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 having a hard time understanding the process of building a bag-of-words. This will be a multiclass classification supervised machine learning problem wherein a webpage or a piece of text is assigned to one category from multiple pre-defined categories. Now the method that I am familiar with w... | Searching for list of terms using Google in order to build a bag-of-words for a particular category | stats | 2017-05-27T15:24:42.727 |
[
{
"message": "I just stumbled the residuals vs. fitted values plot which suppose to aid checking if the assumptions being made about the error $\\epsilon$ hold.<br>In particular:i. $\\mathbb{E}\\left[\\epsilon\\right]=0$<br>ii. $\\forall\\,\\,i\\,\\,:\\,\\,Var\\left(\\epsilon_{i}\\right)=\\sigma^{2}$ (homosceda... | Estimating error - residuals vs. fitted values plot | stats | 2017-05-27T17:46:01.247 |
[
{
"message": "I have a query about comparing binned data (and the theoretical validity of doing so) and would be very grateful if anyone can help. In one of our experiments, we're detecting the distribution of two types of cells from a feature in histological data. This data is noisy, and in the combined data s... | Comparing normalized histograms - Kolmogorov-Smirnov tests and binning | stats | 2017-05-27T17:57:22.913 |
[
{
"message": "I would like to know if there is a mathematical expression linking the correlations between the predictors and the response variable and the coefficient of determination, $R^2$? For this question, the predictors are all uncorrelated.Intuitively I feel that an increase in the correlation between pr... | Impact of increased correlation on $R^2$ | stats | 2017-05-27T22:11:27.350 |
[
{
"message": "I'm learning about statistics, so I am still a beginner. I was learning about the empirical rule, but I don't really understand it well. I think that it means that when you calculate the standard deviation, 68% of all data points are within that standard deviation. But when I try this on a simple ... | Explain the Empirical Rule on a dataset 1 to 100? | stats | 2017-05-28T02:51:27.873 |
[
{
"message": "My question is really basic, if I have used PCA on some data to get it into lower dimension, is it possible do group data into each separate principal component? E.g. this data \"belongs\" in PC1",
"role": "user"
},
{
"message": "No, you're thinking of PCA sideways. PCA, like many othe... | Is it possible to divide data into separate principal components? | stats | 2017-05-28T17:49:39.887 |
[
{
"message": "I have a dataset with 19 features and one binary label (Error: Yes/No).What I would like to find are the maximum values for each of the 19 features, where crossing them would mean having an unacceptably high risk of the \"Error\" value being a \"Yes\".I'd do this, for example, by calculating the A... | Does finding AUC-based cutpoints for individual variables make sense in a classification task? | stats | 2017-05-28T18:39:55.257 |
[
{
"message": "I have usage data of many machines like this:<a href=\"https://i.stack.imgur.com/JySl4.png\" rel=\"nofollow noreferrer\">In this machine, the usage grows linear with the time. However, in early 2016, someone or something messed with the total usage in hours and the next measurement dropped down to... | How to find and correct y-axis offset in time series? | stats | 2017-05-29T11:44:44.753 |
[
{
"message": "I want to model the effect of treatments (fragmented and continuous forest) on species abundance within three different elevational regions in <code>R</code>, using the <code>lme4</code> package. I'm also interested in differences between elevations, so I included this term in the model as a fixed... | GLMM: Elevation as numerical or factor in model? | stats | 2017-05-29T14:50:23.180 |
[
{
"message": "I am working on a machine learning algorithm which performs a binary classification. I have different features, and I would like to know which of them are better for the classification, I mean what of them really make a difference between classes and what of them are not important.I have thought o... | Machine Learning: Feature Comparison | stats | 2017-05-29T19:18:57.467 |
[
{
"message": "What are other ways of feature selection within a dataset $X$ for classifying a binary response variable $y$. I know such tools as logistic regression / linear SVMs with an l1 penalty, and sparse PCA. Then in the nonlinear category I only know of random forest / extra trees ensembles using feature... | Others ways of feature selection aside from sparcity inducing linear algorithms and or random forests | stats | 2017-05-29T20:39:07.070 |
[
{
"message": "Descriptions of boosting (and specific techniques like gradient boosting) typically talk about \"weak learners\" in general, and then immediately switch to discussing boosted trees specifically.Why is this? I've seen some discussions regarding boosting SVMs, but little to no discussion about boost... | Boosting using other "weak learners" than trees | stats | 2017-05-29T21:27:08.623 |
[
{
