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 am new in the field of machine learning. So this question may sound silly. We usually use $sigmoid$ in output layer for binary classification. In my experiments, I found that $tanh$ gives higher accuracy and lower binary cross entropy loss if $sigmoid$ is replaced with $tanh$ in the output layer... | Can I use tanh activation function in the output layer for binary classification? | stats | 2018-02-21T12:49:40.243 |
[
{
"message": "My notes are rather light when it comes to this topic. I understand that the bayesian estimator, defined as (for sample space $\\hat{x}$):$E[\\Theta | \\hat{x}] = \\int_{ \\forall \\Theta}yf_{\\theta|\\hat{x}}(y|\\hat{x})dy $ (ie. the mean of the posterior distribution).You can then look at loss f... | Under the 0-1 loss function, the Bayesian estimator is the mode of the posterior distribution | stats | 2018-02-21T16:49:13.073 |
[
{
"message": "I will like to do classifiaction with unsupervised learning where the input is a time series. Each sample consisting of 5000 datapoints.Most people doing time series analysis are interested in forecasting, but I am primarly interested in unsupervised classification (Later I will introduce labels t... | Machine learning in Time series analysis | stats | 2018-02-21T17:05:06.940 |
[
{
"message": "<a href=\"https://i.stack.imgur.com/xvLpZ.png\" rel=\"nofollow noreferrer\">This plot represents the popularity of technologies in two \"tools\", vue and react. In left-top corner are specific technologies for vue but not for react, right-top technologies popular in both tools - you get the idea.F... | Is there a specific name for this plot? | stats | 2018-02-22T10:34:27.783 |
[
{
"message": "I've computed some variable measures using the packages, gbm, randomForest and party. I develop binary classification models predicting survival in cancer patients. Although the gbm package, randomForest package and party package is well described in both CRAN files, vignettes and publications, th... | Scale of variable importance in randomForest, party & gbm | stats | 2018-02-22T12:30:29.997 |
[
{
"message": "I have a set of data about which I would like as a first step, discover some interesting or frequent relationships. For this I know that there are several algorithms, like association or sequence learning or rules. However, I just know FP-growth. Which other alternatives of this algorithms, can I ... | Which is the state of the art regarding methods for Association rule learning? | stats | 2018-02-22T18:44:51.753 |
[
{
"message": "Suppose we have a convolutional neural network trained for task A, and we wish to adapt it for a similar task B. Generally speaking, we preserve the convolutional weights and fully connected layers, and then fine-tune the network for the new task. Further simplifications include freezing the first... | Learning Rates for Finetuning Convolutional Neural Networks | stats | 2018-02-22T19:19:27.580 |
[
{
"message": "I developed two version of the same algorithm to detect and analyze some medical data through iPhone's camera and I want to compare the result in a mathematical way in order to know which algorith gives better results. The results of the test can be : SUCCESS, FAIL or INVALID. I tested 56 samples ... | Exact Fisher Test for testing algorithms | stats | 2018-02-23T09:04:42.267 |
[
{
"message": "I am looking at a panel data with binary outcomes in each year. The ultimate use of the model I build is for prediction. The cross-sections are quite tall (~100,000 non-cases and ~5,000-20,000 cases) but the number of years is few. I suspect that there may be both a time-varying intercept and one ... | How many groups are needed to reliably estimate variance parameters of random effects in a GLMM? | stats | 2018-02-23T12:19:36.143 |
[
{
"message": "I’ve been taught that one of the criteria for being a “confounding” variable is that it should not be a path variable / mediator (ie. not a descendant of, or associated with, the exposure, and is independently associated with the outcome). Adjusting for such a variable would introduce bias.My ques... | Are there any circumstances where adjusting for path variables / mediators is useful? | stats | 2018-02-23T15:46:14.680 |
[
{
"message": "<a href=\"https://i.stack.imgur.com/JJpbt.png\" rel=\"nofollow noreferrer\">In the above image, It is the part of the resNet Architecture, here they have used dotted line to increase the dimension, but my question is How they are increasing the dimension?? or this dotted line is just a convolution... | How resNet increasing the dimension? | stats | 2018-02-23T17:01:31.960 |
[
{
"message": "If i have this linear model$$Y_{i,t}=\\gamma_t(x_i)+v_{i,t}, v_{i,t} \\stackrel{iid}{\\sim}N(0,\\sigma^2), i=1,\\ldots,m.$$$$\\gamma_t(x)=\\beta_{1,t}+\\beta_{2,t}\\frac{1-e^{-\\lambda x}}{ \\lambda x}+ \\beta_{3,t}\\left( \\frac{1-e^{- \\lambda x}}{\\lambda x}-e^{-\\lambda x}\\right)$$Assume that... | maximising a linear model function with unknowns | stats | 2018-02-24T01:26:30.713 |
[
{
