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": "Given is a linear regression problem, where we have one training point, which is 1-dimensional: $x \\in R_{>0}$ and the corresponding output, $y \\in R$. We duplicate the feature, such that we have one training point with two (identical) features. For this, we have to determine if we can apply ... | Closed form and gradient calculation for linear regression | stats | 2017-07-26T13:05:21.767 |
[
{
"message": "In scikit-learn the <a href=\"http://scikit-learn.org/stable/modules/generated/sklearn.linear_model.Ridge.html\" rel=\"nofollow noreferrer\">Ridge regression estimator has a <code>normalize</code> parameter that normalizes the regressors. I found that it was necessary to set this to <code>True</co... | Scikit-learn: How to normalize Huber regressors? | stats | 2017-07-26T17:12:01.993 |
[
{
"message": "Is Variance inflation factor(VIF) also applicable in order to test multicollinearity in between two categorical variables? What is the use of the Spearman test? How to do this on R?",
"role": "user"
},
{
"message": "Generalized VIF is your friend. See example:<pre><code>data1<-data.... | Multicollinearity between two categorical variables | stats | 2017-07-27T07:01:38.360 |
[
{
"message": "I am working on a method to find a optimal allocation of money in various ways, like putting it on a savings account, investing it, paying off mortgage, etc. The scope of this method is to find a way to increase the money someone has at the start of the retirement as efficiently as possible.For ea... | Quantification method for long term financial risk | stats | 2017-07-27T08:24:57.600 |
[
{
"message": "For which set of values of predictors (numerical) will my response variable (factor) be guaranteed to equal a certain level (using Random Forest)I am going to explain it on base of the <code>iris</code> dataset:Goal --> I need to get as many species of <code>setosa</code> as possibleThe way --> i ... | For which set of values of predictors will my response variable be guaranteed to equal a certain level | stats | 2017-07-27T09:44:33.427 |
[
{
"message": "if I have several datasets and each element in those sets is either A or B (which means I'll get an A/B proportion for each dataset at the end), how many elements should be in each set so that the comparison at the end may tell me whether there are any statistically significant results?I feel like... | Here's a dumb one: how much data is needed to compare different datasets and get a significant result | stats | 2017-07-27T13:00:22.777 |
[
{
"message": "I want to measure whether the binary responses (0 and 1 - disagree or agree) are different among four different statements - i.e. whether certain statements are significantly more likely to be agreed with. It is the same people answering each question, but, due to the fact the statements are diffe... | Is this Cochran's Q test worthy? - Unsure if my data is paired | stats | 2017-07-27T17:55:59.130 |
[
{
"message": "In case a linear regression, Mean Square Error (MSE) is defined as:$$\\frac{1}{n-k-1}\\sum_{i=1}^{n}{(y_i-\\hat{y}_i)^2},$$where $n$ is the number of observations, $k$ is the number of independent variables, $y_i$ and $\\hat{y}_i$ are the $i$th observed value of the response variable and its predi... | What's the substitue of MSE in GAMs? | stats | 2017-07-27T18:13:49.740 |
[
{
"message": "What does the 1-sided vs 2-sided distinction mean for general $M \\times N$ independence tests like Fisher exact, $\\chi^2$ or $G$-test?Which makes more sense?What is the \"negative\" side in these tests?",
"role": "user"
},
{
"message": "Potential test-bias aside, deviation from the n... | 1-sided vs 2-sided general M*N independence tests like Fisher exact or $\chi^2$ tests | stats | 2017-07-27T21:17:14.527 |
[
{
"message": "I have a problem that I thought should be easy but is turning out to be quite difficult. Lets say I have 100 measurements of a time-varying processes at time points $t\\in {1, \\dots, 100}$ which are denoted $y = (y_1, \\dots, y_{100})$. However, I also have 20 repeated measurements of the last ti... | Kalman Smoother with Repeated Measurements | stats | 2017-07-28T03:46:23.953 |