"message": "I have measurements the protein level of ~1000 proteins in 10 biological tissues, and have thus performed 10.000 t-tests.I am now doing a meta analysis, and thus using Fishers method to combine the 10x1000 P-values, into 1000 P-values.Obviously I need to correct for multiple hypothesis comparison.... | Fishers method and multiple hypothesis testing | stats | 2017-05-30T11:02:34.337 |
[
{
"message": "I was reading about learning rate change in a machine learning course. The following statement and image appear:Turning down the learning rate reduces the random fluctuations in the error due to the different gradients on different mini-batches.<a href=\"https://i.stack.imgur.com/IW3Cm.png\" rel=\... | Why does reducing the learning rate quickly reduce the error | stats | 2017-05-30T13:57:13.097 |
[
{
"message": "I read that this is because the mean and variance completely specify a normal distribution. However, e.g. for a Poisson distribution the mean, variance and third moment can all be expressed with the same parameter lambda. Is this not what it means to 'completely specify' a distribution?What is an ... | Why is weak stationarity equivalent to strict stationarity only when distribution is normal? | stats | 2017-05-30T23:21:14.550 |
[
{
"message": "Assume that we have a random sample from the log-normal distribution and that we want to test $H_0: \\tau=0$, where $\\tau=\\mu+\\sigma^2/2$. I want to construct the Wald test for this purpose, and I know that the MLE of $\\mu$ and $\\sigma^2$ is $\\frac{\\sum\\ln x} {n}$ and $\\frac{\\sum(\\ln x-... | Hypothesis testing for log-normal distribution | stats | 2017-05-31T17:34:20.060 |
[
{
"message": "I ran an experiment where participants had to perform perceptual tasks and were assigned to 1 of 3 experimental conditions. In two of the three conditions, participants performed that task in groups of size 5. In the last condition, participants performed the task independently. I am trying to mea... | Accounting for dependencies between data points within groups | stats | 2017-06-01T05:56:23.500 |
[
{
"message": "I am trying to predict the number of events happening with the next time window, given the current values of some input variables. I am trying to pick up a good family of distributions to describe this data. Given the nature of the problem, Poisson distribution seems like a good idea. When I plot ... | Exponential-like distribution for positive data | stats | 2017-06-01T09:08:43.943 |
[
{
"message": "This is more of an experimental design question, but the implications are largely statistical, so I'd appreciate some help.I'm running an experiment with traditional experimental and control groups, and we're expecting ~120 participants. The challenge is that it's an educational intervention, and ... | Assigning experimental conditions when subgroups must have the same condition | stats | 2017-06-01T13:10:36.210 |
[
{
"message": "I am testing splitting phone calls to a service between two IVR menu's to determine which messaging is more effective. 80% to the main IVR menu (Group a) and 20% to an alternative (Group b).The data I have is Group a: Total calls, Transfer rate (10,000, 15%) and the same for group b (2000, 10%).I ... | Comparing two proportions with Z-test | stats | 2017-06-02T02:22:26.253 |
[
{
"message": "I have a time series data of accelerometer in X,Y,Z axis. Data is not sampled at a constant sampling rate(but is close to 100 Hz). In the paper I am <a href=\"http://ieeexplore.ieee.org/stamp/stamp.jsp?arnumber=7772142\" rel=\"nofollow noreferrer\" title=\"Fall Detection Using Machine Learning Alg... | Difference between 'Time domain features' and 'frequency domain features'? | stats | 2017-06-02T19:48:57.153 |
[
{
"message": "I've used scipy's <a href=\"https://docs.scipy.org/doc/scipy-0.19.0/reference/generated/scipy.stats.linregress.html\" rel=\"nofollow noreferrer\">linregress function to fit lines through the points in the four panels below. The function outputs a p-value, shown on each panel. The p-values are larg... | Significance of linear fit (not relative to zero slope!) | stats | 2017-06-03T02:32:12.933 |
[
{
"message": "im trying to use a neural network on an extremely simple custom dataset.<pre><code>from sklearn.neural_network import MLPClassifierimport numpy as npimport tflearnfrom sklearn import datasetsX = np.array([[0, 0, 1], [0, 1, 1], [1, 0, 1], [1, 1, 1]])Y = np.arr... | Error trying to put array into neural network | stats | 2017-06-03T04:01:30.800 |
[
{
"message": "We define Likelihood as follows:$$ \\mathcal{L}(\\theta | X) = \\prod P(x_{i}|\\theta) $$Question: How to assume the probability function $P$, specially in case of complex dataset?I understand that if we are doing a Coin Toss, I can assume $P$ to be Bernoulli. But what if my dataset is complex (ex... | How to assume the Probability function that will be used in Likelihood | stats | 2017-06-04T01:25:53.700 |
[
{
"message": "Suppose $(x_i,y_i)$ constitutes supervision data. Assume a collection of statistical methods which could be trained on one subset and ranked by their accuracy on another subset of this data (according to some loss function). But we are not going to train directly on $(x_i,y_i)$. Instead suppose $(... | Can I re-weight the a training data set to make it more relevant in the selection of algorithms for use on a slightly different data set? | stats | 2017-06-04T03:17:57.973 |