"message": "Consider a simple cross-sectional regression model,$$y = \\alpha + \\beta \\cdot T + \\gamma \\cdot x + \\delta \\cdot x \\times T + \\varepsilon,$$where $T$ is a binary randomized treatment indicator, and x is a covariate (say pre-experimental outcomes, or fixed characteristics of the units). The... | What has to be true of controls (main effects and interactions) for them to be included in experimental analysis? | stats | 2018-02-24T01:59:30.407 |
[
{
"message": "Say I have an input tensor like this:<pre><code># images = (?, 28, 28, 1) # MNIST images</code></pre>where the last dimension (the <code>1</code>) is a pixel value (grayscale, so they're numbers on [0-255] for 256 total possibilties).And, accordingly the last layer of the neural network outputs s... | Loss to compare true labels to distribution? | stats | 2018-02-24T15:38:21.367 |
[
{
"message": "Does log-linear regression fall into the class of generalized linear models? Here I'm defining \"log-linear regression\" as the model $\\log(y) = x'\\beta + \\eta$ where $\\eta \\sim N(0, \\sigma^2)$.Thanks.",
"role": "user"
},
{
"message": "Normally, loglinear models for contingency t... | Is log-linear regression a generalized linear model? | stats | 2018-02-25T04:16:52.620 |
[
{
"message": "Before fitting a GARCH model to a process, we should make sure that the process has zero mean. Which test is used in R?",
"role": "user"
},
{
"message": "Testing for zero mean becomes complicated when the observations are not i.i.d. but rather exhibit autoregressive conditional heteros... | How to test whether a GARCH process has zero mean? | stats | 2018-02-26T08:54:39.623 |
[
{
"message": "Assume I aggregated the following results:<pre><code>| Treatment | Count | Total | Proportion ||-----------|-------|-------|------------|| Control | $c_n$ | $c_t$ | $p_c$ || Variant | $v_n$ | $v_t$ | $p_v$ |</code></pre>It seems like I can compute the $z$-score in one of two methods:... | Z-score computing for two sample proportion comparison | stats | 2018-02-26T13:05:24.590 |
[
{
"message": "I am using MCMC with the Metropolos-Hasting algorithm to generate solutions of a non linear regression problem.LikelihoodMy likelihood is a gaussian distribution centered in 0 of the residuals with sigma as the measurements uncertainties.Such as:$l(\\theta|x)= \\exp[ \\frac{-\\sum\\limits_{i=1}^n ... | MCMC: How to choose an efficient proposal distribution with continuous and discrete variables | stats | 2018-02-26T14:22:18.880 |
[
{
"message": "Must a time series be stationary if it has no unit root? I am not quite sure.",
"role": "user"
},
{
"message": "No, roots outside the unit circle gives asymptotic stationarity, not strict stationarity: For a standard ARMA time-series model, the recursive formula for a model locks in t... | Must a time series be stationary if it has no unit root? | stats | 2018-02-27T01:35:06.103 |
[
{
"message": "I've built a lmertree model using the GLMERTREE package with random slope and intercept, a treatment variable, and a \"partitioning\" variable. I've attached a toy dataset and the associated model:Dataset:<pre><code>toy_data<- structure(list(abund_per_night = c(3.5572510116355, 4.01750851327412... | GLMERTREE: confidence intervals for regression coefficients at terminal nodes and implications of fixed effects in lmer/random component | stats | 2018-02-27T05:50:54.877 |
[
{
"message": "I have a test of a skill which will return a value between 0 and 30 for a participant as a measure of that skill. I have five ordinal groups of participants (they are corresponding to university level attainment - first years, honours students, PhD students, etc) and I intend to have a number of p... | Figuring out how many participants I need | stats | 2018-02-27T11:06:45.167 |
[
{
"message": "Maybe it is a basic question, how can I calculate what is the probality the x>=2 based on this data: (95% conf level)<pre><code>Mean 5,954774Standard Error 0,112709Median 6Mode 5Standard Deviation 2,248529Sample Variance 5,055884Kurtosis ... | Calculating probality based on descriptive data | stats | 2018-02-27T11:18:19.057 |
[
{
"message": "We have several time series, which are basiclly chunks of numeric values.We use Dynamic Time Warping to calculate the distance between these time series.This is working well and gives us some distances like 75.397 or 3752.34.Our goal is to have somekind of a threshold to determine when two series ... | Map distance between two time series to a probability | stats | 2018-02-27T15:19:32.933 |
[
{
"message": "Recently I played a bit around with the <a href=\"http://demo.caffe.berkeleyvision.org/\" rel=\"nofollow noreferrer\">Caffe Classification Demo and recognized bad classification results with images of people. I guessed the model is trained with the ILSVRC'12 classification dataset. When looking at... | Why isn't there a person class at ILSVRC'12 classification task? | stats | 2018-02-27T17:37:02.170 |
[
{
"message": "A pdf is usually written as $f(x|\\theta)$, where the lowercase $x$ is treated as a realization or outcome of the random variable $X$ which has that pdf. Similarly, a cdf is written as $F_X(x)$, which has the meaning $P(X<x)$. However, in some circumstances, such as the definition of the <a hre... | What is the intuitive meaning behind plugging a random variable into its own pdf or cdf? | stats | 2018-02-27T19:01:45.333 |
