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 use well known parameter estimation methods to estimate <code>scale</code> and <code>shape</code> parameters the Weibull. By the end I have a good estimation <code>reliability function</code>. I have <code>failure rate</code> that change over time of my items. Can I use the <code>failure rate as... | Rate parameter in Weibull distribution | stats | 2017-12-21T22:00:00.490 |
[
{
"message": "This is found in 'Deep learning' book, chap.6, ~p.178 (<a href=\"http://www.deeplearningbook.org/contents/mlp.html\" rel=\"nofollow noreferrer\">http://www.deeplearningbook.org/contents/mlp.html), which discusses the problem of predicting the output class of a binary variableIn this section of the... | Meaning of the linear transformation in sigmoid output for Bernoulli parameter estimation | stats | 2017-12-22T04:07:26.600 |
[
{
"message": "There is a famous principle in Bayesian that says: 'Yesterday’s posterior is today’s prior'. <a href=\"http://www.phil.vt.edu/dmayo/personal_website/Lindley_Philosophy_of_Statistics.pdf\" rel=\"nofollow noreferrer\">Lindley (2000).Now, suppose there are three studies conducted chronologically. Ba... | Step-wise Bayesian updating as a prior selection strategy | stats | 2017-12-22T16:52:37.260 |
[
{
"message": "I am working in biostatistics and often have the following conversation with medics: we are talking about some very interesting, but also very rare, disease/disorder (or side effect of a drug) until the point comes, where somebody says \"the prevalence of this disease/side effect is only 5 per 1 M... | How is the prevalence of a rare disease estimated? | stats | 2017-12-22T20:43:50.497 |
[
{
"message": "I have a dataset with different types of user events, and I'd like to set a metric of user activity. I don't have any labeled data of the actual perceived activity level of users.The data consists of around 10 different types of events (count of events normalized by usage time).For example:<pre><c... | Dimensionality reduction of events data | stats | 2017-12-24T11:27:41.403 |
[
{
"message": "I have trained an image classifier (for my own face) via the transfer learning method, in two ways (in order to compare efficiencies later on):1- I created a <code>docker</code> image, built on top of <code>tensorflow</code>'s <code>mobilenet</code> network, and trained it with my own dataset. tr... | Generate images from CNN model built with transfer learning | stats | 2017-12-25T05:03:42.753 |
[
{
"message": "I have more of a high-level question. I’m trying to design a neural network for flower detection. The images are 440x440x3 pixels (RGB) and are taken by drone so flowers are white dots (of radius up to 10 px). I have already annotated over 2000 images but I’m having trouble with the data represent... | Neural Network: output representation (output layer) | stats | 2017-12-25T17:25:45.293 |
[
{
"message": "If $B$ is the lag operator or backshift operator used in time series, what's $(1-B)^d(a_0+...+a_{d}t^d)$? We can think of the polynomial as a trend in a time series process.More specifically, what's $Bt^d$? $t^d-1$ or $(t-1)^d$?",
"role": "user"
},
{
"message": "Because there are impor... | What's $(1-B)^d(a_0+...+a_{d}t^d)$? | stats | 2017-12-26T14:42:18.437 |
[
{
"message": "One of the factors for my regression analysis is customer's familiarity with the store which equals 1 if the customer visited the store more than $N$ times and 0 otherwise. Is there a right way to choose $N$? For some $N$ this factor is statistically significant and for some not.",
"role": "us... | How to choose a threshold? | stats | 2017-12-26T19:35:31.413 |
[
{
"message": "I need to make a composite index from the sum of three power-law distributed variables, which vary on different scales and have different variances.For each variable there are many observations with very low scores and few observations with high scores.I need to normalize the variables to obtain a... | Normalization of power-law distributed variables. Z-scores or Min-Max? | stats | 2017-12-26T21:42:46.150 |
[
{
"message": "I am working on a data set were few qualitative features are having missing values.Qualitative columns having null values(nan):<pre><code>uniques in Gender ['Male' 'Female' nan]uniques in Married ['No' 'Yes' nan]uniques in Dependents ['0' '1' '2' '3+' nan]uniques in Self_Employed ['No' 'Yes' n... | Imputation of qualitative variables | stats | 2017-12-27T13:22:35.240 |
[
{
"message": "I have this problem<a href=\"https://i.stack.imgur.com/x7gUg.jpg\" rel=\"nofollow noreferrer\">I know in a Poisson distribution with the parameter theta, the UMVUE is Sample Mean. But I am not sure how do we obtain the UMVUE of theta square. Any help will be appreciated. Thanks in advance.",
... | Difficulty in obtaining the uniformly minimum variance unbiased estimator of Poisson distribution | stats | 2017-12-27T17:41:35.377 |
[
{