[
{
"message": "I have a coarse and noisy image data taken from two different but geometrically similar samples (pixel size are all the same). I want to prove that there is a statistically significant differences between the images from the two samples.What I am thinking is calculating cross-correlation, and cond... | Combination of cross-correlation and t-test | stats | 2017-06-04T03:19:33.203 |
[
{
"message": "I have fit a GLM poisson regression model. Then i detected overdispersion, which was the reason that I have decided to fit a Negative Binomial model:<pre><code> # oversidpersion check dispersiontest(poismodel, trafo = 0) dispersiontest(poismodel.t, trafo = 0) # there is evidence of overdispers... | glm poisson regression - regressors selection | stats | 2017-06-04T10:22:39.857 |
[
{
"message": "I was reading the <a href=\"http://shop.oreilly.com/product/0636920033400.do\" rel=\"nofollow noreferrer\">bookI came across the conditional probability. The statement is:<blockquote> Imagine a certain disease that affects 1 in every 10,000 people. And imagine that there is a test for this disea... | How does P(T|D) + P(T|~D) = 1? | stats | 2017-06-04T10:56:46.737 |
[
{
"message": "I have two matrices $A_1$ of size $N\\times K$ and $A_2$ of size $M\\times K$ which contain data and every row has a corresponding label $y \\in {1, 2, 3}$. I want to learn a mapping between those two matrices $A_1$ and $A_2$. Is it possible to do it using some machine learning technique? For exa... | Learn a mapping between two datasets using Neural Network | stats | 2017-06-04T13:34:00.400 |
[
{
"message": "I have these variables in my data set:a categorical variables with 5 levels (<code>Country</code>)<code>sex</code>a continuous variable (grade)different continuous variables as dependent such as <code>y1,y2,y3,...,y25</code> (I have 25 columns and each column is one dependent variable)Research que... | Which statitical modeling in more appropriate when there are several yi? (MANCOVA,Multivariate regression, canonocal correlation) | stats | 2017-06-04T14:02:17.847 |
[
{
"message": "I would be very grateful for any suggestions and help regarding the creation of a linear mixed model with lmer4 package and the lmer function.I have created an experiment which randomly assigned participants into 8 different conditions. Each condition presented a short video with an actor. The act... | Is lmer model specified correctly and is it a suitable approach here? | stats | 2017-06-04T17:43:38.703 |
[
{
"message": "It is inherently impossible to know the probability distributions of random variables we might encounter in the \"wild\" -- that is the reason why researchers have to take samples.However, since the underlying distribution is inherently a \"black box\", it seems like an ideal analysis would make a... | Why is it assumed by default that distributions in nature satisfy the CLT? | stats | 2017-06-04T18:29:14.517 |
[
{
"message": "I'm working on a computational biology project, and my professor has given me data for over 1,000 enzymes (represented by a numerical index), namely average solubility, count (number of enzymes of each type), and standard deviation. I'm having some trouble determining how to best graphically summa... | How to present data in a large dataset (x is categorical, y is quantitative)? | stats | 2017-06-04T19:03:27.607 |
[
{
"message": "I'm working on a computational biology project, and my professor has given me data for over 1,000 enzymes (represented by a numerical index), namely average solubility, count (number of enzymes of each type), and standard deviation. I'm having some trouble determining how to best graphically summa... | How to present data in a large dataset (x is categorical, y is quantitative)? | stats | 2017-06-04T19:03:27.607 |
[
{
"message": "<a href=\"https://i.stack.imgur.com/iytV8.png\" rel=\"nofollow noreferrer\">I don't understand why my answer is wrong. My understand of likelihood is the P ( Data | model). For example, if the model is that a coin is fair, and the coin was flipped 10 times and came up heads 6 times, then the likel... | 2 more questions regarding Bayes Theorem | stats | 2017-06-05T05:10:45.300 |
[
{
"message": "I search for a way to model future commodity prices, like heating oil and natural gas. It doesn't have to be very sophisticated, but rather easily to implement.Does anybody know a suitable approach? After theoretical examination, I plan to apply it to real data in R. Thus, implentation in a R pack... | Forecast/predict commodity prices | stats | 2017-06-05T11:52:05.030 |
[
{
"message": "Suppose $ \\{ X_i \\}_{i=1}^{T}$ are states of a markov chain and let $P_{\\theta}(X_1, ..., X_T)$ be the probability of observing the path when $\\theta$ is the true parameter value (a.k.a. the likelihood function for $\\theta$). Using the definition of conditional probability, we know $$ P_{\\th... | How to correctly interpret the likelihood function of a Markov Chain, $P_{\theta}(X_1, ..., X_T)$ vs $P(X_1, ..., X_T|\theta)$? | stats | 2017-06-06T00:18:21.100 |
