a distribution? | stats | 2017-11-05T01:51:47.497 |
[
{
"message": "Observation [1]Word2vec is pretty good at comparing \"subjects\", e.g.:$$\\langle dog, pup \\rangle \\simeq 0.81$$$$\\langle pants, trousers \\rangle \\simeq 0.75$$But it appears to be not great at encoding \"relationships\" in a way that preserves semantics, e.g.:$$\\langle spouse, wife \\rangle ... | Semantic word embedding for relationships? | stats | 2017-11-05T03:56:22.530 |
[
{
"message": "I have a dataset of 250 lines and 11 columns. Each line contains data referring to a school. For each school I have its name and the number of applications, from 2012 to 2016, and I would like to predict the number of applications for 2017. I also have the neighborhood where each school is located... | Hierarchical regression in a time series dataset | stats | 2017-11-05T10:28:19.080 |
[
{
"message": "I am working on a project which we have two groups of people; normal vs obese. I have a data set like the following sample:<pre><code>Subject group time Cholesterol1 normal 1 121 normal 2 141 normal 3 152 normal 1 162 normal 2 182 ... | Mixed model_Identifying the random effect in a analysis | stats | 2017-11-05T14:43:32.223 |
[
{
"message": "I read information about variational autoencoder from this post: <a href=\"https://blog.keras.io/building-autoencoders-in-keras.html\" rel=\"nofollow noreferrer\">https://blog.keras.io/building-autoencoders-in-keras.html. To get reconstructed output, a value is sampled from Gaussian distribution ... | Why do we use sampled points instead of mean to reconstruct outputs in variational autoencoder? | stats | 2017-11-06T01:51:11.903 |
[
{
"message": "I'm currently working on a project where I'm also the one who's labelling the data that im going to use for the model. My model is a document-classification model where I'd classify if a document belongs to a certain category or not. So the problem is that I made different models in different stag... | Less training data gave me better test score | stats | 2017-11-06T10:00:00.813 |
[
{
"message": "I'm currently working on a project where I'm also the one who's labelling the data that im going to use for the model. My model is a document-classification model where I'd classify if a document belongs to a certain category or not. So the problem is that I made different models in different stag... | Less training data gave me better test score | stats | 2017-11-06T10:00:00.813 |
[
{
"message": "to avoid negative forecasts, in this <a href=\"https://stackoverflow.com/questions/21054292/r-batch-forecasting-negative-values\">post it was mentioned to increase each value with a small amount. With the following example I am running into trouble doing this. This is not a forecast running in the... | Extreme peaks if forecasting slow movers | stats | 2017-11-06T13:12:14.483 |
[
{
"message": "I applied applied ARIMA to my time series data (24 hours of a day) which is this:<pre><code>Sdate Speed2012-12-11 00:00:00 0.823237 2012-12-11 01:00:00 0.633637 2012-12-11 02:00:00 1.10858 2012-12-11 03:00:00 1.30435 2012-12-11 04:00:00 1.35649 2012-12-11 05:00:00 0.998616 2012... | Applying ARIMA to time series data | stats | 2017-11-06T14:48:01.620 |
[
{
"message": "I'm working on a project, trying to model electricity consumption and generation from a bunch of PV generators to see how much of the demand can be satisfied by the production in the \"town\".Most models use a fixed demand and production profile in an hourly time-series.I'd like to see how variati... | Generating time series for electricity demand | stats | 2017-11-06T20:36:12.763 |
[
{
"message": "Question: What are the main differences and similarities between using Newey-West (1987) and Hansen-Hodrick (1980) standard errors? In which situations should one of these be preferred over the other?Notes:I do know how each of these adjustment procedures works; however, I have not yet found any d... | Comparison between Newey-West (1987) and Hansen-Hodrick (1980) | stats | 2017-11-06T23:26:31.763 |
[
{