"message": "In many iterative machine learning algorithms, weight/parameters are initialized as random. But is there any mathematical relationship between the random starting point and initial accuracy?For example, in Probabilistic PCA the Principal Subspace \"W\" is initialized as random, which is refined by... | Is there any way to derive the initial accuracy with random initialization? | stats | 2017-12-27T18:54:42.957 |
[
{
"message": "I'm a non-stats person trying to learn more about statistical learning methods, and to organize my thinking I am trying to construct a mental taxonomy of the methods I'm learning about. For instance: <blockquote> Statistical learning methods can be divided into supervised and unsupervised categor... | Where do artificial neural networks belong in the 'taxonomy' of statistical learning methods? | stats | 2017-12-28T14:54:29.713 |
[
{
"message": "I'm new to Bayesian inference and Gibbs sampling in general, and I'm struggling trying to derive the conditional posteriors for a particular data generating process I'm trying to model. The model I am considering is as follows:$k \\sim Beta(a,b) \\\\\\lambda \\sim Gamma(c,f)$for i = 1 to N$d_i \\... | deriving posterior conditionals for gibbs sampling | stats | 2017-12-28T18:03:01.037 |
[
{
"message": "I'm having trouble putting this into plain English.According to the <a href=\"https://esa.un.org/unpd/wpp/General/GlossaryDemographicTerms.aspx\" rel=\"nofollow noreferrer\">UN World Population Prospects glossary it means:<blockquote> The mean age at childbearing is the mean age of mothers at the... | What does "mean age at childbearing" mean? | stats | 2017-12-28T19:31:54.927 |
[
{
"message": "What is the intuition behind why randomForest works well with prediction on lots of applied datasets? No fancy math required for an answer-but if you have some that helps intuition great.",
"role": "user"
},
{
"message": "The kind of intuition I like to have is driven by \"physics\" an... | what is the intuition of why randomforest often works well? | stats | 2017-12-28T23:48:27.413 |
[
{
"message": "Does a family of a distribution have a different definition for statistics than in other disciplines?In general, a <a href=\"https://en.wikipedia.org/wiki/Family_of_curves\" rel=\"noreferrer\">family of curves is a set of curves, each of which is given by a function or parametrization in which one... | Definition of family of a distribution? | stats | 2017-12-29T04:46:14.950 |
[
{
"message": "I am working on a time series that contains daily sales data. The aim of the project is to estimate the impact of marketing expenditure on the sales, while accounting for seasonality and trend. I have subtracted a double seasonality (weekly and yearly) and a trend by using TBATS. Now I plan to reg... | How to treat days when shops are closed in sales time series? | stats | 2017-12-29T11:39:56.563 |
[
{
"message": "Per <a href=\"https://stats.stackexchange.com/q/213201\">this post, you can force seasonality in auto.arima by selecting D=1. I have a weekly time series which looks like it might (or might not) have a seasonal component (I have a priori reasons for thinking it might have a seasonal component). <p... | auto.arima returns a non-seasonal model even though I am forcing seasonality | stats | 2017-12-29T12:04:30.460 |
[
{
"message": "I am trying to apply Gaussian process on estimating the value of a sensor reading. I have the readings if the sensor for few years (hourly paced time series) so my data is an array of two columns the first one is the time the other one is the sensor reading at that time. I have tried to write the ... | Gaussian process with time series | stats | 2017-12-30T22:46:26.203 |
[
{
"message": "<a href=\"https://www.vox.com/the-big-idea/2017/12/28/16823266/medical-treatments-evidence-based-expensive-cost-stents\" rel=\"nofollow noreferrer\">\"The proportion of medical procedures unsupported by evidence may be nearly half.\" If we assume that half of all procedures are based on observatio... | Less than half of medical procedures are based on adequate evidence. What percent of those should we expect to be wrong? | stats | 2017-12-31T06:11:09.917 |
[
{
"message": "The question has been asked (one time) on CV before, but the answer is really imprecise and does not really answer the question in my opinion.So: What are the assumptions for estimating a linear regression model via quantile regression?To my understanding (and as several CV users have mentioned), ... | What are the assumptions for applying a quantile regression model? | stats | 2017-12-31T10:46:00.977 |
[
{
"message": "In Google's paper <a href=\"https://arxiv.org/abs/1609.08144\" rel=\"nofollow noreferrer\">Google's Neural Machine Translation System: Bridging the Gap between Human and Machine Translation, it is stated<blockquote> Our LSTM RNNs have $8$ layers, with residual connections between layers ...</bloc... | What are "residual connections" in RNNs? | stats | 2018-01-01T03:03:02.960 |
[
{
"message": "I want to make a quantitative statement like \"There is a 90% chance that this $X$-$Y$-data follows a linear model (with some noise added on top)\". I can't find this kind of statement discussed in standard statistics texbooks, such as James et al.'s \"An Introduction to Statistical Learning\" (as... | Probability that residuals are normal | stats | 2018-01-01T09:04:22.423 |