[
{
"message": "I've always had trouble understanding ANOVA (regressions make much more sense to me, and are more powerful, so why bother with ANOVA?). But I've been reading a book on the history of the gene-environment interaction debate, and I wanted to make sure I understand how ANOVA works. So let's constru... | Confusion interpreting ANOVA sum of squares | stats | 2017-06-06T21:29:31.927 |
[
{
"message": "I have been doing AB tests for quite a while. I use either a <a href=\"https://docs.scipy.org/doc/scipy-0.19.0/reference/generated/scipy.stats.fisher_exact.html\" rel=\"nofollow noreferrer\">Fisher Exact Test or a <a href=\"https://docs.scipy.org/doc/scipy-0.14.0/reference/generated/scipy.stats.tt... | Resolving Power in an AB test | stats | 2017-06-06T23:22:35.660 |
[
{
"message": "<blockquote> I'm trying to understand how to perform meta-regression treating each arm of studies in my data as an individual study with a single proportion as the outcome. I have read through the documentation for the R package metafor, but have only found the option to estimate using relati... | Meta-regression of a single-arm study with proportion outcome in R | stats | 2017-06-07T04:34:32.370 |
[
{
"message": "I have a situation where I have two sets of apples. I want to show that one batch has more problems than the other. How could I go about doing it?The problems are things like: \"Mold\", \"Worms\", \"Rotten\"So far I looked at each apple and gave it a score where each instance of a problem count... | Can you average categorical variables and then perform a two sample t-test? | stats | 2017-06-07T15:51:33.477 |
[
{
"message": "I have a binary outcome fit by a logistic model with a continuous independent variable that is logged to ensure a linear rather than exponential relationship to the dependent variable. I have included the second order term as it appears the fit is improved overall. The resulting formula is:<code>f... | How to calculate the probability of a logistic model with higher order terms | stats | 2017-06-07T16:36:15.933 |
[
{
"message": "I have two vectors that look like this:<a href=\"https://i.stack.imgur.com/blH9p.png\" rel=\"nofollow noreferrer\">I would like to make a significance test on the paired differences between the two vectors, as well as measure association.The process of data generation is \"known\" to generate log-... | how to choose a transformation for left heavy tailed data due to arbitrary upper limit imposed by experimenter? | stats | 2017-06-07T19:26:20.217 |
[
{
"message": "I notice that after normalizing a variable by firm size (to control for firm size), the variance of that variable goes up. I was expecting the variance to go down in fact. Does this mean that I should not normalize by firm size?",
"role": "user"
},
{
"message": "Let me restate your que... | Increase in the variance of the variable after normalizing by firm size, right or wrong? | stats | 2017-06-07T22:50:47.740 |
[
{
"message": "After looking at <a href=\"https://stats.stackexchange.com/questions/263211/trying-to-emulate-linear-regression-using-keras\">This question: Trying to Emulate Linear Regression using Keras, I've tried to roll my own example, just for study purposes and to develop my intuition.I downloaded a simple... | Simple Linear Regression in Keras | stats | 2017-06-08T05:40:19.057 |
[
{
"message": "Text of the problem I have to solve..State the generic case of a Bayesian treatment of the parameters $\\theta$ used to model the data, i.e., $p( \\theta | X, Y)$. Derive the estimate of the mean, assuming that the model of the output variable is a Gaussian distribution with a fixed variance.... | Bayesian inference of mean of Multivariate Gaussian | stats | 2017-06-08T08:58:47.353 |
[
{
"message": "I am fitting a linear mixed effect model to study the interaction of two independent variables, a covariate time and a factor m (levels \"R\" and \"V\"), on the outcome variable var. Data are grouped by the variable id, and I consider the intercept for each group as a random variable. In particula... | post-hoc test on linear mixed effect model | stats | 2017-06-08T17:20:15.897 |
[
{
"message": "The parameters for a skipgram classifier are defined like this:<a href=\"https://i.stack.imgur.com/MWn3y.png\" rel=\"nofollow noreferrer\">Why are there two separate vectors, <code>u</code> and <code>v</code>?",
"role": "user"
},
{
"message": "They CAN be the same, and some recent work... | Why are skipgram parameters defined in terms of two vectors | stats | 2017-06-09T14:01:57.923 |
[
{
"message": "I am solving the following problem:<blockquote> An electronic tablet producer claims that the batteries on their tablets lasts for 10 hours but from my experience I think it is less than that. It is known that the battery life-span follows an exponential distribution. A random sample of size 1... | How to deal with critical value hypothesis test when test statistic is negative? | stats | 2017-06-10T05:17:45.947 |
[
{