[
{
"message": "I have a dataset with approximately $70,000$ entries and $8$ features. Some of them are ordinal and the rest are nominal. The task is a binary classification task; however, the class I am interested in is represented only by $5\\%$ in my dataset (highly imbalanced classes).Some of the nominal feat... | Handling categorical and ordinal data with highly imbalanced classes | stats | 2018-02-27T23:14:27.513 |
[
{
"message": "I understand Gibbs sampling is a means of statistics inference, and it seems that sometimes certain variables can be integrated out in the sampling process, known as collapsed Gibbs sampling. I really want to know in what circumstances the collapsed Gibbs sampling can be applied, and which variabl... | When can the collapsed Gibbs sampler be implemented? | stats | 2018-02-28T07:24:24.730 |
[
{
"message": "I understand that using $R^2$ in time series models may not be the best as $R^2$ is non-decreasing. I also read this post: <a href=\"https://stats.stackexchange.com/questions/101546/what-is-the-problem-with-using-r-squared-in-time-series-models\">What is the problem with using R-squared in time se... | Showing that R-squared might not be useful in time series data | stats | 2018-03-01T02:40:03.273 |
[
{
"message": "I am a teacher working on a simple research with the aim of studying whether the set of lesson designs I created can improve student performance. I have two groups with 15 students each. I divided them into the two groups making sure that each group has the same number of low, average, and high pe... | Should I use non-parametric tests? | stats | 2018-03-01T05:36:01.823 |
[
{
"message": "My question is more about the methodology. Assuming in some experiment we have measured quantity $y$ per each unit of time $x.$ So $y$ and $x$ form our data set here. Moreover, we know that they are related by apower law type of relation, e.g., $y = D x^{\\alpha},$ where $D$ is just a constant. No... | Extracting power of a power law from data | stats | 2018-03-01T10:52:13.577 |
[
{
"message": "For a classification problem(assume that the loss function is the negative binomial likehood) the gradient boosting (GBM) algorithm computes the residuals (negative gradient) and then fit them by using a regression tree with mean square error (mse) as split criterion. How is that compared to the X... | XGBoost vs Gradient Boosting Machines | stats | 2018-03-01T14:12:04.450 |
[
{
"message": "I am using <a href=\"http://scikit-learn.org/stable/modules/generated/sklearn.ensemble.RandomForestClassifier.html\" rel=\"nofollow noreferrer\"><code>RandomForestClassifier</code> from <code>scikit-learn</code> and I get the following results:\"accuracy of 77%\" with a train/test split 75/25%.\"a... | How to train the final model after cross-validation? | stats | 2018-03-01T15:59:39.387 |
[
{
"message": "I've implemented the following algorithm. For each minibatch:Compute the gradient using the mini-batch sampleUpdate the parametersUpdate the hidden layers. If $\\Gamma_L$ are the new parameters at the $L$th layer, $\\mathbf{X}$ is the input data, and $a()$ is the element-wise activation function... | Should I use the whole dataset in the forward pass when doing minibatch gradient descent? | stats | 2018-03-01T16:33:12.970 |
[
{
"message": "I am looking at if the correlation between the <a href=\"https://en.wikipedia.org/wiki/S%26P_500_Index\" rel=\"nofollow noreferrer\">S&P 500 stock index and the MSCI ACWI has changed over time. I have data from 1990 to 2017. I have split the data by year and have calculated the correlation coe... | How to test if a correlation between two variables has changed significantly over time? | stats | 2018-03-01T19:26:20.613 |
[
{
"message": "The elastic net regularization method and the stepwise method are two well-known methods for variable selection. Recently, I saw an example of variable selection, and in this example, we have a high dimension dataset with high collinearity. The person who has played with this dataset, used firstly... | Is it possible to run the Elastic net then the stepwise? | stats | 2018-03-02T12:21:51.190 |
[
{
"message": "I have data that look like this:<pre><code>amount creator accounts100 john cash, accounts payable325 jane accounts receivable, cash200 john tax account, accounts payable, cash</code></pre>How should these data points be clustered?Thoughts so far:Popular, c... | Clustering numeric, categorical, and multivalue categorical data | stats | 2018-03-02T14:37:16.520 |
[
{
"message": "I have a model in R that includes a significant three-way interaction between two continuous independent variables IVContinuousA, IVContinuousB, IVCategorical and one categorical variable (with two levels: Control and Treatment). The dependent variable is continuous (DV). model<-lm(DV ~ IVCon... | How can I visualise a three way interaction between two continuous variables and one categorical variable? | stats | 2018-03-02T15:08:31.220 |
[
{