[
{
"message": "I originally posted this on Stack Overflow, and it was suggested that this question would be better suited for CV: With reference to the HoltWinters function in R, how does one deal with time periods with irregular frequencies (f)? Most obviously, there is an irregular number of days in the year -... | R - Holt-Winters - irregular frequency | stats | 2018-01-01T18:07:31.300 |
[
{
"message": "Let's say you have this dataset:<pre><code>+-----------------+-------------+| Hour of the day | Page visits |+-----------------+-------------+| 1 | 12 || 2 | 7 || 3 | 7 || 4 | 10 || 5 | ... | Basic time of the day analysis | stats | 2018-01-02T17:53:23.380 |
[
{
"message": "My understanding of the multinomial likelihood, with four states, ${A}$, ${B}$, ${C}$ and ${D}$ is that it can be expressed as:$Likelihood = \\frac{N!} {nA! nB! nC! nD!} P(A)^{nA} P(B)^{nB} P(C)^{nC} P(D)^{nD}. $where${N}$ = number of trials.${nA}$ = number of trials resulting in State ${A}$${nB... | multinomial log likelihood: rounding error or estimation error? | stats | 2018-01-03T08:27:15.303 |
[
{
"message": "I have data on two levels: team and individual. However, since the ICC on team level is low, I’ll not use a multilevel model but just a regular regression on individual level. After all, the impact of the team variables and the estimation of clustered standard error is small and has not a signific... | ICC low, but still team variables in individual model? | stats | 2018-01-03T08:46:07.320 |
[
{
"message": "NoteI am a first-time user of this site, and am not sure what determines how broad a question is. I consciously limited the question to general principles in order to avoid making it too broad (by asking for examples, etc.).Nevertheless, if it is too broad, let me know in the comments, and do sugg... | General principles for extending the Elo system to games in which the margin of victory matters | stats | 2018-01-03T09:35:16.207 |
[
{
"message": "I want to make supervised learning on a dataset containing for each observation a list of labels (the predictors) and a list of types to predict. The train dataset looks like this:<pre><code> label1 label2 label3 type1 type21 book novel <NA> person writer2 fly tree eggs ani... | Supervised learning: predict a list of features from a list of predictors | stats | 2018-01-03T10:26:35.917 |
[
{
"message": "<blockquote> Let X and Y are two independent uniformly distributed random variable on [0,1].The value of $P(|X-Y|>\\frac{1}{3}/X\\geq1/2)=?$</blockquote>My try$P(|X-Y|>\\frac{1}{3}/X\\geq1/2)=\\frac{P(|X-Y|>\\frac{1}{3},X\\geq1/2)}{P(X\\geq1/2)}$Here I solved the denominator part that is... | $P(|X-Y|>\frac{1}{3}/X\geq1/2)=?$ | stats | 2018-01-03T10:56:41.290 |
[
{
"message": "Fairly new to statistics here. Can someone please show me how to calculate the probability that this \"team\" will collectively score at least 463 points? I need to do this in Excel.<pre><code>Player Projection Mean StDevPlayer A 50 49.16 21.61Player B 54 53.14 12.54Playe... | Joint Probability | stats | 2018-01-03T14:38:36.113 |
[
{
"message": "I've got a longitudinal dataset with three variables: FIPS, eighteenplus, & year. FIPS is the id , and I'd like to impute data for eighteenplus. Eighteenplus data were only available for 1990 and 2000, so I'd like to impute data for each FIPS-year in the period 1991-1999. However, I ran this c... | Impute missing data for one variable in longitudinal data set? | stats | 2018-01-03T15:31:30.467 |
[
{
"message": "Does any one know of a good source for the study of maximum likelihood estimation on a general exponential family of the form $f(x;\\theta)=a(\\theta)g(x)\\exp[{\\sum_{i=1}^{k} b_i(\\theta)R_i(x)}]$? Any help is greatly appreciated.",
"role": "user"
},
{
"message": "The references in C... | Maximum Likelihood Estimation on Exponential Family | stats | 2018-01-03T16:16:57.187 |
[
{
"message": "I am trying to perform the equivalent of a repeated-measures ANOVA using data that have a non-linear relationship. The independent variable <code>position</code> runs from -20 to +20, and we have measured a dependent variable <code>performance</code> in 17 subjects. What I'd like to know is the ex... | Equivalent to ANOVA for non-linear (quadratic) relationships | stats | 2018-01-03T18:12:52.670 |
[
{
"message": "I did 2 linear regression analyses. White woman (WW) N1= 50Black woman (BW) N2= 49Correlation btw WW's V1 & V2 P = 0.001Correlation btw BW's V1 & V2 P = 0.013How do i know if the 2 p values are difffernet from each other in order to say that V1 & V2 of WW is more associated than that o... | Comparing 2 p values of different sample size | stats | 2018-01-04T02:44:01.407 |
[
{
"message": "I'm a little confused on how to manage my data set with WEKA.(for data mining)I have a Dat set including 11377 record classified as follows:11111 records have class YES266 records have class NOThis is an unbalanced class, and if i start the classification process with WEKA, the results will be poo... | Cross-validation with unbalanced-classes | stats | 2018-01-04T10:25:04.007 |
