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": "In random walk model the error term is generally modelled using normal distribution. I have two questions.Q1. How to calculate the parameters of error term in case of Random walk with drift.Q2. For a data set which follows Weibull distribution. Is it correct if I model the error term of my random ... | Error term in Random walk with drift | stats | 2017-06-22T15:45:22.670 |
[
{
"message": "I'm trying to figure out if I can perform ANOVA on conversion rate. Would this work? Editing for more information: The question we are trying to solve is for our AB Testing program. Oftentimes we have multiple variants within our tests, and we are measuring conversion rate (expressed as orders / u... | Does ANOVA work with percentages, like Conversion Rate? | stats | 2017-06-22T18:40:22.660 |
[
{
"message": "I've collected data to judge the attitude of teachers and the students on a 20-items 5-point Likert scale towards computer. Now I want to compare their (Teachers vs Students) responses. How do I analyze my results. what type of test can I use for comparison between the two categories (Teachers and... | How to compare two populations | stats | 2017-06-22T20:03:25.970 |
[
{
"message": "I have a multi-variable linear model. More precisely, a set of variables to explain a target variable. After adding Gaussian noise ($\\sim N(0,1))$, the MSE increased from roughly $21$ to roughly $22$.How can it be explained? Is that what's called overfitting?",
"role": "user"
},
{
"me... | Why adding Gaussian noise increased MSE on the test set? | stats | 2017-06-23T09:47:24.853 |
[
{
"message": "I'm doing <a href=\"https://www.edx.org/course/analytics-edge-mitx-15-071x-3\" rel=\"nofollow noreferrer\">Analytics Edge course from EDX. The course is using R while I'm using Python.In linear regression, in order to improve the model, we have to figure out the most significant features.The cours... | For feature selection in linear regression model, can I use coefficient estimates? | stats | 2017-06-23T20:37:52.817 |
[
{
"message": "Let $\\mathcal{N}(\\mu,\\sigma)$ denote the Normal Distributionwith mean $\\mu$ and variance $\\sigma^2$, let $d_{tv}(X,Y)$ be thetotal variation distance of $X,Y$.QuestionAssuming $d_{tv}(\\mathcal{N}(\\mu_1, \\sigma_1), \\mathcal{N}(\\mu_2, \\sigma_2)) < \\epsilon$, where $\\epsilon$ is a pos... | Bounding Mean and Variance of Normal Assuming Total Variation Upper Bound | stats | 2017-06-25T00:42:53.473 |
[
{
"message": "I know the procedure how to test the statistical significance of the difference between correlation coefficients for two groups. The method I am familiar with is by converting each of the r values into z values, and put them into an equation to calculate Zobs (observed value of z-score).How do we ... | Determine the difference between correlation coefficients | stats | 2017-06-25T01:43:04.543 |
[
{
"message": "Recently I have learned about Generative Adversarial Networks.For training the Generator, I am somehow confused how it learns. Here is an implemenation of GANs:<pre><code>`# train generator z = Variable(xp.random.uniform(-1, 1, (batchsize, nz), dtype=np.float32)) x = gen(z) ... | Generative Adversial Networks: how the generator is trained with the output of discriminator | stats | 2017-06-25T15:22:28.360 |
[
{
"message": "I have a discrete stochastic process $X(t)$ which I believe is a Poisson process, that is the value of $X(t)$ at time $t$ is a Poisson random variable with parameter $\\lambda t$ and disjoint intervals are assumed to be independent.Due to the nature of the data I only have values of $X(t)$ at disc... | Testing Poisson process where $X(t)$ is given at fixed times | stats | 2017-06-25T22:30:29.600 |
[
{
"message": "My employer is currently running a company wide survey about attitudes towards the office i.e. Sentiment. In the past, they opened the survey to all areas of the business (Let's assume 10 very different departments) and all employees within them (Assume 1000 employees in total in the entire compan... | Surveys: Is 25% of a large user base representative? | stats | 2017-06-26T07:39:02.957 |
[
{
"message": "I'm following two timeseries: one is a setpoint, the other is the controlled output. When the setpoint rises I want the controlled output to follow quickly; when the setpoint drops, it's acceptable to have the output drop more slowly.Is there a metric that can quantify this behaviour? Some kind of... | Is there a way to cross-correlate two timeseries, but only when one of them rises? | stats | 2017-06-26T13:10:01.237 |
[
{
"message": "I am trying to implement <a href=\"https://en.wikipedia.org/wiki/Transfer_learning\" rel=\"nofollow noreferrer\">transfer learning to make predictions on test set using a model trained on another dataset collected from a different sample.For this, I need to identify the subset of training data tha... | How to identify the subset of a large dataset that has a similar distribution with the another dataset | stats | 2017-06-26T15:30:09.357 |
[
{