"message": "I have a model in R that includes a significant three-way interaction between two continuous independent variables IVContinuousA, IVContinuousB, IVCategorical and one categorical variable (with two levels: Control and Treatment). The dependent variable is continuous (DV). model<-lm(DV ~ IVCon... | How can I visualise a three way interaction between two continuous variables and one categorical variable? | stats | 2018-03-02T15:08:31.220 |
[
{
"message": "Crates of eggs are inspected for faults by randomly removing 4 of the in succession and examining them. If all 4 eggs pass the test the crate ships;otherwise rejected. What is the probability that a crate will shipthat contains 150 eggs, which have 10 have blemishes.Pr(bad egg)=10/150=1/15Pr(bad... | Interesting probability question | stats | 2018-03-05T00:36:59.613 |
[
{
"message": "I want to use a statistical test to show that there is a significant difference between 9 algorithms over 2 datasets. I have read Demsar's paper and used Friedman's test (also used Iman's corrected Friedman test). The test find a p-value of 0.08 which is higher than the 5% threshold thus the null ... | Statistical Test Evaluation? | stats | 2018-03-05T03:59:21.373 |
[
{
"message": "I am doing mixed model analysis to evaluate (Y=) fruit intake (continuous variable) between two groups (intervention versus control) over time (baseline, year 1, year 2, year 5, year 7 and year 15). My model look like this: Y = group + time + group*time. My question regards the baseline measuremen... | Baseline adjustment in mixed models | stats | 2018-03-05T11:19:23.423 |
[
{
"message": "What is people's method of early stopping? I run my validation data against the trained network and if the error is > the previous low error then I increment a counter. If the error < the the previous low error then I record the new low and reset the counter. When the counter hits 3 I stop trai... | Method for early stopping in a neural network | stats | 2018-03-05T15:02:17.057 |
[
{
"message": "I was confused by how LDA (by the original variational inference) can be implemented in a way such that the number of operations for each document $j$ is $\\mathcal{O}(N_j~K)$, where $N_j$ is the unique number of words in $j$ and $K$ is the number of topics. In the original paper by Blei, their in... | latent dirichlet allocation: complexity and implementation details | stats | 2018-03-05T15:40:14.243 |
[
{
"message": "The multivariate t distribution seems to be defined as a \"ratio\" of a vector of normal random variables and a single gamma (or chi-squared) random variable (independent from the vector of normal). Thus, even if the normal rvs are independent (i.e. generated from a multivariate normal with a dia... | Joint distribution of independent t-distributed random variables | stats | 2018-03-05T17:09:26.060 |
[
{
"message": "I have two variables which are highly correlated (0.99). But I want to evaluate their individual effect on the target variables (2 in this case). I don't want to create a latent variable using these two variables because logically they don't belong in the same group.If I use a regression-like mode... | Will Structural Equation Modeling be reliable if I have two highly correlated variables and I know that they cannot share the same latent variable? | stats | 2018-03-05T17:11:33.333 |
[
{
"message": "I've received survey data from a sample of 1000 responses from a choice-based conjoint analysis where a respondent were presented with two cards and had to choose their preferred option. In the survey there were 3 attributes with 4 levels each and the sample was split in to 5 blocks with 10 choice... | Conjoint analysis on split-sample? | stats | 2018-03-05T18:37:02.470 |
[
{
"message": "I'm modeling a quaternary response using multinomial logit. N is about 3000, however, there are only 500 occurrences of the rarest event. My usual go-to sources (Agresti 2013: 207; Hosmer et al 2013: 407-408) suggest as a rough guideline that the number of parameters in the model should not exceed... | Maximum number of categorical predictors in multinomial (polytomous) logistic regression | stats | 2018-03-05T19:46:10.333 |
[
{
"message": "<a href=\"https://www.google.com/search?q=educational-attainment+bachelor%27s-degree+OR+college-degree+(men+OR+male+women+OR+female)+OR+(sex+OR+gender)\" rel=\"nofollow noreferrer\">Reports and webpages like the following prompted this question: \"<a href=\"https://www.census.gov/newsroom/blogs/r... | Significance of relationship between sex and bachelor's degree or higher (2017 U.S. labor force, ages 25 and up) (disparity, difference) | stats | 2018-03-06T09:44:11.633 |
[
{
"message": "For long time I did not understand why the \"sum\" of two random variables is <a href=\"https://en.wikipedia.org/wiki/Convolution_of_probability_distributions#Introduction\" rel=\"nofollow noreferrer\">their convolution, whereas a mixture density function sum of $f(x)$ and $g(x)$ is $p\\,f(x)+(1-p... | Why is the sum of two random variables a convolution? | stats | 2018-03-06T09:46:18.460 |
[
{
"message": "Define $Y_1$ and $Y_2$ to be two positive and independent random variables, for which the pdf (probability density function) is the same and is given as:$f(y) = \\beta \\exp\\left(- \\beta y\\right),\\beta>0$.<br>Suppose that time is slotted, and $t$ ($=0,1,2,...$) is the time index. $Y_1$ is a... | CDF of a function of two random variables | stats | 2018-03-06T14:28:26.990 |