"message": "I try to modelize princing datas where the price depends on 3 parameters : the profession and the city of the user.The model is very simple : Price = $avgPrice_{profession}\\cdot\\beta_{city} $ : for each profession, we have a average price, corrected by a coefficient for each city.With R, I used ... | Linear regression with two factors interaction in R | stats | 2017-11-07T09:59:12.970 |
[
{
"message": "<blockquote> For the given significance test, determine the probability of a Type II error or the power, as specified. Suppose we wish to test $H_{0}: p = 0.5$ against $H_{1}: p < 0.4$ using $α = 0.05$. If $p$ is actually equal to $0.4$, what is the probability of a type II error assumin... | Finding the probability of a Type II error or the power, as specified | stats | 2017-11-07T14:18:13.520 |
[
{
"message": "This question seems fundamental enough that I'm convinced it has been answered here somewhere, but I haven't found it.I understand that if the dependent variable in a regression is normally distributed, maximum likelihood and ordinary least squares produce the same parameter estimates.When the dep... | What are the properties of MLE that make it more desirable than OLS? | stats | 2017-11-07T17:13:03.117 |
[
{
"message": "The random effects estimator for panel data can be cast as a penalized verion of the \"fixed-effects\" estimator from econometrics. In both cases, the model is$$y_{it} = \\mathbf{D}_{i}\\alpha_i + \\mathbf{X}_{it}\\beta + \\epsilon$$Where $\\mathbf{D}_{i}$ is a matrix of dummies indicating the cr... | Is there a generalization of the "within" transformation to partial pooling? | stats | 2017-11-07T20:54:10.883 |
[
{
"message": "Working through some homework problems for a Mathematical Statistics course and I'm having a hard time finding good examples in the text to explain some details. This particular problem is:$Y_1 ... Y_n \\sim f_\\theta(y) = \\frac{6}{\\theta^3} y (\\theta-y)$Find a constant a so that $\\hat{\\thet... | Consistent estimator - bias and variance calculations | stats | 2017-11-08T05:03:08.110 |
[
{
"message": "I have a set of z-scores corresponding to different tests taken by the same subjects. Can i take the average of the z-scores for each subject and compare the average z-scores as it was actual z-scores? (i.e. can I calculate a percentile for each subject based on the average of the set of z-scores?... | Can I treat the mean of a set of z-scores as a z-score? | stats | 2017-11-08T10:15:30.073 |
[
{
"message": "I have a solid user-item matrix, with which I have build a collaborative filtering recommender system. I also have for each item a number of high quality features.If a new user comes to the website (online store), I quickly want to find out his taste. Currently I do this by asking 20 questions, in... | What is the most efficient way to set up a questionnaire get to know a user his taste | stats | 2017-11-08T12:58:57.830 |
[
{
"message": "I am running a negative binomial model and one of my predictor variables is a count variable. Since this variable was heavily skewed, I decided to log-transform it.However, the effect of this variable is hypothesized to be non-linear. However, as soon as I include the squared term in my model, I o... | Multicollinearity between ln(x) and ln(x)^2 | stats | 2017-11-08T15:56:50.207 |
[
{
"message": "I am estimating the parameters for mean and covariance in Multivariate Normal Distribution (MVN). Following <a href=\"https://en.wikipedia.org/wiki/Conjugate_prior#Continuous_distributions\" rel=\"nofollow noreferrer\">Wikipedia, I used MVN for the mean and Inverse-Wishart for covariance and tried... | How to set the priors for Bayesian estimation of Multivariate Normal Distribution when the correlation matrix has small values? | stats | 2017-11-09T10:04:36.930 |
[
{
"message": "I am trying to fit a hypothesis to my data in order to predict the duration for a certain event.My data is strictly categorical and I used one-hot encoding for all features.After using one-hot encoding the dataset now has the dimensions 20.000x414.After plotting the training and cross validation e... | linear regression - polynomial of higher degree with one hot encoding | stats | 2017-11-09T12:50:48.557 |