"message": "I have hourly summer cooling data for 4 months starting May 2016 to August 2016. In my data the cooling is high on standard business hours range from 08:00 to 21:00 during weekdays and is low in non-business hours and weekends. I have some predictor variables that also time dependent, which I use... | Forecasting High-Frequency, Multi-Seasonal Data with External Regressors in ARIMA | stats | 2017-06-26T21:17:42.647 |
[
{
"message": "Suppose we have a Bayesian DAG with the following structure:\\begin{array}{c} \\alpha & & \\beta & & \\gamma & & \\delta\\\\ & \\searrow & \\downarrow && \\downarrow &\\swarrow \\\\ && p && q\\\\ && \\searrow && \\swarrow\... | How to factor random variables that involve conditionals on hyper-parameters? | stats | 2017-06-26T21:49:31.777 |
[
{
"message": "I'm trying to run a logistic regression on categorical dependent variables data; The dependent variable is a choice of Yes/No/Unsure.I want to use <code>glmer</code> in <code>lme4</code>, how do I specify the family type?If I transformed the dependent variables into rate of Yes (<code>ACC</code>),... | How to do GLMM if the dependent variable is categorical in R? | stats | 2017-06-27T09:07:03.657 |
[
{
"message": "I have a sample of N integer values and I would like to check the null hypothesis $H_0 \\equiv $ \"the sample has a Poisson($\\lambda$) distribution\"This is, $p_i = P\\{X=i\\} = e^{-\\lambda} \\dfrac{\\lambda^{i}}{ i!}, i=0,1,...$So I've tried two approaches, both taken from the book \"Simulation... | Testing if two samples have the same probability distribution | stats | 2017-06-27T09:47:17.097 |
[
{
"message": "Suppose I have a dataset consisting of $3N$ elements ($X,Y$ pairs) and I split it evenly into three subsets. I know the Pearson correlations between $(X,Y)$ in each of these subsets, and suppose they are all equal to some value $k$, i.e. $r_1 = r_2 = r_3 = k > 0$. Is it possible for the correla... | Correlation of subsets vs correlation of full data set | stats | 2017-06-27T14:15:34.417 |
[
{
"message": "My question is similar to <a href=\"https://stats.stackexchange.com/a/5754/\">this other one, but I would like to know if it is possible to correct the p-values for multiple testing (and how). I have a large 42 gene expression values which are correlated with 25 clinical variables. So I end with a... | Correcting p-values in all vs all correlations | stats | 2017-06-28T15:09:53.170 |
[
{
"message": "I have the following problem. I want to find the expression for the autocorrelation of the following random variable or MA(1) process.$X_n = \\epsilon_n - \\epsilon_{n-1}$Where $\\epsilon$ is a stationary correlated noise with finite mean $\\mu_\\epsilon$ and standard deviation $\\sigma_\\epsilon$... | Autocorrelation of a MA(1) process with correlated noise sources | stats | 2017-06-28T16:40:12.610 |
[
{
"message": "I've been using linear models (<code>lm</code> function in R) to determine if the the expression of certain proteins is associated with disease severity. Sometimes the expression of proteins can also correlate with age, so I've been including that in the models as so: <pre><code>lm(ProteinA ~ Dise... | Interpreting non-significant coefficients when the entire linear model is significant | stats | 2017-06-28T19:29:38.160 |
[
{
"message": "In a comment to <a href=\"https://stats.stackexchange.com/questions/78839/how-should-tiny-p-values-be-reported-and-why-does-r-put-a-minimum-on-2-22e-1/78852#78852\">Jaap's answer to <a href=\"https://stats.stackexchange.com/questions/78839/how-should-tiny-p-values-be-reported-and-why-does-r-put-a-... | Why is $z$-value more meaningful than $p$-value for very low $p$-values? | stats | 2017-06-28T22:14:04.817 |
[
{
"message": "I have a small dataset of 25 observations with a classification variable (factor 0,1) and 82 features scaled to have values between 0 and 1. I used the <code>rfe()</code> function of the <code>caret</code> package to identify the best subset of features <code>(2:30)</code> in terms of <code>metric... | recursive feature elimination: why select subset based on AUC vs sensitivity/specificity | stats | 2017-06-29T08:49:19.630 |
[
{
"message": "I got these results after fitting a model:<a href=\"https://i.stack.imgur.com/Or8GW.png\" rel=\"nofollow noreferrer\">In the above picture X axis shows the fitted values and Y axis shows the truth values.We can see bias although I tuned <code>reg_alpha</code> & <code>reg_lambda</code> (i used ... | How to measure bias variance trade-off | stats | 2017-06-29T15:05:24.273 |
[
{
"message": "I want to test for the difference between means for what I think are two negative binomial or poisson-like distributions that are 0 inflated.Can I rely on the law of large numbers to do a simple t -test? Or , is this going to be unreliable given the data type? My data are graphed below:<a href=\"h... | test for difference between means of two non-normal distributions (poisson or negative binomial) | stats | 2017-06-29T15:35:08.217 |
[
{
"message": "While trying to train different architectures of Convolutional Neural Networks (CNN) for a binary classification task (part of my undergraduate research, the statistical methods gives only 56% accuracy so I gave CNNs a try), there was a very strange thing: a relatively shallow network outperformed... | More shallow network outperformed a deeper one in accuracy? | stats | 2017-06-29T17:29:57.883 |