[
{
"message": "I am looking for different modelling approaches which are able to build regression trees (i.e. with continuous input and output variables) with multiple input and output levels.The most common approach (e.g. with CART) is to recursively do binary splits. I am looking for methods that could split t... | Regression trees with multiple input and output levels | stats | 2018-03-07T18:36:44.747 |
[
{
"message": "On Wikipedia, it says:$$R^{2}= 1-{\\sum _{i}(y_{i}-f_{i})^{2} \\over \\sum _{i}(y_{i}-{\\bar {y}})^{2}}$$However, on other sites, R is defined as the following:$$R = { n({\\sum xy})-({\\sum x})({\\sum y})\\over {\\sqrt {(n{{\\sum(x^2)-({\\sum x})^2})(n{{\\sum(y^2)-({\\sum y})^2})}}}}}$$and $R^2 = ... | How come there are two forms to the coefficient of determination? | stats | 2018-03-07T21:23:26.530 |
[
{
"message": "I am using logistic regression for a problem and a colleague suggested trying a MLE solution, with the assumption that some of my features $X_i$ may not have a linear relationship with the target variable $Y_i$. So his idea is that I take my features (assume they are continuous) and \"bin\" them i... | Guidelines for doing Maximum likelihood for nonlinear classification? | stats | 2018-03-08T01:15:34.917 |
[
{
"message": "I would like to know the meaning of an autocorrelation graph of a sine wave. When the time lag is 0, then the autocorrelation should give the highest value of 1 since a copy of the signal is completely correlated to itself. By this logic, after a time equal to the period of the signal, the correla... | Autocorrelation of a sine wave | stats | 2018-03-08T08:24:39.083 |
[
{
"message": "TLDR: Do thin plate regression splines have a probabilistic/Bayesian interpretation?Given input-output pairs $(x_i,y_i)$, $i=1,...,n$; I want to estimate a function $f(\\cdot)$ as follows\\begin{equation}f(x)\\approx u(x)=\\phi(x_i)^T\\beta +\\sum_{i=1}^n \\alpha_i k(x,x_i),\\end{equation}where $k... | Probabilistic interpretation of Thin Plate Smoothing Splines | stats | 2018-03-08T09:36:17.743 |
[
{
"message": "I have fitted a negative binomial regression model to my data, and the summary of this compares latency of 3 resources to that of burrows: <pre><code>NegativeBinomalLatencyModel <- glm.nb(Latency_s ~ Resource, data = Cricket)summary(NegativeBinomalLatencyModel)Coefficients: Estimate S... | Negative binomial pairwise comparison in R | stats | 2018-03-08T16:33:15.500 |
[
{
"message": "I'm working in Python with statsmodels. I have a response variable <code>y</code> and a design matrix <code>X</code> from which I have already removed the most strongly correlated (redundant) predictors. I add a constant and check the VIFs:<pre><code>> from statsmodels.stats.outliers_influence ... | Regression model constant causes multicollinearity warning, but not in standardized model | stats | 2018-03-08T18:11:15.423 |
[
{
"message": "Between the two, should I use a model's training or validation threshold to get best results (from a distributed random forest binary classifier built using <code>h2o.ai</code>) (especially when their values differ by orders of magnitude)? Details:Used <code>h2o flow UI</code> to create a RDF mode... | Training threshold vs validation threshold for better prediction results? | stats | 2018-03-08T21:53:55.960 |
[
{
"message": "Here I have a time series (the dots represent measured data, and the line connecting the dots was just added by excel)<a href=\"https://i.imgur.com/j6NDowH.png\" rel=\"nofollow noreferrer\">https://i.imgur.com/j6NDowH.pngIt clearly goes across 3 different statesFirst is approximately linear, with ... | Change of states identification | stats | 2018-03-08T22:56:38.977 |
[
{
"message": "I have a table of 288 rows and 4 columns where each row corresponds to a tumour sample, and each column is a gene. All of the values are 0 or 1, to indicate whether there's a mutation in a particular gene for a particular sample, but obviously each sample can have more than one mutation.I want to ... | Correlation Test for Non-Mutually-Exclusive Categorical Data | stats | 2018-03-09T11:44:39.810 |
[
{
"message": "I am looking to run multiple t-tests on a dataset but I am unsure if the types of tests I am running would necessitate a multiple comparison correction or not. Below are essentially the tests I will be running:Is profit margin for big customers is less than for smaller customersSame as 1 but just ... | Does this situation necessitate multiple comparison corrections? | stats | 2018-03-09T17:40:11.940 |
[
{
"message": "I'm really sorry if this question is too basic, but I've been looking for a while and haven't been able to find a convincing response. My statistics background is rather poor.Geometric distribution is defined as the probability distribution of the number X of Bernoulli trials needed to get one suc... | Geometric distribution with random, varying success probability | stats | 2018-03-09T20:56:41.143 |
[
{