[
{
"message": "I'm working on a linear model like:<a href=\"https://i.stack.imgur.com/TLJ15.gif\" rel=\"nofollow noreferrer\">I'm applying the formulae to the data to calculate the estimators of a and b using R.First I got some data like:<pre><code>x <- c(10,11,23,24)y <- c(4,2,7,8)</code></pre>Then I appl... | Variance of the estimators in Linear Model with manual formulae in R | stats | 2018-01-04T12:16:09.950 |
[
{
"message": "$$p(W,H,β|V) = \\frac{p(V|W,H) p(W|β) p(H|β) p(β)}{p(V)}$$I have tried a lot but I cannot prove this formula. The paper is: Ioannis Psorakis, I, Roberts, S, Ebden, M, & Sheldon, B. (2011). Overlapping community detection using Bayesian non-negative matrix factorization. PHYSICAL REVIEW E ... | How to prove the Bayes formula below? | stats | 2018-01-04T16:03:46.970 |
[
{
"message": "I just completed a Linear Regression course in college, and I recall that the TA during office hours would explain the least squares estimator using the drawing of a parabola, and indicate that the minimum was at the bottom. I've seen this concept come up again however with straight lines due to t... | Question about least squares estimator explanation with a parabola | stats | 2018-01-04T19:49:48.153 |
[
{
"message": "I have data from 44 twin pairs (88 patients total) and they are split into <code>group_A</code> (n=50) and <code>group_B</code> (n=38). For each of the patients, I have attribute data (Let's say m=100) so my data matrix is <code>(n=88, m=100)</code>. I have properly normalized the data and used ... | Does the Mann-Whitney U-test need to be adjusted in twin studies? | stats | 2018-01-05T18:09:13.267 |
[
{
"message": "I was trying to carry out feature selection on a dataset using sequential feature selection. The dataset contains more than 5000 observations (rows) and 22 features (columns). Now I see that there are two options to do it. One is 'backward' and the other is 'forward'. I was reading the article <a ... | Forward or backward sequential feature selection? | stats | 2018-01-05T21:07:13.940 |
[
{
"message": "Consider as an example the following Var(1) process:$y_t=Gy_{t-1}+\\varepsilon_{t+1}$, where $\\varepsilon_{t+1}$ is white noise and the matrix $G$ has all eigenvalues strictly smaller than 1. Then by standard results the process is stationary, and since $\\sum_iG^i$ is absolutely summable, it can... | Can a stationary var(1) process have no variance? | stats | 2018-01-06T10:54:52.037 |
[
{
"message": "I'm trying to model a bivariate distribution using copulas in R. See image below for the pairs plot of the data. Variable 1 can be modeled nicely using a gamma distribution, but variable 2 fails miserably. I think the only way variable 2 could be modeled is by a customized piece-wise distribution?... | Copula for non-standard distributions in R | stats | 2018-01-06T21:14:04.590 |
[
{
"message": "From Theodoridis' Machine Learning, exercise 3.26.<blockquote> Consider, once more, the same regression as that of Problem 3.8, but with $\\boldsymbol\\Sigma_{\\boldsymbol\\eta} = \\mathbf{I}_N$. </blockquote>For context, this is the regression model $$y_n = \\boldsymbol\\theta^{T}\\mathbf{x}_n +... | Find the MSE of a true response and its predicted value using OLS estimation | stats | 2018-01-07T07:30:31.363 |
[
{
"message": "I am trying to build a binary classifier from a relatively large medical data set (1 - disease, 0 - no disease). The data set contains about 500 patients, of which 9% have the disease, and about 70 features (predictor variables).I would like to try:1) feature selection - to reduce the number of fe... | Imbalanced data, SMOTE and feature selection | stats | 2018-01-07T14:57:44.270 |
[
{
"message": "I am studying time series, following Time Series Theory and Methods by Brockwell and Davis. I am reading the proof of the Herglotz Theorem, I have the following questions.First, the proof given in the book is the next one:<a href=\"https://i.stack.imgur.com/Dg3Ia.jpg\" rel=\"nofollow noreferrer\">... | Proof of Herglotz Theorem in Time Series Analysis | stats | 2018-01-07T21:54:22.780 |
[
{
"message": "I am reading <code>Bishop - Pattern Recognition and Machine Learning</code> book. In Chapter 4 first page, there is a statement that<blockquote> In this chapter, we consider linear models for classification, by which we mean that the decision surfaces are linear functions of the input vector x an... | Why decision boundary is of (D-1) dimensions? | stats | 2018-01-08T13:24:14.480 |
[
{
"message": "I am confused on the definitions of steepest descent. In some literature, such as <a href=\"https://rads.stackoverflow.com/amzn/click/0387303030\" rel=\"nofollow noreferrer\">this and <a href=\"https://www.rose-hulman.edu/~bryan/lottamath/congrad.pdf\" rel=\"nofollow noreferrer\">this, steepest de... | What is steepest descent? Is it gradient descent with exact line search? | stats | 2018-01-08T22:44:12.600 |
[
{