[
{
"message": "Is the following integral solvable?$$P(X) = \\int^{\\infty}_{-\\infty} \\int^{\\infty}_{-\\infty} P(X|\\mu,K)P(\\mu|K)P(K) d\\mu dK$$with$$P(K) = \\frac{|K| ^{(v-d-1)/2}}{2^{vd/2}|V|^{v/2}\\Gamma_d|\\frac{v}{2}|} e^{-tr(V^{-1}K)/2}$$ (Wishart distribution)$$ P(\\mu|K) = \\frac{|\\lambda_0K|^{1/2... | Unsolvable Integral? | stats | 2017-06-30T13:47:04.213 |
[
{
"message": "Most common convolutional neural networks contains pooling layers to reduce the dimensions of output features. Why couldn't I achieve the same thing by simply increase the stride of the convolutional layer? What makes the pooling layer necessary?",
"role": "user"
},
{
"message": "You c... | Why is max pooling necessary in convolutional neural networks? | stats | 2017-07-01T01:35:52.450 |
[
{
"message": "Suppose we have $\\alpha_1,..\\alpha_n,\\beta_1,..\\beta_n$~$N(0,1)$.Define $x_i = u_i + \\sigma\\alpha_i$, $y_i = u_i + \\sigma\\beta_i$, for $(\\mu_1,..,\\mu_n) \\in \\mathbb{R}^n$, $\\sigma > 0$.Consider the model $(x_1,y_1),..,(x_n,y_n)$, for it we get the likelihood function which will yie... | Confidence Interval for Pairs of Normal Data | stats | 2017-07-01T15:37:20.020 |
[
{
"message": "I am stuck with a problem and hope you people can help me out.In simple words, I have been researching about the impact of input factors on the output.My input factors consists of 8 variables of which 6 are in the form of dichotomous data i.e. Yes/No and 2 are in the form of Likert scale data 1 to... | Correlation between the input factors which are a combination of Yes/No and Likert type scale with the output factor which is the revenue generated | stats | 2017-07-03T06:52:52.080 |
[
{
"message": "I am planning a study and would like to perform a power analysis to design the optimal sampling strategy. I would like to know how samples would be necessary to detect a significant effect.The study is to assess whether there is a significant effect of habitat type on the growth rate of a species ... | Mixed effects model for power analysis to aid study design | stats | 2017-07-03T17:14:36.400 |
[
{
"message": "I need to estimate the probability that an outcome R comes from either the sum (SUM) or from the difference (DIF) of two independent random variables. To do that, I need to compute the conditional probabilities P(SUM|R) and P(DIF|R).Suppose that the elements of the sum of two independent random va... | Derivation of the conditional probability from an mixture of two normal distributions | stats | 2017-07-04T01:48:32.247 |
[
{
"message": "Let $X \\thicksim B(n,p)$ then I would like to evaluate kurtosis and skewness of X.First I want to use the fact that kurtosis $k_3(\\dfrac{X-\\mu}{ \\sigma})=\\dfrac{k_3(X)}{\\sigma^3}$ and skewness kurtosis $k_4(\\dfrac{X-\\mu}{ \\sigma})=\\dfrac{k_4(X)}{\\sigma^4}$.To use above identity, one nee... | Kurtosis and Skewness of Binomial Distribution | stats | 2017-07-04T13:12:01.627 |
[
{
"message": "I m a PhD student in the biomedical field. I have an issue about the use of Pearson correlation coefficent (PCC) in the context of my experimental procedure. I have several slices of tissue where I measured the content, the localization and the intensity of two proteins. So I have obtained two ima... | Pearson correlation coefficent in slices of tissues | stats | 2017-07-04T19:47:19.113 |
[
{
"message": "I looking for examples where someone has graphed the results of a simple linear regression model where the dependent variable is continuous and the predictor variable is categorical with more than two categories.For example, predicting mean temperatures from 3 different types of ovens.I am finding... | Examples of linear regression models where one variable is continuous and one is categorical with more than two categories | stats | 2017-07-04T20:48:12.607 |
[
{
"message": "I'm trying to help a colleague with a proposal to assess the impact of an intervention (let's call that \"Variable A\") and understand why the intervention is working. The intervention has three conditions (one of the conditions is a control group). My friend thinks that the intervention will imp... | Regression to Assess if Change in Variables B & C is related to Change in Variable D...vs. Mediation? | stats | 2017-07-04T22:31:30.000 |
[
{
"message": "There's a deep learning course on Udacity made by Google Brain. One of the course's <a href=\"https://www.youtube.com/watch?v=nqEYVzJLR_c\" rel=\"nofollow noreferrer\">videos talks about validation and test sets size. That video explains that a change in 30 samples is usually significant, but no d... | Validation set and test set size. Significant change in samples | stats | 2017-07-05T13:40:08.593 |
[
{
"message": "I am confused about this. Are they the same? There are some problems in which I am asked to find the Uniformly Minimum Variance Unbiased Estimator (UMVUE) first and then check if it achieves the CRLB. Yet from what I've read, I understand that an unbiased estimator that achieves CRLB is UMVUE. Tha... | Clarification on the difference between the UMVUE and the estimator that achieves CRLB | stats | 2017-07-06T00:23:35.697 |