"message": "I work on a binary classification problem with proteomic data, where the goal is to select the best subset of proteins which contribute to better classification (AUC). However, the problem is that some proteins are missing, and the complete-case analysis results in substantially shrunk data set. A... | Binary classification with multiple imputations | stats | 2018-03-10T01:07:30.470 |
[
{
"message": "<a href=\"https://i.stack.imgur.com/akULr.png\" rel=\"nofollow noreferrer\">I hope someone would be able to shed some light as to why equation 1.33 is the way it is from first principles. It looks a lot like the case where the initial state is randomised but the final state to which the Markov cha... | derivation of probability that an entire species will die out given an initial number k for first generation | stats | 2018-03-10T07:22:08.880 |
[
{
"message": "I am meta-analyzing with multiple effect sizes from each study.The studies included in my meta-analysis measured the effects of participants REPEATDLY with MULTIPLE TESTS. I am trying to deal with dependent effect sizes using three-level meta-analysis. I see, some people use three level meta-analy... | Do I need to know correlations between dependent effect sizes for multilevel meta-analysis? | stats | 2018-03-10T19:00:04.747 |
[
{
"message": "The Feller-Pareto distribution was originally is defined in terms of a transformed beta distribution. If $Y\\sim \\beta(\\gamma_1, \\gamma_2)$ then $W=\\mu + \\sigma\\left(\\left(1/Y\\right) - 1\\right)^\\gamma=W(\\mu, \\sigma, \\gamma_1, \\gamma_2, \\gamma)$ is the five-parameter Feller-Pareto. ... | Are the Feller-Pareto and the generalized beta distributions really the same? | stats | 2018-03-11T07:57:43.580 |
[
{
"message": "Searching this site, I see over 1,000 posts triggered by the search term \"variable importance\", mostly machine learning related. However, I've never encountered the definition before. Is it a term that applies to a specific (set of) model(s)? If so, what does it measure and how is it measured? F... | What is variable importance? | stats | 2018-03-12T13:29:43.220 |
[
{
"message": "<a href=\"https://i.stack.imgur.com/TTFTz.png\" rel=\"nofollow noreferrer\"><a href=\"https://i.stack.imgur.com/cCz9K.png\" rel=\"nofollow noreferrer\">I am trying to forecast hourly wind speeds for a couple of years. My dataset contained trends and seasonality so a applied a difference of 24 to r... | How to determine the order of SARIMA Model? | stats | 2018-03-12T22:47:01.483 |
[
{
"message": "Please refer to an excerpt from a text titled Essentials of Stochastic Process by Durret. <a href=\"https://i.stack.imgur.com/rmCsZ.png\" rel=\"nofollow noreferrer\">Here comes a Lemma, built on the above argument.<blockquote> Lemma: $N\\left ( s \\right )$ has a poisson distribution with mean $\... | probability of a function of poisson random variable | stats | 2018-03-13T04:39:36.647 |
[
{
"message": "say I have two time series that move together but both seem to be characterised by a deterministic trend. I have two questions:How can I test whether the trend is deterministic or stochastic?How would I determine the long-run relationship between the two series in the event they both have determin... | Long-term relation between time series with deterministic trends | stats | 2018-03-13T13:41:00.107 |
[
{
"message": "In the boosting algorithm,AdaBoost ,those observations which were misclassified by the classifier in the (m-1)th step have their weights increased in the mth step, and those which were correctly classified have their weights decreased. My question is, that isn't it possible that the new classifier... | AdaBoost algorithm question | stats | 2018-03-13T17:17:15.033 |
[
{
"message": "I cross-validated a model using the classification accuracy using leave-one-out-cross-validation (proportion of correctly classified cases). Below is a matrix of accuracies typical to what I see. The rows and columns represent different combinations of two hyper-parameters that are cross-validated... | How to choose the model hyperparameter after cross-validation when the model fit indices are really similar? | stats | 2018-03-13T19:33:25.280 |
[
{
"message": "I have a set of $n$ objects for an experiment and I want to randomise them into a control group and treatment group with fixed sizes. I would like to use <a href=\"https://en.wikipedia.org/wiki/Blocking_(statistics)\" rel=\"nofollow noreferrer\">block randomisation to balance covariates, in order... | Best way to do block randomisation with covariates? | stats | 2018-03-13T20:23:13.337 |
[
{
"message": "This is a follow-up to my <a href=\"https://stats.stackexchange.com/questions/333048/kendalls-w-for-a-series-of-answers-about-the-same-phenomenon-in-different-entit/333073#333073\">earlier question. Let me summarise what the original question dealt with. I asked whether I could compute Kendall's W... | Correct interpretation of Kendall's W | stats | 2018-03-13T21:45:17.263 |
[
{
"message": "I have some data that are proportions that I am trying to fit a glm to. As the data are proportions someone suggested that the quasibinomial is the correct family of glm to go for. I am now trying to do the model selection. However, as R does not give AIC scores for quasi models I'm at a bit of a ... | Comparing quasibinomial glms in R | stats | 2018-03-14T10:06:11.930 |