"message": "I am confused on the definitions of steepest descent. In some literature, such as <a href=\"https://rads.stackoverflow.com/amzn/click/0387303030\" rel=\"nofollow noreferrer\">this and <a href=\"https://www.rose-hulman.edu/~bryan/lottamath/congrad.pdf\" rel=\"nofollow noreferrer\">this, steepest de... | What is steepest descent? Is it gradient descent with exact line search? | stats | 2018-01-08T22:44:12.600 |
[
{
"message": "As a motivating example, consider this hypothesis: A friend and I were discussing how it might be the case that, the more one person is given control in the process of making a movie, the higher the variance of the quality of that film. The more hands that go into making a film, the safer of a bet... | Conditionally heteroskedastic linear regression: How can I model variance from given predictors? | stats | 2018-01-09T02:41:37.740 |
[
{
"message": "I am new to ML. I am currently reading the classic book Machine Learning in Action by Peter Harrington. In its implementation of ridge regression in P165 Listing 8.3, the book standardizes feature matrix $X$ by subtracting means of attributes and then dividing it by variances of attributes not by ... | Is this a mistake in the feature standardization of ridge regression in book Machine Learning in Action? | stats | 2018-01-09T10:24:29.617 |
[
{
"message": "Will it be correct to use Mean absolute scaled error in non time series data? I've got a set which contains a lot of zeros, so errors like MAPE can not be used here. MASE based on difference between yt and yt-1 (<a href=\"https://en.wikipedia.org/wiki/Mean_absolute_scaled_error\" rel=\"nofollow no... | Is MASE specified only to time series data | stats | 2018-01-09T16:29:25.397 |
[
{
"message": "Greene (econometric analysis p. 235 7th ed) discusses the Hausman test (test for whether the OLS is consistent). Greene states:<blockquote> <a href=\"https://i.stack.imgur.com/rEbb5.png\" rel=\"nofollow noreferrer\"></blockquote>Probably, Greene believes that Hausman's technical statement of this... | intuition/explanation for "Hausman's result"? | stats | 2018-01-09T18:14:03.000 |
[
{
"message": "As I read many cases of \"standardization\",there are some opinions conflict with them, e.g.some cases will add lag features and some of these features arecreated by other original features and it might lead to strongcorrelation between them.however logistics regression models arestrongly advised ... | features preprocessing in model building | stats | 2018-01-10T04:44:26.053 |
[
{
"message": "I've trained two models (binary classifiers using h2o AutoML) and I want to select one to use. I have the following results:<pre><code> model_id auc logloss logloss_train logloss_valid gini_train gini_validDL_grid_1 0.542694 0.287469 0.092717 0.211956 0.8... | logloss vs gini/auc | stats | 2018-01-10T12:56:11.973 |
[
{
"message": "I am interested in using Hidden Markov Models in the context of multi-sensors sequences in vegetation remote sensing.The observation labels are the same as the state labels.Each observation at a given time $t$ is classified and I want to use HMM in order to reduce classification errors.For example... | Hidden Markov Models - Weight observations | stats | 2018-01-10T15:21:11.200 |
[
{
"message": "I am trying to understand the relationship between the beta-binomial and the binomial distribution. More specifically, I am trying to show that the limit of the beta-binomial distribution, with $p=a/(a+b)$ is binomial as $a+b$ goes to infinity. I am having trouble showing it. Any useful hints wou... | Limit of beta-binomial distribution is binomial | stats | 2018-01-10T16:36:56.473 |
[
{
"message": "I understand that with Ridge or Lasso regression we are trying to shrink regression coefficients, and we specify the amount of shrinking we need by varying alpha. But I cannot understand the intuition or rationale behind doing it? as we no longer fit the best line.",
"role": "user"
},
{
... | Rationale behind shrinking regression coefficients in Ridge or LASSO regression | stats | 2018-01-11T03:18:25.283 |
[
{
"message": "In an experiment, I am asking people to choose between two items (A or B). The task instructions use two different sentences (e.g., \"pick A or B\", \"pick B or A\", Q1 and Q2). In the results, it seems that the user behaviour is different with Q1 and Q2 (for example with N = 20):<pre><code>_ A... | Significance testing of binary selection | stats | 2018-01-11T11:55:23.727 |
[
{
"message": "I'm less than ... enthusiastic about some of Taleb's claims regarding, say, the paleo diet. I make no comment on his political content, but I want someone more factual and hard, and less prone to controversy and drama. I make no comment on Taleb's content herein as all I am saying is that I want s... | I'm looking for a risk analysis book with citations from academic backgrounds that focuses on shocks and the unknown. Looking for a Taleb alternative | stats | 2018-01-11T12:24:55.700 |
[
{
"message": "If I understood the algorithm properly it should go like this:Randomly initialize SOM weights $\\xi_1, ... , \\xi_n$ in feature space.Randomly pick sample from training set v(k) (k as in step k)Find BMU (Best matching unit, closest SOM vector to feature vector) b(k)Update all $\\xi_m$ according ... | Kohonen Self-Organizing Maps algorithm clarification. On each iteration, it goes trough all dataset or just a subsample? | stats | 2018-01-11T13:18:49.920 |