[
{
"message": "I am comparing two ordinal variables (i.e., two independent Likert items). I've used a chi-squared test to test significance of a relationship between the two, and a Pearson correlation (I'm expecting the two variables to have a linear relationship) to test the strength. I have a sample size of 25... | Ordinal vs Ordinal, correlation vs significance | stats | 2017-07-06T03:08:37.943 |
[
{
"message": "I am working on a Regression model based on Neural Network. I wanted to know about some Parameter Optimization libraries for this purpose other than Grid Search and Randomized Search. The dataset I am using is Mammographic Mass data set. I am using the following piece of code for Randomized Sear... | Parameter Optimization for a Regression Model | stats | 2017-07-06T04:53:01.963 |
[
{
"message": "I have question about the 'setup' for the data for Cox PH survival modelling in case of modelling time to 'breakdown'.My data are houses and roof repair. For each house I have either the age of the house when it was repaired (Event_01=1) or, if was not repaired, the age at the time of sampling (Ev... | Cox PH model and time splitting | stats | 2017-07-06T09:18:19.280 |
[
{
"message": "I know that there is at least another page with inputs on this problem but I have some additional questions not included in them (I think) and I don't know if I should post in that thread instead of making a new one. Anyway, here's the question.I have $X_1,X_2... X_n$ iid $Normal(\\theta,\\theta^2... | Correction factor for the standard deviation | stats | 2017-07-06T09:24:43.260 |
[
{
"message": "I'm trying to cluster my customers in terms of their buying pattern throughout 7 years. Each customer has the quantity they bought at each quarter for 7 years for 10 products. So there are multiple time series for each customer. I would like to cluster customers based on their buying pattern (I al... | Clustering time series when each object has multiple time series | stats | 2017-07-06T14:21:44.967 |
[
{
"message": "I'm being confused about how to interpret my logistic regression and I would appreciate some input on the matter. I work with R's glm.I have one binary response (emerged/not emerged), and two predictors, one continuous (treatment time) and one binary (group, 0 or 1). My n=20 per group per treatme... | Help with Interpretation of a logistic regression | stats | 2017-07-06T17:57:52.657 |
[
{
"message": "My data looks like the following:<pre><code>id x - y (in m) ----------------------- 1 n 100 m 3.09 s 1.12 n 101 m 4.56 s 1.23 n 100 m 2.8 s 0.0084 n 102 m 4.8 s 0.3</code></pre>The value after n indicates the number of samples, the v... | How to compute mean and standard deviation of a set of values each of which is itself a mean and has standard deviation? | stats | 2017-07-07T03:38:04.840 |
[
{
"message": "Why the meaning of doing it that output zero when input is below 0. Is it a good way to calculate the gradient ? Or something else.Thanks.",
"role": "user"
},
{
"message": "Relu activation function is designed to squash the value of it's output to 0 when it's input is below zero.<code>... | Why Relu activity function make the input that is below zero to be zero as output? | stats | 2017-07-07T05:55:42.260 |
[
{
"message": "I believe this question is related to Extreme Value Theory, an area of statistics that I have not studied.Let$X$ and $Y$ be random variablesthe null hypothesis be that $X=Y$ in distribution$\\{X_i\\}_{i=1}^{n_X}$ be a sample of size $n_X$ from $X$ and $\\{Y_i\\}_{i=1}^{n_Y}$ be a sample of size $... | Hypothesis Test: Bound for number of observations from Y that exceed max(X) if X=Y in distribution | stats | 2017-07-07T17:37:42.183 |
[
{
"message": "I am currently reading this paper (<a href=\"http://image.diku.dk/igel/paper/AItRBM-proof.pdf\" rel=\"nofollow noreferrer\">http://image.diku.dk/igel/paper/AItRBM-proof.pdf) on Restricted Boltzmann Machines.On page 22, Given a Markov Random Field $\\mathbf{X} = (X_1,\\ldots,X_N)$ w.r.t a graph $G ... | Transition probabilities for Gibbs Sampling in a Markov Random Field | stats | 2017-07-07T19:58:40.667 |
[
{
"message": "We have $y_1,\\cdots,y_M \\in \\mathbb{R}^r$ vectors. Suppose that the last entry of each vector $y_i$ is $i$, so that the vectors are sorted by the last entry. I solved the quadratic programming problem:minimize $|y_M-y_1-w|^2$ subject to $w^t y_{i+1} > w^t y_i$This is always possible, since t... | Difference is normal distributed, numbers are uniformly distributed | stats | 2017-07-08T12:23:05.363 |
[
{
"message": "I have gathered two sensor data over a 5 minute time period, and Sensor 1 starts misbehaving at point 4000. What are the statistical ways I can figure out which sensor and at which point it starts sending wrong data?<a href=\"https://i.stack.imgur.com/DhVnI.jpg\" rel=\"nofollow noreferrer\">",
... | Anomaly detection of two correlated sensors? | stats | 2017-07-09T15:29:57.113 |
[
{
"message": "Im having a few issues with understanding cross validation and how to apply this to produce predictive models. Im am currently working on Neural Networks (in r) and i'm using the caret package to perform a k-fold cross validation (k=10) on the train portion of my dataset (70% of entire dataset). I... | Cross validation and predicting models in R | stats | 2017-07-10T11:03:33.250 |