"message": "I have modelled a lasso regression for a set of features.The model looks suspiciously very good.The $R^2$ is about $0.98$ and the $RMSE$ is $0.03$ for the $y$ (the predicted value) ranges from 1 to 3000.Such good result makes me feel that there is something wrong, given that I did testing on a sep... | Goodness of the regression model with very high $R^2$ and very low RMSE | stats | 2017-06-10T14:13:15.263 |
[
{
"message": "The purpose of the paper was to optimize some parameters by maximizing the regularized log-likelihood. Then they calculate Partial derivatives.And then authors mention that they optimize the equation using L-BFGS, a standard quasi-Newton procedure to optimize smooth functions of many variables (no... | How does the L-BFGS work? | stats | 2017-06-11T02:55:37.670 |
[
{
"message": "I have a question regarding Bayesian Hypothesis testing using \"Bayes Factors\".Does weighting the Likelihood Ratios by a prior give the Likelihood ratios any property (e.g., removing conditionality on Hypotheses, changing p(Data | Hypothesis) =to=> p(Hypothesis | Data) etc.) that Likelihood rati... | Does weighting the Likelihood Ratios by a prior give the Likelihood ratios any Bayesian property? | stats | 2017-06-11T17:48:24.047 |
[
{
"message": "What is the difference between interaction and association? (It would be great if someone explains it to me by a plot or example). Can we have interaction between two continuous variables? Also, do I need to bring the interaction among the variables into the model? if yes, Why?",
"role": "user... | Interaction vs Association | stats | 2017-06-11T20:02:23.953 |
[
{
"message": "I have a data set that is transformed to stationarity and I'm trying to fit it to an ARIMA model. I found that variance is lowest when the transformed set is differenced to 1, and here are my ACF and PCF plots for that:<a href=\"https://i.stack.imgur.com/kabfE.png\" rel=\"nofollow noreferrer\"><a ... | auto.arima() fits a different model than ACF/PACF plots suggest | stats | 2017-06-11T20:18:15.150 |
[
{
"message": "According to the Wikipedia article <a href=\"https://en.wikipedia.org/wiki/Likelihood_function\" rel=\"nofollow noreferrer\">Likelihood function, the likelihood function is defined as:$$\\mathcal{L}(\\theta|x)=P(x|\\theta),$$with parameters $\\theta$ and observed data $x$. This equals $p(x|\\theta... | Why do people use $\mathcal{L}(\theta|x)$ for likelihood instead of $P(x|\theta)$? | stats | 2017-06-11T22:21:45.523 |
[
{
"message": "I have a time series data structure in the form:$$ \\stackrel{\\mbox{Time $t$}}{% \\begin{bmatrix} 0 & 1 & 0 & 0 & 1 & 1 & 1 & \\dots & p_{t} & p_{t+1}\\end{bmatrix}}\\$$where each entry is a binary result for some task, I would like to know if it is pos... | Predicting outcome of binary data | stats | 2017-06-12T00:33:23.547 |
[
{
"message": "I was wondering if we need to use adjusted P-values when we use several multiple regressions (same independent variables and covariates, but different dependent variables)? Also in multiple comparisons test, (bonferroni/Tukey) are based on adjusted p-value or we need to calculate it by ourselves?"... | Adjusted P_values | stats | 2017-06-12T04:11:54.120 |
[
{
"message": "Recently I got an interesting dataset, it looks like this:| user | ip_set | label|| user1 | {ip1,ip2,ip3,ip4} | 0 || user2 | {ip1,ip2...} | 1 |The purpose is to classify user using ip_set, but I don't know how to extract features from it. Do you guys have any idea?... | How can I deal with dictionary-like data for classification？ | stats | 2017-06-12T07:30:51.063 |
[
{
"message": "(My background: physicist rusty on statistics, evaluating an experimental dataset).I'm studying a dataset with a random variable $X$, which is approximately normally distributed with standard deviation $\\sigma$. I compute the sample average $Y =\\sum \\frac{X_i}{N}$ and standard error in the mean... | Confidence interval for a folded normal distribution | stats | 2017-06-12T08:24:19.913 |
[
{
"message": "So I have 4 columns of data, shown below. The first column is the independent variable and the next 3 columns are the values of dependent variables.<pre><code>1 223064 222724 2226722 220066 219400 2192983 217105 216128 2159784 214105 212906 2127095 211295 209732 209492</code></... | How can I calculate relative difference among 3 columns? | stats | 2017-06-13T03:48:00.637 |
[
{
"message": "My understanding is when we are computing sufficient statistics on a stream, when a new instance arrives, the value of the new instance is added to the already computed sufficient stats. so there is no way of forgetting/decrementing any data since the value of all the current data is summarised in... | Is it possible to forget data when computing sufficient statistics on a stream? | stats | 2017-06-13T08:44:14.780 |
[
{
"message": "I'm trying to run a mixed-effects analysis on some data that I have, but cannot determine if I am using the correct model.First, I am trying to determine if there are between-group difference in 5 independent variables. My data consists of a number of participants who performed 31 different tasks ... | Mixed effects model for group differences in R | stats | 2017-06-13T12:33:23.650 |
[
{