[
{
"message": "Consider a heteroskedastic model of the form, $y_i|x_i \\sim \\mathcal{N}\\left(x_i, \\text{exp}\\{\\boldsymbol\\beta^\\top\\boldsymbol{x}\\}\\right)$ where $\\boldsymbol{\\beta}=\\left[\\beta_0,\\beta_1\\right]$ and $\\boldsymbol{x}=\\left[1,x_i\\right]$. $x_i$ and $\\boldsymbol{\\beta}$ must be ... | Metropolis-Hastings for heteroskedastic regression | stats | 2018-01-11T19:53:12.963 |
[
{
"message": "I want to calculate the quantile curves at 0.025,0.50,0.975 percentiles. I have one predictor variable (age with min value 0.08 and max value=19 years) with this distributions:<a href=\"https://i.stack.imgur.com/hcOp1.png\" rel=\"nofollow noreferrer\">This is also the distribution of the dependent... | Should I use Transformation method in this analysis? | stats | 2018-01-12T02:42:22.670 |
[
{
"message": "I have histograms/distributions like the following that I would like to characterize/summarize by one or maybe two number(s). A mean +/- std would be one such example, but is there something better that can say something about the shape of the distribution? Most of the times the most frequent valu... | How can I characterize a histogram/distribution with a single value? | stats | 2018-01-13T06:37:24.017 |
[
{
"message": "Suppose we have a random variables <code>x</code>. <code>x <- rnorm(500, 2,3)</code>Suppose that we do not know the marginal distribution of (<code>x</code>) (I know it is normal).Then, I would like to estimate the marginal using empirical cumulative distribution function (<code>ecdf</code>). T... | How to estimate the margins distribution using ecdf? | stats | 2018-01-13T12:10:25.337 |
[
{
"message": "I am using <a href=\"https://machinelearningmastery.com/machine-learning-in-python-step-by-step/\" rel=\"nofollow noreferrer\">this website to learn Machine Learning. I am working on a simple project to learn it. I want to predict employee's attendance. This is the data in the file: <pre><code>... | How to predict employee's attendance based on previous attendance | stats | 2018-01-13T16:25:02.113 |
[
{
"message": "I am performing a conditional logistics regression (CLR) case-control (1:3) study over a very large dataset that has been partitioned according to a set of study requirements (to follow). Each entry is a patient record: age, gender and up to nine disease entries, etc. I take a male 20-29 populatio... | How can I be sure my sample size is large enough for conditional logistic regression? | stats | 2018-01-13T19:56:39.857 |
[
{
"message": "I have read that the variables must be approximately normally distributed to apply Pearson correlation; <a href=\"https://i.stack.imgur.com/icbyr.png\" rel=\"nofollow noreferrer\">However, I came across this answer <a href=\"https://stats.stackexchange.com/a/3733/188268\">here that they dont need... | Normal Distribution for Pearson Correlation | stats | 2018-01-14T07:59:51.890 |
[
{
"message": "I have a data as follows<pre><code>Date PaidJan-14 13392905Feb-14 11939873Mar-14 12473667Apr-14 12237110May-14 12579693Jun-14 12030095Jul-14 12052101Aug-14 10205025Sep-14 12102526Oct-14 1237336Nov-14 12148331Dec-14 9842860Jan-15 11990085Feb-15 11061740Mar-15 12076397Apr-15 11702... | ARIMA model with flat forecasts | stats | 2018-01-14T20:59:37.463 |
[
{
"message": "State duration in HMMs follows a geometric distribution by construction. How can one estimate the state duration, since it is not explicitly modeled (e.g., in HSMMs)? I'm particularly interested in the following packages: <code>hmmlearn</code> (Python) and <code>depmixS4</code> or <code>hmm</code>... | HMM and State Duration Estimation | stats | 2018-01-15T01:08:13.807 |
[
{
"message": "I feel like I have come as far as I can in statistics while not understanding how design and contrast matrices work. Specifically I am interested in how to code custom contrasts like <a href=\"https://stackoverflow.com/questions/35651138/coding-custom-contrasts\">this and whether such custom contr... | Book recommendations for Design and Contrast Matrices | stats | 2018-01-15T11:36:39.167 |
[
{
"message": "I found out that the chi square test in R may not be working. I don't know where I am doing it wrong.1) test two similar distribution<pre><code># create a sequence from 0 to 1000, seperated by 10x <- seq(0,1000,10)# create two similar gaussian distributionr1<- rnorm(x, 1000,100)r2 <- rnor... | Chisq.test not working in R? | stats | 2018-01-15T14:25:00.550 |
[
{
"message": "In orthogonal design of lasso, we get $\\hat{\\beta}_j^{\\text{lasso}} = 0 \\text{ if abs}(\\hat{\\beta}_j) \\le \\lambda /2$. WHY? I've seen the answer and derived it myself, but don't know why.We begin with definition of lasso,$$\\hat{\\beta}^{\\text{lasso}} = \\underset{x} {\\arg\\min} \\sum_... | How is the lasso orthogonal design case solution derived? | stats | 2018-01-15T18:05:50.657 |
[
{