[
{
"message": "I have a following time series: <pre><code> 36035 30074 39956 33935 39356 35065 42497 37562 42133 46456 37641 39701 46817 38346 41736 41220 56562 50693 44526 45808 48889 42228 34534 37228 38919 32653 33361 34933 37872 40907 43287 43901 41313 45780 33867 28645 27501 29818 36292 29057 34617 35370 36... | Arima - Tests detect nonseasonality of time series | stats | 2017-07-10T18:28:55.527 |
[
{
"message": "I am building a binary classification model to predict patient admission with respiratory issue in R. Each row in my data set is a patient record. The dependent variable is admit or not(1 or 0), and the features including age, gender, weather info, and air quality info. All the variables are in nu... | How to improve rare event binary classification performance? | stats | 2017-07-11T03:41:18.093 |
[
{
"message": "My DV is count, obtained from psychological questionnaire (14 questions with options ”Yes”/”No”, each yes is 1 point, thus overall result is count of yeses).I’ve checked that Poisson distribution isn’t exactly what I’ve got (data is a bit overdispressed) and NB fits better (in comparison to Poisso... | Negative Binomial „Ancova” with planned contrasts | stats | 2017-07-11T19:00:34.813 |
[
{
"message": "I have 10 studies who look at a surgery for facial paralysis. The main outcome is time to nerve recovery. I have the mean, SDs for the time in months to recovery but obviously there is no control or baseline data. Do I just use zero for the mean and SD for my pre-op values? This gives me a weighte... | Can I perform a meta analysis with my data? | stats | 2017-07-11T19:34:29.550 |
[
{
"message": "Is this expected from Gaussian Mixture Model? Given a perfectly homogenous dataset, the cluster center is not exactly the same as the data point?<pre><code>//Create a vector (180,3)val v = Vectors.dense(180.toDouble,3.toDouble)//Create an array with all the elements set to 'v'val tVrdd = sc.parall... | Spark MLLib Gaussian Mixture Model feature or bug | stats | 2017-07-11T23:23:39.703 |
[
{
"message": "I'm currently performing analysis on a dataset I've retrieved by running an economic experiment. Subjects were either in treatment 0 and 1 and had to perform 'real effort' tasks. That is, they had to indicate how many letters they wished to decode for a certain price. This price was determined by ... | What type of regression analysis to use for data on economic experiment | stats | 2017-07-12T13:07:33.140 |
[
{
"message": "I have some generated data that I want to follow a given Gaussian distribution $N(\\mu,\\sigma)$, and I would like to quantify the distance between the generated distribution and $N(\\mu,\\sigma)$.Specifically, I am generating a set of atomic positions and I want the distribution of the lengths be... | Distance measure between probability density functions | stats | 2017-07-12T16:44:19.737 |
[
{
"message": "I learned about time-dependent covariates in Cox regression in R using the function survSplit of the package survival.I use this as an interaction term for covariates which do not follow the Cox proportionality assumption which works fine.The problem is now, that I want to make predictions for new... | How to make predictions with time-dependent covariates with Cox regression | stats | 2017-07-12T19:43:57.707 |
[
{
"message": "I have psychological data that consists of series of binary choices (e.g., 1001010101) made by research subjects, where 1 and 0 reflect two different options that can be chosen.Are there any known measures of the variation in such sequences?For example, the sequence of 1s and 0s in 0101011010 is m... | measures of sequential variation | stats | 2017-07-12T23:52:13.550 |
[
{
"message": "I want to design a system for product recommendation, where I have the following:~1000 products that are tagged with 1 to ~10 descriptive tags by professional product specialists.~200000 users, that can \"like\" a product (no \"dislike\", no numerical rating), along with buying products (these are... | Designing a simple tag-based recommender system | stats | 2017-07-13T12:12:51.063 |
[
{
"message": "I have read as many questions as I could on model selection, cross validation, and hyperparameter tuning and I am still confused on how to partition a dataset for the full training/tuning process.The scenario: I have 100,000 training instances and I need to pick between 3 competing models (say ran... | How to split dataset for model selection and tuning | stats | 2017-07-13T13:04:13.303 |
[
{
"message": "I searched many posts but could not find a solution to my particular problem. I would like to implement in R a way to measure the association between a dependent variable Y and an independent variable X, and estimate if a treatment influencing both X and Y has an effect when comparing pre- and pos... | Repeated measures in R with both independent and dependent variables changing | stats | 2017-07-13T15:27:17.137 |
[
{