[
{
"message": "Lets say I want to model weekly grocery store sales. I have 300 stores. Only 100 remain active during the duration of the modeling period. This is due to some stores opening, some stores closing, and some stores being remodeled etc. It seems that I have at least two options for modeling. Exclude a... | Is is better to keep core observations or to make a variables that counts the number of observations | stats | 2017-11-09T13:13:32.520 |
[
{
"message": "I am running an experiment where I get 22,152,480 p-values in a given order, ranging from 0 to 1, but strongly tilted toward 1 (i.e. not uniformly distributed). I want to say that a given series of them is significant between two samples.For example, the p-values for given tests are 0.0428, 0.058... | Probability density Function for p-value product | stats | 2017-11-09T17:33:56.767 |
[
{
"message": "There seems to be a lot of discussion about this on CV but none quite answer my question.I have a variable <code>y</code> which represents number of adverse events occurring within a four-week period. There are three types of adverse event: 'mild', 'moderate' and 'severe' (and of course 'none').Th... | Poisson or Multinomial Logistic Regression (or something else)? | stats | 2017-11-10T01:09:28.417 |
[
{
"message": "I know this has been asked in the past many times, but i could not find an adequate answer to my problem. I have a dataset with many NaN values. I am making the calculated assumption that these values were not filled in purpose. Probably 50% of observations in continuous columns have a NaN value. ... | Handling NaN values by replacing them with -999 | stats | 2017-11-10T06:54:37.597 |
[
{
"message": "Assume we have a sample where the treatment is present for only a small fraction of the sample, and we want to exploit the treatment using propensity score matching. However, since the treatment group is small, matching with a caliper distance will result in a completely different matched sample e... | Bootstrapped Propensity Score Matching | stats | 2017-11-10T08:54:35.103 |
[
{
"message": "I am given an estimate of the mean and the variance of the estimated mean to 5 normally distributed random variables. I need to test if all 5 variables have the same mean.When I look for an answer online I’m led to a single-sample ANOVA, but I cannot implement the ANOVA, because I don’t have sampl... | Test if multiple random variables have the same mean | stats | 2017-11-10T14:36:37.993 |
[
{
"message": "Whenever a result is positive in a study, authors always give the p-value, which I understand as following :<blockquote> A really is higher than B, and I have 0.00015 probability of beeing wrong saying this.</blockquote>Genuinely, I'd like to give an anti-p-value when I give a negative result, wh... | Why isn't power always given with negative results? | stats | 2017-11-10T17:46:59.450 |
[
{
"message": "I was trying to write an answer for this question:<a href=\"https://stats.stackexchange.com/questions/311406/selection-of-data-range-changes-coefficients-too-much-in-lmer-inverse-regressio\">Selection of data range changes coefficients too much in lmer (inverse regression)Basically the OP has lots... | If in this problem I regress $x$ on $y$ instead than $y$ on $x$, do I need to use an error-in-variables model? | stats | 2017-11-10T17:47:11.010 |
[
{
"message": "Consider the model $$y=\\frac{1}{1-\\theta_1x^{\\theta_2}}+\\theta_3+\\epsilon$$(assume Gaussian iid errors, even though this is not relevant for the question). Is it possible to transform it into a linear one? I fiddled with it a bit, without success. Am I missing something, or is it just impossi... | Can this nonlinear model be transformed to a linear one? | stats | 2017-11-10T17:59:14.103 |
[
{
"message": "I'm reading a paper that uses survival regression to examine hospital length of stay, and then assigns variable importance based on the contribution of the deviance for each variable to model fit. They did not give any references for this, and I am having difficulty understanding their conclusion,... | Variable importance in a survival regression | stats | 2017-11-10T18:32:55.797 |