"message": "I'm doing a <code>Simple Logistic Regression</code> using R. The description of the variable is listed below: <pre><code> vars n mean sd median trimmed mad min max range skew kurtosis seX1 1 1382 14410.84 39410.4 2352.5 5507.66 3235.03 7 440000 439993 5.83 43.1 ... | How to handle and interpret highly skewed predictor in logistic regression? | stats | 2018-01-16T21:53:08.610 |
[
{
"message": "Given data matrix $X_{n,p}$ where $n$ is the sample size, $p$ is the dimension, the sample covariance is $$\\hat{\\Sigma}=\\frac{1}{n-1}X^\\top X=\\{\\hat{\\sigma}_{ij}\\}_{1\\le i,j\\le p}$$Is there any result on the quantity like $cov(\\hat{\\sigma}_{i_0,j_0},\\hat{\\sigma}_{i_0,j_0+1})$? I.e. w... | Result for covariance between elements of the sample covariance matrix | stats | 2018-01-17T01:58:37.020 |
[
{
"message": "Problem: we have two processes $x_{t}$ and $y_{t}$ as follows:$x_{t} = y_{t} + w_{t}$$y_{t} = \\phi_{0} + \\phi_{1}y_{t-1} + u_{t}$$w_{t}, u_{t}$ iid with var: $\\sigma_{w}^{2}, \\sigma_{u}^{2}$, mean of $w_{t}$ is 0 (mean of $u_{t}$ not mentioned)$\\phi_{1} \\neq 0$then: $x_{t}$ is ARMA(1,1) with... | How to write this state space model as an ARMA(1,1) | stats | 2018-01-17T08:57:56.450 |
[
{
"message": "I understand the basic principles for the naïve bayes classification with one feature:$$P(Class|feature) = (P(f|Class) * P(Class)) / P(f)$$We have a dataset that has the following attributes/features:<code>day | outlook | temperature | humidity | wind | play</code>Day is just a number (sequence)Ou... | Naïve Bayes Theorem for multiple features | stats | 2018-01-17T11:15:41.883 |
[
{
"message": "I'm looking for some advice on selecting an appropriate forecasting model for panel data. I'm just starting out in the field and would appreciate any hints or rules of thumb to help make such decisions. Here's my particular case:I have quarterly data on the incomes of 12 competing companies. Each ... | Looking for advice regarding model selection for forecasting (dynamic?) panel data | stats | 2018-01-17T14:23:44.363 |
[
{
"message": "I came across the formula for obtaining the upper confidence bounds on the k-armed bandit problem:$$c\\sqrt{\\frac{\\text{ln} N_i}{n_i}}$$where $n_i$ is the amount of samples we have for this particular bandit and $N_i$ is the total amount of samples we have from all bandits. The same algorithm is... | Upper Confidence Bound in Machine Learning | stats | 2018-01-19T03:20:18.627 |
[
{
"message": "I had a query about Data set splitting.Say, I have a data set and I split them into 3 different sets - Training Set, Validation Set and Test Set.I will use the Training Set and Validation set to go over different algorithms and choose the best performing one (Based on validation Set accuracy and a... | Validation set for Model selection, but what if Test set gives bad result! | stats | 2018-01-19T05:02:15.850 |
[
{
"message": "For an $AR(p)$ process $ Y_t = a_1Y_{t-1}+a_2Y_{t-2}+...+a_qY_{t-q}$ : Is having the coefficients $|a_1|,....,|a_p| < 1$ just a necessary condition for stationarity, or is it sufficient as well?",
"role": "user"
},
{
"message": "It is certainly not sufficient, try the AR(2) process$... | Are all $AR(p)$ processes for which $|a_1|,....,|a_p| < 1$ stationary? | stats | 2018-01-19T06:14:06.157 |
[
{
"message": "I have the following cumulative distribution function:$F(x)=\\begin{cases} 0& \\text{ if } x<0 \\\\ \\frac{1}{4}+\\frac{1}{6}(4x-x^2) & \\text{ if } 0\\leq x<1\\\\ 1& \\text{ if } x\\geq1\\end{cases} $Now, it is required to calculate the probability $P(X=0|0\\leq x<1)$. How c... | Probability based on cumulative distribution function | stats | 2018-01-19T08:18:52.023 |
[
{
"message": "I was asked recently about a model evaluation metrics involved in a binary classifier. This person mentioned they were only interested in the <code>True Positives</code> and the <code>True Negatives</code>. <a href=\"https://i.stack.imgur.com/f99VR.png\" rel=\"nofollow noreferrer\">We could define... | Can a useful metric defined only using TP and TN? | stats | 2018-01-19T08:58:39.360 |
[
{
"message": "I decided to give box and whiskers plots a try with my data. However, the produced box plots look a bit abnormal. I have not been able to find such cases online. For example, my \"T\" value has no box at all, while the median of \"R\" value is actually the same as first quartile. Is this normal? I... | Help needed with my box plot | stats | 2018-01-19T11:15:39.193 |
[
{
"message": "The default number of features $m$ used when making splits in a random forest regression is $m=p$ in Python's sklearn, where $p$ is the number of predictors in the regression problem (see <a href=\"http://scikit-learn.org/stable/modules/generated/sklearn.ensemble.RandomForestRegressor.html\" rel=\... | References on number of features to use in Random Forest Regression | stats | 2018-01-22T05:09:41.677 |
[
{
"message": "Is there a way to determine if all the observations made over a population are similar?The data consists of 14 variables and 10-15 observation points over a mineral grain. Some cells have null value. I have to check if that mineral grain is homogeneous and if not to what degree.",