"message": "I'm doing 2-class image classification (determining whether an object is present or absent in images) with CNNs. The dataset is a bunch of photos with continuous timestamps. And I observed that timestamps could be used for prediction as well. For example, in a series of photos, if one image is pre... | machine learning techniques for classifying images with timestamps | stats | 2017-07-13T15:44:54.573 |
[
{
"message": "I hope I'm using the right terms to describe my problem.Let's say I have the following list of numbers: 1,1.6,2,2.6,3,3.7,1000000The last number (1000000) will greatly affect the calculated average and I'd like to somehow \"ignore\" it when performing the calculation (as its value is very differen... | Reducing standard deviation by removing "noisy" items | stats | 2017-07-13T21:05:46.093 |
[
{
"message": "I am currently working with a rounded up values of continuous distribution and I am trying to find out some of its general properties. I have the following model:$y = \\lceil x \\rceil$where $x$ has continuous distribution and $\\lceil x \\rceil$ is a rounded up value of $x$. I am mainly intereste... | Quantiles of rounded up values and rounded up quantiles | stats | 2017-07-14T09:14:36.150 |
[
{
"message": "Looking for a bit of help on how to construct an equation for a linear model when there's a covariate involved.I've been doing a simple lab assay where an absorbance measurement of an indicator can be compared back to a calibration curve of known concentrations of a reaction product to determine t... | Including covariate in linear model equation | stats | 2017-07-14T18:39:56.793 |
[
{
"message": "Suppose I have a random variable $X \\sim Unif(0.61, 0.79)$ and now I'm interested in the mean and variance of $Y \\sim \\log X$. I can easily calculate the mean using the equation,$$E(g(X)) = \\int f_X(x)g(x)\\,dx$$where $f_X$ is the pdf of $X$. For my case this boils down to,$$E(g(X))=\\dfrac{... | Variance Of Uniform Distribution After Log Transformation | stats | 2017-07-14T21:06:06.730 |
[
{
"message": "In the <a href=\"https://www.coursera.org/learn/machine-learning/resources/EcbzQ\" rel=\"noreferrer\">week 5 lecture notes for <a href=\"https://www.google.com.au/url?sa=t&rct=j&q=&esrc=s&source=web&cd=1&cad=rja&uact=8&ved=0ahUKEwic_-Wp_4zVAhXFQpQKHXEUAL4QFggoMAA&am... | Why is sqrt(6) used to calculate epsilon for random initialisation of neural networks? | stats | 2017-07-16T05:13:48.380 |
[
{
"message": "I was checking <a href=\"https://www.kaggle.com/c/titanic/data\" rel=\"nofollow noreferrer\">Kaggles Titanic problem and a common feature processing is playing with <code>Parch</code> (number of parents) and <code>Sibsp</code> (number of siblings/spouses).First they take it as they come.Then they ... | Variable transformation on Kaggle titanic problem | stats | 2017-07-16T16:00:03.000 |
[
{
"message": "I am having some difficulties to understand the difference between:Basis Pursuit DeNoising (BPDN) which is often stated as:$min \\left \\| x \\right \\|_1 s.t \\left \\|Ax-b \\right \\|_2 \\leq \\varepsilon$ (1)but solutions are generally found by solving:$min \\left \\| Ax-b \\right \\|_{2}^{2}... | Basis pursuit denoising (BPDN) and LASSO with a given measurement error? | stats | 2017-07-17T14:04:31.483 |
[
{
"message": "I have done Principal Component Analysis for a scale comprising multiple latent variables. Is it necessary to do Confirmatory Factor Analysis before doing Structure Equation Modelling?",
"role": "user"
},
{
"message": "Discussions of <a href=\"https://stats.stackexchange.com/questions/... | Is it necessary to do confirmatory factor analysis for structure equation modelling? | stats | 2017-07-17T16:53:12.993 |
[
{
"message": "Let's say, I have two math problems (puzzles), like:<br>ProblemA) Solve $ax+b=0$ and<br>ProblemB) Solve $ax^2+bx+c=0$<br>and would like to check how similar they are.<br>I ask 1000 people to solve these two problems, and learn that k people solved both, m - solved only P1, n - solved only P2 and l... | How to test one directional correlations? | stats | 2017-07-18T15:08:51.630 |
[
{
"message": "The <a href=\"http://amzn.to/2lQDmJR\" rel=\"nofollow noreferrer\">Fundamental Theorem of SimulationSimulating$X \\sim f$is equivalent to simulating$(X,U) \\sim \\mathscr{U}\\{(x,u): 0<u<f(x)\\}$The proof is trivial.One thing that is made clear by this theorem is that we can generate X in th... | The fundamental theorem of simulation | stats | 2017-07-18T19:04:29.003 |
[
{
"message": "I am looking to compare individual's scores on different factors which have been computed based on responses to a survey. Specifically, the survey data corresponds to 4 factors, [call them Factor A, Factor B, Factor C, and Factor D] and I would like to know whether any individual, or group of indi... | Comparing Individuals Scores on Different Latent Factors | stats | 2017-07-18T19:47:02.207 |
[
{
"message": "Say we have a sample from two populations: <code>A</code> and <code>B</code>. Let's assume these populations are made of individuals and we choose to describe individuals in terms of features. Some of these features are categorical (e.g. do they drive to work?) and some are numerical (e.g. their h... | Investigating differences between populations | stats | 2017-07-18T20:52:09.233 |
[
{