[
{
"message": "I am new to stats and I need to compare two groups of count data. I have two groups of participants who did X a number of times (out of 90 possible times). Group A did X 59 out of 90 times and Group B did X 74 out of 90 times. How do I set up the table to know if there is a significant differen... | how to do chi square test | stats | 2017-11-11T11:13:29.327 |
[
{
"message": "How do I go about representing data in a stem and leaf diagram with an amplitude of 5? Do I write the number modulus 5 or what? I find it confusing and not helping in organizing the data at all.",
"role": "user"
},
{
"message": "Do you mean a bin or interval width of 5 (or ... 0.05 or ... | Stem and leaf representation with an amplitude of 5 | stats | 2017-11-11T11:29:04.203 |
[
{
"message": "I've read in some posts that the absolute function is not differentiable. However, it is not differentiable only at 0. Can I not check the value at each training point to calculate the derivative. Only if the error happens to be 0 will it create a problem, in which case I could ignore the point. S... | Can I use gradient descent for Least Absolute Deviation Regression? | stats | 2017-11-11T19:03:28.840 |
[
{
"message": "How does one go about identifying if a complementary relationship (in the economic sense) between $x_1 $and $x_2$ exists in the determination of $y$.i.e. $$y=\\beta_o+\\beta_1\\min\\{x_1,x_2\\}+\\mu$$ what tests have to be done here and can this be estimated using OLS? *R code would be appreciate... | Identifying a $\min\{x_1,x_2\}$ in a regression | stats | 2017-11-12T00:13:31.830 |
[
{
"message": "I have a naive question about decision theory. We calculate the probabilities of various outcomes assuming particular decisions and assign utilities or costs to each outcome. We find the optimal decision by finding the one with the greatest expected utility.But why should we reason in this way? Ea... | Why care so much about expected utility? | stats | 2017-11-12T05:25:35.767 |
[
{
"message": "I am wondering about the different ways that Bayesian and Frequentist statistic connect with each other. I recalled that the Maximum Likelihood estimate of a parameter $\\theta$ is <a href=\"https://stats.stackexchange.com/q/252129/7224\">not necessarily an unbiased estimator of that parameter. Th... | Is the mean (Bayesian) posterior estimate of $\theta$ a (Frequentist) unbiased estimator of $\theta$? | stats | 2017-11-12T14:03:16.407 |
[
{
"message": "In a factorial experiment the definition of the main effect of a factor A with two levels, 0 and 1, is the difference in outcome means between the two level averaging over all other factors, $\\bar{y}_{A=0} - \\bar{y}_{A=1}$. What is the extension of this definition to factors with more than two l... | What is the definition of a "main effect" of a factor when it has more than two levels? | stats | 2017-11-12T15:04:34.570 |
[
{
"message": "A model is said to be represented in state space form if it can be written as$$Y_t = G_t X_t + W_t$$where $$X_t =F_t X_{t-1} + V_t $$and $W_t,V_t$ are some kind of random noise.The steady state instead is written as $$Y_t = G_t X_{t|t-1} + W_t$$where $$ X_{t+1|t} = F_t X_{t|t-1} + V_t $$This shoul... | Difference between the steady state of a model and state space models? | stats | 2017-11-12T20:23:01.200 |
[
{
"message": "I have several time series of two variables over the course of one year (approx. 2.5k observations). I hypothesize one variable (x) acts as a potential predictor for the other variable (y). I looked for the period in which y is best described by x (\"best\" as in strongest Pearson), took the obser... | Autocorrelation and heteroskedasticity in time series data | stats | 2017-11-13T12:57:31.000 |
[
{