[
{
"message": "Throughout the Snorkel tutorial here <a href=\"https://github.com/HazyResearch/snorkel\" rel=\"nofollow noreferrer\">https://github.com/HazyResearch/snorkel and in the team's related white paper there's references to \"gold labels\", but the term evades definition. What are 'gold labels' in the se... | What does the term "gold label" refer to in the context of semi-supervised classification? | stats | 2018-03-14T14:00:03.050 |
[
{
"message": "After searching here (asking tons of questions), I have now managed to do some initial fitting of my distribution using the <code>fitdistrplus</code> package in R. I need some advise if I am doing this correctly or not or does the analysis make sense. I have date that records percentage of plantin... | Fitting a probability distribution and understanding the Cullen and Frey graph | stats | 2018-03-14T16:46:35.857 |
[
{
"message": "I am trying to predict different products' sales volume where the data includes several products sales volume day for a month as well as a madeup index (a number that determines that products likelihood of selling fast). The data looks like this:<pre><code>Product April 1 Sales April 1 Index ...... | Predicting sales Volume given a makeup index | stats | 2018-03-15T04:31:38.147 |
[
{
"message": "Consider a pairwise Markov random field, for any two neighbours $A$ and $B$, is it correct to use any function to describe the relationship between them? Is there any constraint or any condition that a function needs to be satisfied to be a valid potential function $\\phi(A,B)$?",
"role": "use... | Markov random field potentials | stats | 2018-03-15T05:39:57.560 |
[
{
"message": "I am trying to wrap my head around multiple output of neural networks, especially output of CNN in image classification with localization:Lets say we have CNN with 2 cond layers (conv + pool, conv + pool) and 2 fully-connected (FC) layers. At the end, the last FC layer is connected to softmax laye... | Multiple output of neural network | stats | 2018-03-15T18:18:02.643 |
[
{
"message": "Below is a brief snippet of R syntax. If you run it, you will see that model 2 v model 3 produces the same F ratio in each output. However, model 1 vs model 2 produces different F ratios. My understanding is that these should be the same. Any insights as to what is happening would be appreciated.... | anova() for lm() object returning inconsistent results | stats | 2018-03-16T00:42:52.897 |
[
{
"message": "I already posted the same question on <a href=\"https://stackoverflow.com/questions/49298634/how-to-interpret-results-of-auto-arima-in-r\">https://stackoverflow.com/questions/49298634/how-to-interpret-results-of-auto-arima-in-r but some one pointed to ask it on here. I would appreciate any relevan... | What is the meaning of results produced by auto.arima() function of R? | stats | 2018-03-16T05:33:17.247 |
[
{
"message": "I am working on an example for Benford's law and using UK house numbers I get the following empirical and theoretical distribution for the first digits.<a href=\"https://i.stack.imgur.com/aiARU.png\" rel=\"nofollow noreferrer\">Although the graphical inspection clearly shows that the numbers do co... | References for excess power of a Chi-Squared test | stats | 2018-03-16T09:15:19.373 |
[
{
"message": "The company I work for shares a building with another company, so when we need to access that building, we use a 4-digit access code (which never changed in several years) for the main door, and then an electronic badge to access our own offices and labs.Earlier this week I was entering the code, ... | guessing a 4-digit access code | stats | 2018-03-17T10:44:35.483 |
[
{
"message": "I'm doing some research (I haven't studied anything related to statistics) and I have been stuck for a while now so bear with me:I am trying to simulate data (generate data) based on empirical data.My empirical data is a list of 4276 numbers representing travel times ranging from 143 to 596 minute... | Fitting frequency distribution on unbalanced data? | stats | 2018-03-17T13:01:59.433 |
[
{
"message": "I am finding a model for the change of DNS request between any 2 continuous periods every day. This is used to optimize the work of our data center.Let me take an example here. On the first day of January, from 1 am to 2 am (first period), we capture 1000 DNS request. And from 2 am to 3 am (second... | Model for the change of quantity over time everyday | stats | 2018-03-17T14:37:07.527 |
[
{
"message": "Hello Cross Validated Community, I hope you will help with this one. Below you see my Precision-Recall curves after performing 10-fold Stratified Cross Validation on my dataset.Note that my dataset is imbalanced that's why I'm checking the performance with this curve. Given that I am interested in... | Choosing estimator based on Precision-Recall Curve | stats | 2018-03-17T17:32:29.703 |
[
{
"message": "I have 3-dimensional datapoints I want to cluster. The idea is to do this in an unsupervised fashion with neural networks for a research project. To see how the system performs I'm trying with datasets whose original classes I already know.At first, I train a Kohonen network (SOM) to find potentia... | Which criteria to use to determine cluster centroids? | stats | 2018-03-17T18:30:38.607 |