"message": "Apologies if this is confusing at all, I'm very unfamiliar with geometric means. For context, my data set is 35 month-end portfolio values. I found the month to month growth rate [Month(N)/Month(N-1)] - 1, such that I now have 34 observations and would like to estimate a month end value using the ... | How to calculate confidence interval for a geometric mean? | stats | 2017-06-13T18:04:27.233 |
[
{
"message": "Currently, I have made an ARIMA model and to validate it I have studied the autocorrelation (ACF and PACF) of residuals and also a Box-Pierce test.But I am having doubts about how to validate a model made using ARTIFICIAL NEURAL NETWORKS.Should I treat it as an ARIMA model and study residuals in t... | How to validate an ANN model? | stats | 2017-06-13T22:47:07.083 |
[
{
"message": "I was following <a href=\"https://www.analyticsvidhya.com/blog/2015/02/avoid-over-fitting-regularization/\" rel=\"nofollow noreferrer\">https://www.analyticsvidhya.com/blog/2015/02/avoid-over-fitting-regularization/ to figure out the basic understanding of regularization in machine learning applic... | doubt regarding regularization in linear regression | stats | 2017-06-14T05:41:21.797 |
[
{
"message": "Suppose I have a task. I recruited 100 people to do the task, each performed the task 5 times and I scored them. In total, I have 500 scores.I have an independent variable (well, let's say how much money I paid for each time one person do the task - it doesn't matter) so I want to perform a linear... | How to deal with collinearity in a correct way in regression? | stats | 2017-06-14T08:17:48.320 |
[
{
"message": "I have the following dataset:<pre><code>d = structure(list(x = c(23.1073083778966, 22.9362216327734, 24.4504147133069, 24.7226685133887, 23.2710364752618, 22.5253827558421, 23.545305003427, 23.7449683042789, 24.8139647577093, 22.8804536162757, 24.3948588709677, 25.4304112554113, 25.550081967... | Why is my nonlinear least squares confidence band so wide? | stats | 2017-06-14T20:43:49.510 |
[
{
"message": "Lets say I have a set of N items, and I want to choose the best one.Each item is represented using 6 feature.I could fix N but it would be nice if it can vary.The \"best choice\" might depends on what other item is present in the setIs there a way to formulate it?",
"role": "user"
},
{
... | How can I formulate a "choose 1 from N" problem into a machine learning model? | stats | 2017-06-15T03:16:57.847 |
[
{
"message": "Below (in R), I have two INDEPENDENT groups of scores that are binomially distributed. These two groups of scores are known to have different probability of success (i,e., $p_1 \\neq p_2$). Let's now assume two scenarios regarding the probability of success within each group: (1) The probability ... | Comparing two groups with binomially distributed data | stats | 2017-06-15T05:44:48.813 |
[
{
"message": "how exactly is partial derivative different from gradient of a function?In both the case, we are computing the rate of change of a function with respect to some independent variable. While I was going through Gradient Descent, there also the partial derivative term and the gradient were written an... | gradient versus partial derivatives | stats | 2017-06-16T08:29:02.237 |
[
{
"message": "In the paper Deep Survival Analysis (Ranganath, 2016), the author specifies a generative model for deep survival analysis. Say $\\mathbf{x}$ denotes the set of covariates, $\\mathbf{\\beta}$ the parameters for the data with some prior $p(\\mathbf{\\beta})$, $k$ a fixed scalar, and $n$ be the index... | How to make predictions with the posterior predictive distribution? | stats | 2017-06-16T09:40:45.133 |
[
{
"message": "My data set contains few varibales which I converted to factor as I wanted them to be in that format. To start with, I wanted to check the importance of each variable and check for multicollinearity. But when I run code, I get NA values for all those factor variables.<a href=\"https://i.stack.imgu... | VIF doesn't show up values for categorical variables | stats | 2017-06-16T12:56:06.757 |
[
{
"message": "I am trying to make a model using GLMMparts of data as follow (it is a ten years data,just post parts )<pre><code>id year distance1 sum1 sum1 2006 183.21 5148 3.71 2 2006 442 1360 3.13 3 2006 187.33 11455 4.06 4 2006 795.74 287 2.46 5 2... | asking for help with question for rescale variable in R | stats | 2017-06-16T13:16:39.350 |
[
{
"message": "I am trying to estimate the user ability (success or fail) using item response theory. So, I am re-implementing an algorithm from <a href=\"https://link.springer.com/chapter/10.1007/11774303_47\" rel=\"nofollow noreferrer\">this paper but I can not understand the following line:<a href=\"https://i... | Estimating user ability (success or fail) using maximum likelihood and Item response theory | stats | 2017-06-16T13:53:36.247 |
[
{
"message": "I am currently working on my master thesis and need help. Basically, the correlation is not significant in most of the cases (except the one between the 2 DV).Despite this, I got a significant interaction between the IV and Moderator using the PROCESS macro for SPSS.My assumption is that the insig... | Significant interaction and not significant correlation | stats | 2017-06-16T18:07:46.803 |