"message": "Find the maximumlikelihood estimator of the following density function. When I asked before, @Glen_b said that this is special case of shifted gamma distribution.$$y=a+u^2$$ for u~N(0, $\\sigma^2$)Question says that work out the density of y.Therefore I take $f(y,a)=(y-a)^{1/2}$<blockquote> <bloc... | Find the maximumlikelihood estimator of the following density function | stats | 2017-11-13T22:19:13.717 |
[
{
"message": "<a href=\"http://amzn.to/2iTHvwO\" rel=\"noreferrer\">Casella and Berger state the invariance property of the ML estimator as follows:<blockquote> <a href=\"https://i.stack.imgur.com/QzpZQ.png\" rel=\"noreferrer\"></blockquote>However, it seems to me that they define the \"likelihood\" of $\\eta$... | Is the invariance property of the ML estimator nonsensical from a Bayesian perspective? | stats | 2017-11-14T08:35:32.737 |
[
{
"message": "A friend of mine is estimating the following model, using ols:$y=\\alpha + \\beta X + u$, where $y$ and $X$ are continious variables, $\\alpha$ and $\\beta$ are parameters and $u$ is an error component. In a second step, he then splits the sample at the median of the residuals. He then estimates t... | Regression: OLS: residual split | stats | 2017-11-14T09:10:21.510 |
[
{
"message": "TL;DRIn the HSLDA paper by Perotte et al, the posterior conditional distribution of $z_{d,n}$ for Gibbs Sampling is specified as:\\begin{equation*}p(z_{d,n}=k| \\mathbf{z}_{-d,n}, \\mathbf{a}, \\mathbf{w}, \\eta, \\alpha, \\beta)\\propto \\underbrace{\\frac{n_{-i, (k)}^{w_i}+\\beta}{n_{-i, (k)} + ... | Gibbs sampling in Hierarchically Supervised LDA (HSLDA) | stats | 2017-11-14T12:25:10.643 |
[
{
"message": "I'm trying to understand the history of <a href=\"https://en.wikipedia.org/wiki/Gradient_descent\" rel=\"noreferrer\">Gradient descent and <a href=\"https://en.wikipedia.org/wiki/Stochastic_gradient_descent\" rel=\"noreferrer\">Stochastic gradient descent. Gradient descent was invented in <a href=... | Who invented stochastic gradient descent? | stats | 2017-11-14T13:49:20.220 |
[
{
"message": "What would be a valid similarity measure to quantify the (dis)similarity between two different datasets processed using the same trained version of a self-organizing map (trained on the combination of both datsets)? What I mean is, each instance from the first dataset will be assigned to a specifi... | Quantify similarity between self-organizing maps (SOMs) | stats | 2017-11-14T14:28:20.790 |
[
{
"message": "I have weekly forecasts. I would like to also obtain monthly forecasts. Should I forecast using monthly data or just average my weekly forecasts?",
"role": "user"
},
{
"message": "Neither one.Instead, do both. The forecasts will not be sum consistent. Now consolidate them, using <a hre... | Forecast monthly outcomes or average weekly forecasts | stats | 2017-11-14T15:01:46.107 |
[
{
"message": "I've come across something called a dropout method that involves setting a threshold parameter $p$ and then for each predictor in your training set, generate a uniform random number. If that uniform random number is less than p, drop it. Basically, for each predictor in the training sample, set th... | How is the dropout method different than Random Forests? | stats | 2017-11-14T15:22:51.187 |
[
{
"message": "Assume that we have a random vector $\\mathbf{Y}=(Y_1,...,Y_n)$ with unknown joint distribution. We know however that the conditional distribution of an entry $Y_i$ given the rest of the vector, without the entry $Y_i$ ($Y_{-i}$) is normal:$$ Y_i|Y_{-i}\\sim N(\\mu+\\beta Y_kY_j,\\sigma^2) $$with ... | Going from conditional distributions to the joint distribution function | stats | 2017-11-14T15:29:15.733 |
[
{
"message": "I have a random forest classification model built on balanced positive and negative classes. I am trying to estimate the number of false positives and false negatives in the new data, in order to select an appropriate threshold. However, I don't have a good estimate for the number of positives i... | Random Forest: Estimate False Discovery Rate in new data? | stats | 2017-11-14T23:06:10.613 |
[
{