"message": "I have a set of students with mean height of 100cm with standard deviation of 10cm. I want to be able to qualify a student based on his/her height relative to the mean height for the group. Would it be possible to look at the deviation of a student's height from the mean height for the group in te... | qualifying sample similarity / difference using population standard deviation | stats | 2017-07-19T14:03:24.993 |
[
{
"message": "I am analysing some survey data, but before running some tests I'd like to be sure about the level of measurement of some variables:income group:Below £10,000, £10,000-19,999, £20,000-39,999, £40,000 or aboveAge group:Below 18 years old, 18-25 years old, 26-35 years old etc.Number of travels by tr... | Are these variables ordinal? | stats | 2017-07-19T15:58:32.643 |
[
{
"message": "I collected Likert Item responses to a series of questions. My goal is to demonstrate that some of the groups are different from the others.The dataset has the following format:<pre><code> UserID Group Q1 Q2 Q3 ... --------------------------------- user1 Group_A 5 4... | How to report results based on Likert item group differences? | stats | 2017-07-19T19:30:26.943 |
[
{
"message": "If I have the 10th percentile, mode and 90% percentile for a triangular distribution, how can I find the minimum (i.e. 0th percentile) and maximum (i.e. 100th percentile) of the distribution?",
"role": "user"
},
{
"message": "Using <a href=\"https://en.wikipedia.org/wiki/Triangular_dis... | Defining a triangular distribution based on percentiles | stats | 2017-07-20T00:22:27.777 |
[
{
"message": "I have a theoretical question about CNN. As a reference I'm using: <a href=\"http://cs231n.github.io/convolutional-networks/#case\" rel=\"nofollow noreferrer\">http://cs231n.github.io/convolutional-networks/#caseI'm pretty clear on the RELU layer and Pooling Layers. Those are deterministic and eas... | Confusion about feature maps in CNN -- why don't they learn the same thing | stats | 2017-07-20T06:16:30.600 |
[
{
"message": "I've been asked the following question by a scientist who is not a statistician: Suppose we take a sample $x_1, \\ldots, x_n$ from a population that we can assume is normal (I don't think this assumption is critical). We then calculate the sample mean $\\bar x$ and variance $s^2$. We then take a d... | Question about degrees of freedom in an independent sample t-test | stats | 2017-07-20T07:21:12.047 |
[
{
"message": "Given some Data $X_{1},X_{2},\\ldots ,X_{n}$ we are interested in constructing a $\\textbf{consistent}$ hypothesis test for$H_{0}:\\theta =\\theta _{0}$ vs. $H_{1}:\\theta \\neq \\theta_{0}$. Suppose that there is a weak convergence result such as under $H_{0}$$\\alpha_{n}(T_{n}-\\theta)\\rightarr... | Construct hypothesis test | stats | 2017-07-20T09:11:44.370 |
[
{
"message": "I have a dataset of equal length feature vectors, where each vector contains around 20 features extracted from an audio file (fundamental frequency, BPM, ratios of high to low frequencies etc).I am currently using <a href=\"https://en.wikipedia.org/wiki/Cosine_similarity\" rel=\"nofollow noreferre... | Is feature normalisation needed prior to computing cosine distance? | stats | 2017-07-20T19:52:01.287 |
[
{
"message": "I was reading <a href=\"https://github.com/gmodena/bayesian-changepoint/blob/master/changepoint.Rmd\" rel=\"nofollow noreferrer\">here about change point detection using STAN(bayesian modeling language).In section Discrete sampling gmodena uses simplex as a data type to store probabilities of a mo... | How is Simplex related to statistics at all? | stats | 2017-07-21T03:57:08.203 |
[
{
"message": "I am researching whether an increased number of women in a board of directors has influence on the company's performance.I have conducted a hausman test and am using a fixed effects model.My model includes several uncorrelated independent variables / controls like R&D-Budget, Board size, usw. ... | Can I include a correlated dummy in a Fixed Effects Model? | stats | 2017-07-21T07:54:02.600 |
[
{
"message": "for my research I have a hypothesis containing a categorical IV (positive or negative article that the participants have to read) and a continuous moderator (ideology level of the participant). The x axis is the evaluation that participants are giving (by answering different questions on a 7-point... | Moderation hypothesis (continuous moderator, categorical IV) | stats | 2017-07-21T17:29:36.593 |
[
{
"message": "I trying to understand approximate Bayesian computation (ABC) better so please evaluate my idea to analyse the error in the ABC posterior:Choose arbitrary constant values $\\theta_0$ for model parameters $\\theta$.Generate $n$ sets of synthetic data $X$.Use an ABC algorithm to compute an approxima... | An approach to analyse error in ABC posterior | stats | 2017-07-21T19:21:58.093 |
[
{
"message": "I wish to investigate whether endocranial volume (the volume inside the skull) is normally distributed, ideally with a sample size in the hundreds. Few studies have released their data on this subject, but one has. Hoadley and Pearson (1929) gathered data for the endo volume of some 700 ancient Eg... | Is there a way to correct for continuity for the Shapiro-Wilk test? | stats | 2017-07-21T22:54:34.553 |