[
{
"message": "I have a two-factor shot noise process as follows (sorry for the picture of text):<a href=\"https://i.stack.imgur.com/QkxML.png\" rel=\"nofollow noreferrer\">I want to simulate from this process. Is it valid to do so in a discretized way? The solution to these SDEs is a compound Poisson process, s... | Is it valid to simulate a shot noise Poisson process with discretization (R) | stats | 2017-06-16T20:37:27.593 |
[
{
"message": "I have made some research and I acquired the following data:40 \"packs\" of dataeach \"pack\" contains 10 scores of variable A and 10 scores of variable BA is always 1,2,3,4,5,6,7,8,9,10B is a measurement result and scores in 0-100%My thesis is: the higher A, the lower B.Now, having all this info,... | Should I draw the conclusions from average or individual data? Is this approach using Pearson CC correct? | stats | 2017-06-17T13:07:35.137 |
[
{
"message": "I recently touch the idea of <a href=\"https://en.wikipedia.org/wiki/Generative_adversarial_networks\" rel=\"nofollow noreferrer\">Generative adversarial networks, which is a competition between a generative network and a discriminative network.This idea makes me think of replacing the word \"netw... | Regression vs. classification and generative vs. discriminative | stats | 2017-06-17T16:27:16.610 |
[
{
"message": "Financial returns have been shown to follow leptokutotic distributions, however volatility forecasting models like EWMA and DCC-GARCH assume conditionally (dependent on time) Normal distribution for returns.Can anyone explain why? Especially when financial return distributions are clearly not norm... | Normal vs leptokurtic distribution for financial returns | stats | 2017-06-17T16:35:25.410 |
[
{
"message": "A clinical trial is being planned, in which the primary outcome is binary (success/failure). There are two treatment groups (treatment/control). The aim of the trial is to show that the treatment is better. The outcome is bad, meaning that in the treatment group, we wish to have a smaller proporti... | Fisher's Exact Test, Relative Risk or Odds Ratio? | stats | 2017-06-17T18:04:41.143 |
[
{
"message": "A clinical trial is being planned, in which the primary outcome is binary (success/failure). There are two treatment groups (treatment/control). The aim of the trial is to show that the treatment is better. The outcome is bad, meaning that in the treatment group, we wish to have a smaller proporti... | Fisher's Exact Test, Relative Risk or Odds Ratio? | stats | 2017-06-17T18:04:41.143 |
[
{
"message": "Forgive me if this a too much of a beginner question but I am PCA algorithm on a dataset with having a hard time understanding the implemenation of PCA on a dataset with 18 features. These are the questions I have regarding this:PCA normally reduce the dimensionality from n to k. In my case, the ... | How to implement PCA? | stats | 2017-06-18T00:24:10.703 |
[
{
"message": "I have a list of categorical data and I want to apply an unsupervised classification method to cluster this data.Which method could be used?Example: <blockquote> gene1 gene2 gene3 gene4 gene5 gene6 gene7 gene8</blockquote>My goal is to cluster these genes. Could anyone sugges... | Which unsupervised classification method can be used for categorical data? | stats | 2017-06-18T06:51:34.623 |
[
{
"message": "I have time series data that reflects users activity on some platform, and it has clear daily seasonal pattern. I understand that in order to fit a model such as ARMA to this data I should first detrend it and remove its seasonal component, which is commonly performed using differencing. This shou... | How to make time series data with changing variance stationary? | stats | 2017-06-19T13:38:49.453 |
[
{
"message": "How can i recover μ and σ for the lognormal distribution (income) knowing mean GDP per-capita (which should be my μ) and the Gini coefficient with data on 5 quintile income shares? Thanks to all.σ is a number. In the formula for σ = 2/ erf (g), erf is a function defined for values of x that I do n... | Lognormal parameters knowing GDP per-capita, Gini coefficient and quintile shares | stats | 2017-06-19T14:02:35.587 |
[
{
"message": "I understand the Bayesian regression approach, in which I compute the posterior distribution of the parameters $\\theta_i$. Now I am interested in how to compute the credible intervals of the regression curve: $$y=x_0+\\theta_1*x_1+..+\\theta_n*x_n$$In a frequentist setting, a prediction interval ... | Computing Bayesian Credible Intervals for Bayesian Regression | stats | 2017-06-19T16:27:51.987 |
[
{
"message": "Pretty much a complete newbie with PLS, Python, stats, (and stackexchange), sorry:When using sklearn for PLSRegression, why is the resulting scores matrix not given by the product of (scaled) input and the weights matrix?I.e. T = X0 * W Minimum working example showing this is given below.I have fi... | Python - sklearn PLSRegression: why is T != X0*W (scores, scaled data, weights, respectively) | stats | 2017-06-19T18:06:38.093 |
[
{