"message": "Apologies for a long post. I believe the answer of my questions involve basic statistics though I am reading it in the context of two-stage randomization design. The questions appear in the unbiasedness section. The other two sections (model framwork and estimator) only describe the relevant thing... | Unbiased estimator of distribution function in two-stage randomization design | stats | 2017-11-15T02:56:06.650 |
[
{
"message": "I'm trying to generate a dataset with a pre-defined correlation between a normally distributed variable and a binary variable.The method I had originally thought of was the following:Generate $X \\sim Norm(0,1)$Generate $Y \\sim Norm(0,1)$Generate $Q = \\rho X + \\sqrt{1-\\rho^2}Y$, this will be t... | Generate a Gaussian and a binary random variables with predefined correlation | stats | 2017-11-15T11:25:19.180 |
[
{
"message": "<a href=\"https://i.stack.imgur.com/toGxQ.png\" rel=\"nofollow noreferrer\">In the following solution, I am not sure how $f_x(x)$ got the value $\\frac{1}{2\\pi}$.I'm familiar with the expected value for continuous variables calculation.",
"role": "user"
},
{
"message": "$f_{\\mathbf x... | Need help understanding answer calculating the expected value? | stats | 2017-11-15T22:37:54.863 |
[
{
"message": "I’ve a question related to the NARX architecture of neural nets:What is the usage of the tapped delay line in this architecture?My problem is, that I can’t figure out the difference of this compared to a basic multilayer perceptron. Let’s say I have a set of data $S$ which represents a time series... | NARX architecture of neural networks | stats | 2017-11-16T06:57:30.060 |
[
{
"message": "I am studying share price log returns and AR(1) model.I downloaded data from FTSE100 and used the Adj.close column to find the Ln returns: <a href=\"https://i.stack.imgur.com/oAcSm.png\" rel=\"nofollow noreferrer\"><a href=\"https://i.stack.imgur.com/ewBNB.png\" rel=\"nofollow noreferrer\">Now I a... | Estimate AR(1) using Log returns | stats | 2017-11-16T11:17:36.630 |
[
{
"message": "I need to simulate some antibody labeling scenarios. To keep it non-field specific, I'll talk in terms of fruit instead of nanobodies though.Let's say I have an infinite supply of fruit. 70% of this supply are apples. If I now sample this population an infinite amount of times, with a sample size ... | How can I calculate the SD of a Gaussian obtained from sampling a binomial distribution | stats | 2017-11-16T16:22:24.717 |
[
{
"message": "I was looking at this example: <a href=\"https://onlinecourses.science.psu.edu/stat500/node/59\" rel=\"nofollow noreferrer\">https://onlinecourses.science.psu.edu/stat500/node/59and I got to the point where they use $\\beta_0=-222$ My question is where did they get those parameters, since they s... | Understanding where they got the parameters from | stats | 2017-11-17T16:28:39.837 |
[
{
"message": "I have the following non-linear model $(y_t -X_t\\alpha)^a=u_t$ where $u_t $ ~ $N(0,\\sigma^2)$Assume taht you estimated this model consitional on $a=1$. Calculate an Lagrange Multiplier LM test which you could use to test this restriction without estimating the unrestricted model. My attempt is a... | Calculatation of Lagrange multiplier LM test for nonlinear regression model | stats | 2017-11-17T20:25:46.363 |
[
{
"message": "I have a dataset of monthly air pollution levels (i.e. PM2.5) as well as a corresponding dataset with monthly rainfall amount (i.e mm) spanning several years. These datasets have moderately strong, negative relationship (i.e. R-squared = 0.6). I show an example of the data below.<a href=\"https://... | How can I adjust values in a timeseries to account for effects from other variable(s)? i.e. using a GAM | stats | 2017-11-17T20:33:02.143 |
[
{
"message": "I read papers that when the authors implement their regression algorithm (mainly using Conv Net) they sometimes use the correlation to evaluate their regression algorithm even though they used the Mean Square Error (MSE) as the loss function for their regression algorithm. My question is what does... | Should I evaluate my regression algorithm using MSE or correlation? | stats | 2017-11-17T20:40:51.833 |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.