[
{
"message": "Let $X \\sim N(0,1)$ and $Y=X$ if $|X|>c$ and $Y=-X$ if $|X|<c$, for any $c>0$.I've already proved that $Y \\sim N(0,1)$.How do we prove that $(X,Y)$ is not a bivariate normal? I've tried proving that $Cov(X,Y)=0$ and because they are not independent, then we reached our desired conclusio... | Proving that (X,Y) is not bivariate normal | stats | 2017-07-22T10:44:56.627 |
[
{
"message": "I have been using a neural network to classify an object as either 'good' or 'defective' (2 classes). It seems to be doing a decent job of it except in certain unforeseen/unexpected scenarios.<a href=\"https://i.stack.imgur.com/4wK6V.jpg\" rel=\"nofollow noreferrer\">For example, in the above imag... | Biasing a trained neural network to a specified category for unexpected inputs | stats | 2017-07-22T11:36:32.573 |
[
{
"message": "I am trying to build a recurrent neural net model using lstm trying to predict future outputs from a financial time series. Outputs are classified in macro classes according to the magnitude of absolute changes.My inputs are the variable i am trying to predict itself plus some other features.I bui... | Use of shuffled dataset for training and validating lstm recurrent neural network models | stats | 2017-07-22T14:01:53.197 |
[
{
"message": "So I understand the bias term as essentially akin to the slope in regular multiple linear regression, my question is how do I add one to my data? Is it as simple as adding a column with all 1's to my training data set?",
"role": "user"
},
{
"message": "Yes, you can add a column with 1'... | How do I add a bias term to my neural net? | stats | 2017-07-24T00:16:40.393 |
[
{
"message": "I am confused about how to apply two-factor ANOVA when I get actually no real data, but only count for each outcome, because the dependent variable is categorical, and is binary (only 0 and 1), and I get the count of 0 and count of 1. The data is like this:<pre><code>Gender | Group | Outcome | Cou... | How to apply Two-Factor ANOVA in SAS when I only know the counts of each outcome? | stats | 2017-07-24T00:18:16.490 |
[
{
"message": "Before running a linear mixed model I transformed my response variable with log(x+1) to get closer to a normal distribution of residuals. Doing so I get these results (for a simplified example):<pre><code> Estimate Upper CI Limits Lower CI Limits p-valuelevel1 0.6518415 ... | Interpretation of linear mixed model with log(x+1)-transformed response variable | stats | 2017-07-24T08:03:52.793 |
[
{
"message": "I am working on a Time Series model, and the series appeared to be non stationary (presence of trend & seasonality), as I was using ARIMA to predict for my time Series , I performed first order differencing.My question is now if I am predicting future values, are the predictions going to be di... | Prediction for differenced Time Series model | stats | 2017-07-24T10:45:57.877 |
[
{
"message": "I'm currently working on sales forecasting. I'm using a Regression Forest to make my forecast. (with MLLib from Spark on Databricks)I'm trying to find what features are useful in my forecasting.Something disturbs me, the standard deviation (STDDEV) of my prediction is really low. For a period of 6... | Optimize a regression forest (Better parameters and how to obtain them) | stats | 2017-07-24T15:10:11.630 |
[
{
"message": "I'm currently trying to learn a bit about neural nets (did Andrew Ng's Coursera course) but have a question I haven't been able to find a good \"rule of thumb\" answer to.Lets say I have the classic data set of house prices, and for input data I have a bunch of data like floor plan area, number of... | Use continuous variables or buckets in neural net? | stats | 2017-07-25T10:03:56.643 |
[
{
"message": "I have read a lot of threads concerning this question but I still seem not to understand the reason we normalize data for PCA. If we normalize the data, every feature is on the same scale. To make use of this normalized data for, say, making similarity prediction, we have to normalize new data and... | Why is PCA normalization necessary? | stats | 2017-07-26T00:37:02.480 |
[
{
"message": "I am trying to explore the Metropolis-Hastings algorithm but I am wondering about the characteristics of this sampling method. It is known about the Metropolized independent sampling that if we designed everything well then for sure it will converge to the target when sample sizes grows to infinit... | A comparison between the convergence of Metropolis-Hastings and INDEPENDENT Metropolis-Hastings algorithm | stats | 2017-07-26T09:34:28.893 |
[
{
"message": "I have an experiment with a continuous dependent variable, and an independent variable with a number of categories, k. The categories come from a randomised controlled trial I ran. There is 1 control group, and k-1 treatment groups.I have created a multiple linear regression with k-1 dummy variabl... | Should I adjust the significance levels in a multiple (linear) regression with dummy variables, when making many comparisons? | stats | 2017-07-26T10:17:12.267 |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.