[
{
"message": "In the book <a href=\"http://amzn.to/2FSUd94\" rel=\"nofollow noreferrer\">Statistical inference by Casella and Berger, given that the pdf of X is $f_X(x) = \\frac{2}{9}(x+1)$ for $-1 \\le x \\le 2$, we want to find the pdf of $Y=X^2$. But it says we are not able to directly use the theorem 2.1.8 ... | Computing directly the pdf of $Y=X^2$ for the pdf $f_X(x) = \frac{2}{9}(x+1)$ | stats | 2018-03-18T07:29:55.197 |
[
{
"message": "I'm using generalized linear models and generalized nonlinear models in a modeling project, so I refer to the final predictor simply as the predictor. But I find that this is confusing and unclear, as you can also refer to the predictor variables as predictors. Is there another way to refer to the... | How to disambiguate predictor and predictor variables? | stats | 2018-03-18T11:40:16.750 |
[
{
"message": "I am working on time series forecasting of monthly averaged rainfall data (from a rainfall subdivision in India) using ARIMA methodology in R. But, in order to improve the forecast result, I want to include the (time series) data from El Niño Sea Surface Temperature (SST) data as an exogenous inpu... | How to fit El Nino SST data (as an exogenous data) in ARIMA modeling in R | stats | 2018-03-18T15:09:30.370 |
[
{
"message": "I'm trying to fit a set of data to a variety of Poisson-based models, and have hit a stumbling block when trying to fit a piecewise-stationary Poisson process. What I mean by this is a Poisson process that has intensity $\\lambda_1$ for time interval $T_1$, then intensity $\\lambda_2$ for the time... | Grid based piecewise-stationary Poisson process test | stats | 2018-03-18T23:52:21.300 |
[
{
"message": "The example below is taken from the lectures in <a href=\"http://deeplearning.ai\" rel=\"nofollow noreferrer\">deeplearning.ai shows that the result is the sum of the element-by-element product (or \"element-wise multiplication\". The red numbers represent the weights in the filter: $(1*1)+(1*0)+... | In a convolutional neural network (CNN), when convolving the image, is the operation used the dot product or the sum of element-wise multiplication? | stats | 2018-03-19T00:45:45.617 |
[
{
"message": "<a href=\"https://i.stack.imgur.com/rPjMp.png\" rel=\"nofollow noreferrer\"><a href=\"https://i.stack.imgur.com/p9Fzl.png\" rel=\"nofollow noreferrer\">hey, I have a dataset that contains hourly wind speeds. When I plotted my original acf, it showed seasonality at every 24 lags so I applied a diff... | How to determine order of sarima? | stats | 2018-03-19T04:37:27.077 |
[
{
"message": "I have a set of data referring to the sales that a company had in the past 90 days.I need to determine the distribution that this data may come from in order to use it in R. If I know the distribution, I can use different functions to generate numbers that respect that distribution (for example, r... | Distribution of sales to generate numbers from that distribution | stats | 2018-03-19T06:38:49.227 |
[
{
"message": "I am hearing a lot about probabilistic programming.Turns out its just a way to specify probabilistic graphical models.Like Tensorflow is to neural networks.So, why use it? Do you know of any place where it has been useful?",
"role": "user"
},
{
"message": "If you ask about software, am... | What is Probabilistic Programming Used for? | stats | 2018-03-19T07:02:50.880 |
[
{
"message": "Question: Suppose that you are testing the idd-ness of a random number generator, and you've done so with the permutation test and the monkey test. Both tests produce a $\\chi^2$ statistic and a corresponding $p$-value. How would you calculate the corresponding standard errors to indicate the accu... | How do I calculate the standard error of the $\chi^2$ statistic? | stats | 2018-03-19T09:03:12.773 |
[
{
"message": "I have a count dataset with mean=3.2, and a little bit Zero-inflated.<a href=\"https://i.stack.imgur.com/QGu6e.jpg\" rel=\"nofollow noreferrer\"><pre><code>X1 X2 X3 YFood3 Low 13 2Food3 High 27 1Food2 Low 13 1Food1 Medium 27 1Food1 High 20 8Food3 Low ... | Why GLM Poisson model predict negative value for count data? | stats | 2018-03-19T10:08:55.517 |
[
{
"message": "I have a question regarding the convolutional neural network known as U-Net (see link below) and hope somebody can help me out. <a href=\"https://lmb.informatik.uni-freiburg.de/people/ronneber/u-net/\" rel=\"nofollow noreferrer\">https://lmb.informatik.uni-freiburg.de/people/ronneber/u-net/In the... | How to implement a weight map for a U-Net | stats | 2018-03-19T17:11:16.270 |
[
{
"message": "When models fitted using REML are compared, the fixed structure needs to be the same between all models. However, when models are fit using ML (to compare fixed effects), does the random structure need to be the same?from Zuur et al. (2009; PAGE 122): <blockquote> To compare models with nested fi... | Mixed model comparison - do the random effects need to be identical for ML comparison? | stats | 2018-03-19T19:02:15.273 |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.