"message": "I am trying to maximize a function $f(x)$ of a vector of reals $x=<x_1, x_2, ...x_n>$. In my practical application, I have no expression for $f$ whatsoever, all I can do is given a vector $x$, calculate $f(x)$ via a deterministic experiment.So, instead of having to set a step size $\\alpha$,... | Does this gradient descent make sense? | stats | 2017-06-20T03:34:20.570 |
[
{
"message": "Can someone give me more insight about the meaning of the fitted values in ARIMA model (i.e. $y_{ob,t}-\\epsilon_{t}$? It seems to be not very useful for ARIMA, while checking the stationary assumption using the residual is more important. It also does not mean the expected value of $y_t$, since A... | What is the meaning and usage of the fitted value in ARIMA models? | stats | 2017-06-20T08:39:58.670 |
[
{
"message": "I have about 150 samples 1000 features (ranked by their importance by Relieff score). My question is, what would be the best approach to:choose the hyper parameterschoose the optimal number of features to use report the accuracy of my model using SVM and kNN (I don’t intendto choose which one of t... | Feature selection: is nested cross-validation needed? | stats | 2017-06-20T12:50:45.333 |
[
{
"message": "In glmnet using caret my the model is trained and tuned by cross validation on my training set. I have a 10 fold cross validation, over a grid of 10 alphas and 10 lambdas. The best model chosen by glmnet is the model with the combination of alpha and lambda which has the best performance. This per... | Elastic net beta coefficients using Glmnet with Caret | stats | 2017-06-20T21:58:57.850 |
[
{
"message": "Given the comments below, I reformed my questions with more background information and simulation/examples. My question also includes the validity of the method in theory. Please correct me if any statement is not accurate.Background: 1) For our client (policy makers), it is often interesting for ... | Decompose a time series data into deterministic trend and stochastic trend | stats | 2017-06-20T22:37:44.457 |
[
{
"message": "Hi I'm studying regression techniques.My data has 15 features and 60 million examples (regression task).When I tried many known regression techniques (gradient boosted tree, Decision tree regression, AdaBoostRegressor etc) linear regression performed great. Scored almost best among those algorithm... | Can Tree-based regression perform worse than plain linear regression? | stats | 2017-06-21T04:10:32.043 |
[
{
"message": "I was taking an online course and saw linear regression being by gradient descent The intuition behind why the method would work seemed plausible.I tried understanding normal equation as to why setting individual partial derivates to 0 and solving the equations give the optimal values of theta, bu... | Proof of correctness of normal equation | stats | 2017-06-21T09:05:17.107 |
[
{
"message": "I am new to time series analysis and I am trying to model a time series.I know there are similar questions but I could not figure out the solution to my problem. I have a time series like the one below (Blue color).<a href=\"https://i.stack.imgur.com/0nP37.png\" rel=\"nofollow noreferrer\">To remo... | How do I tell that my time series is stationary or not? | stats | 2017-06-21T09:34:42.800 |
[
{
"message": "n00b question:Lets say I am looking at a sample of records, say, sales data from several McDonald's restaurants. Lets say I detect a difference between two groups of McDonalds.For example, McDonald's stores located in Oregon sell fewer McRibs per month than do stores in Tennessee.Some descriptive ... | Descriptive test statistics v.s. Probability | stats | 2017-06-21T16:21:45.717 |
[
{
"message": "I have a non-significant moderation. However, when I plot it, the lines are not parallel, even crossing at a certain point. Does this mean anything? Should I still present a plot that can be misleading, as it shows an interaction that is not significant?",
"role": "user"
},
{
"message"... | Plotting non-significant moderations | stats | 2017-06-21T16:26:49.993 |
[
{
"message": "Below (in R code), I'm showing the Bayesian estimation of the Difference between two proportions resulted from two binomially distributed groups (<code>groups</code>) of scores (<code>y</code>).My question is how can I now compute a Bayes Factor to understand which hypothesis (i.e., $H_1$ or $H_0$... | Obtaining a Bayes Factor for the difference between two proportions (R code provided) | stats | 2017-06-21T17:22:08.617 |
[
{
"message": "My regression models have heteroscedasticity problems. Gujarati (2008 and 2011) suggests that we can either transform one variable or do WLS. I choose transform by transforming my dependent variable to (1/Y) like what <a href=\"http://stattrek.com/regression/linear-transformation.aspx?Tutorial=AP\... | How to interpret regression coefficient if the dependent variable is reciprocal? | stats | 2017-06-22T06:00:17.847 |
[
{
"message": "I have a data as follows.<pre><code>data <- structure(list(Loc = structure(c(17L, 27L, 33L, 6L, 39L, 10L, 9L, 11L, 36L, 4L, 2L, 5L, 34L, 45L, 18L, 15L, 29L, 31L, 14L, 40L, 44L, 19L, 1L, 22L, 3L, 32L, 16L, 21L, 20L... | Setting custom contrasts in R | stats | 2017-06-22T11:46:27.410 |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.