"role": "use... | Checking if sampling points located on a mineral grain are homogeneous | stats | 2018-01-22T09:02:22.773 |
[
{
"message": "Let $X_1,X_2,....X_n$ be a random sample from a population with probability density function $$f(x|\\theta)=\\dfrac{\\theta}{2}e^{-\\theta|x|} ,-\\infty < x < \\infty,\\theta>0$$ Then a UMVE of $\\theta$ is ?Can someone tell me if i did everything right or not in the following steps. I do... | Uniformly minimum variance unbiased estimator of theta. | stats | 2018-01-22T12:14:29.737 |
[
{
"message": "When teaching GLMs, it's commonly taught that the linear and log link are collapsible but that the logit is not. The log link is collapsible because the curves are proportional and the means are modeled with ratios. The linear link is collapsible because the trend-lines are parallel and the means ... | Is there a mathematical definition of non-collapsibility? | stats | 2018-01-22T15:05:09.320 |
[
{
"message": "I have trained a translation seq2seq model. In my model, I have kept vocabulary size to 100,000. This constraint limits my model from generating any words which are not in this 100,000.So how does Google Translate or Bing Translate works for any word in their input? Basically, my question is how t... | How to make a seq2seq model work with infinite vocabulary? | stats | 2018-01-22T17:09:41.807 |
[
{
"message": "In regression, the asymptotic normality requires, other than the central limit theorem, observations are independent, and panel data clearly violates this assumption as observations are at least correlated within an observation unit (e.g., family, firm, etc.). Does it means we can't use the asympt... | Does the asymptotic normality hold for panel structured data? | stats | 2018-01-22T22:53:56.857 |
[
{
"message": "In this <a href=\"https://www.youtube.com/watch?v=0tomU1q3AdY\" rel=\"nofollow noreferrer\">talk at 19:32, the following method of reducing a multivariate integral is discussed:Let $\\theta \\in \\mathbb{R}^p$ be the parameter vector, $\\mathbf{x}_i \\in \\mathbb{R}^p$ be the $i$-th data vector, $... | Linear subspace property of Gaussian integrals | stats | 2018-01-23T01:20:40.910 |
[
{
"message": "During the follow-up time, event A will happen multiple times, and there are 3 types of A, I call it A1, A2 and A3. I wonder if there is a statistical method that I can calculate the incidence rates of A1, A2 and A3 separately and compare the incidence rate to each other?Should I only consider A1 ... | Compare incidence rate | stats | 2018-01-23T09:44:05.983 |
[
{
"message": "Say I have an experiment running where I give treatment to a random selection of people, and I know that the target variable is affected by a number of factors. I know most of the factors that affect the target. So with this, I can run a model on my data, predict the target variable and see if the... | Determine treatment effect based on conditional factors | stats | 2018-01-23T13:47:56.993 |
[
{
"message": "I was stuck with the function 17.13 in the open source book deep learning on page <a href=\"http://www.deeplearningbook.org/contents/monte_carlo.html#p=590\" rel=\"nofollow noreferrer\">590.For short, the question is that, For the importance sampling estimator:$$\\hat s_q = \\frac{1}{n}\\sum_{i=1,... | How is this minimum variance worked out for this importance sampling estimator? | stats | 2018-01-23T16:14:51.570 |
[
{
"message": "There are four card types. Red, Blue, Green, and Black. From a deck of 20 cards (6 red, 6 blue, 6 green, and 2 black) you randomly draw 6 cards without replacement. I am trying to program a calculator that calculates the probability of drawing 2 reds for instance. How about 4 blues? 6 greens? I wo... | What is the statistical model to find probabilities of drawing certain cards in my card game? | stats | 2018-01-23T18:39:03.017 |
[
{
"message": "I have a dataset, which contains <code>DateTime</code>, <code>target</code>, <code>target_type</code>. <code>target</code> is basically the count of a process. <code>target_type</code> is binary and it says if the count was of the type, say \"outflow\" or of type, say \"inflow\". this has been rec... | Best approach for count prediction in time-series? | stats | 2018-01-24T08:33:33.623 |
[
{
"message": "What was the first derivation of the normal distribution, can you reproduce that derivation and also explain it within its historical context? I mean, if humanity forgot about the normal distribution, what is the most likely way I would rediscover it and what would be the most likely derivation? ... | How could I have discovered the normal distribution? | stats | 2018-01-24T08:54:48.130 |
[
{
"message": "In both <a href=\"http://www0.cs.ucl.ac.uk/staff/d.silver/web/Teaching.html\" rel=\"nofollow noreferrer\">the reinforcement learning course given by David Silver and <a href=\"http://incompleteideas.net/book/bookdraft2017nov5.pdf\" rel=\"nofollow noreferrer\">the latest draft of Richard S. Sutton'... | In reinforcement learning, what is the formal definition of the symbols $S_t$ and $A_t$? | stats | 2018-01-24T16:14:52.287 |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.