[
{
"message": "1) Is there an intuitive explanation for why data becomes correlated once rotated into the principal component basis?2) Is there any intuitive explanation behind why rotation doesn't affect the whitening of data?Specifically, I want to understand why $x_{ZCA} = U x_{PCA}$ where $x_{PCA} = D^{-1/2}... | Intuition behind PCA decorrelation and whitening | stats | 2017-07-28T04:07:45.387 |
[
{
"message": "I'm currently taking Andrew Ng's Machine Learning course on Coursera, and I feel as though I'm missing some key insight into Backpropagation.Particularly, I'm stuck on this algorithm slide:<a href=\"https://i.stack.imgur.com/uzShq.jpg\" rel=\"nofollow noreferrer\">First, when we set capital Delta ... | What is the significance of the Delta matrix in Neural Network Backpropagation? | stats | 2017-07-28T04:30:29.763 |
[
{
"message": "<blockquote> If the input sample correlation matrix consists of low correlations (say below 0.3), do not perform factor analysis. There is not much to model! </blockquote>I read this from statistics textbook. I don't understand the meaning of <code>input sample correlation matrix</code><br>How ... | Why cannot perform factor analysis when correlation below 0.3? | stats | 2017-07-28T12:53:53.747 |
[
{
"message": "I am trying to implement the suggestion by <a href=\"https://www.google.ch/url?sa=t&rct=j&q=&esrc=s&source=web&cd=1&cad=rja&uact=8&ved=0ahUKEwjun6HoyqzVAhXEVRoKHWQsCM8QFggsMAA&url=http%3A%2F%2Fwww.stat.columbia.edu%2F~gelman%2Fresearch%2Fpublished%2Fpriors11.pdf... | bayesian logistic regression with weakly informative priors (pymc3) | stats | 2017-07-28T18:55:20.617 |
[
{
"message": "E.g. is it possible to solve the XOR problem without backpropagation. If so, what would a solution look like?",
"role": "user"
},
{
"message": "Purpose of Backpropagation is to optimize the bias of each hidden layer and the weights on the connecting neurons. So without backpropagation ... | Can you solve non-linear problems with a neural network without using backpropagation? | stats | 2017-07-29T06:09:52.313 |
[
{
"message": "The optimal weight w* for ridge regression is ($\\lambda$ is a positive scalar):$$w^* = (XX^T+\\lambda I_n)^{-1}Xy$$I want to predict the output for a new datapoint $x_i$, whereby $w^*$ is already given - how could that be calculated? I would use the above equation to reformulate:$$y_i = w^T*x_i$$... | Prediciting an output with (kernelized) ridge regression | stats | 2017-07-29T11:32:20.257 |
[
{
"message": "I have two bags each with $m$ balls.In the first bag I have $n_1$ blue balls.In the second bag I have $n_2$ blue balls.The target is to pull out a total of k blue balls from both bags ($m>n_1>n_2>k$).I pull out one ball from the first bag and then one ball from the second bag, and so on. ... | What is the repetition distribution of Pulling balls out of two bags? | stats | 2017-07-29T14:46:52.680 |
[
{
"message": "I am conducting a fMRI study in which there are only 8 participants (and 4 control participants). I will be seeking differences in the 8 participants between periods of time, and also seeking differences between the 8 participants and the 4 controls at one particular time-point.There is quite a lo... | T-test for small-sample with outliers and skewed data good enough? | stats | 2017-07-29T21:29:43.830 |
[
{
"message": "This is little off-the-track question than the conventional ones asked in this forum. This is a problem related to my research. I am stuck to an optimization problem of the following nature:$\\text{min} ~~ Q(x) ~~ \\text{subjected to} ~~C(x, y) \\geq C_0$, where $y \\sim \\mathcal{N}(\\mu, \\sigma... | Question related to optimization of nature $\text{min} ~~ Q(x) ~~ \text{subjected to} ~~C(x, y) \geq C_0$ | stats | 2017-07-30T15:59:47.987 |
[
{
"message": "Please excuse my lack of terminology. I am just a humble discrete optimizerAssume we have a kind of \"coin toss\" where the result is not binary, but a rational number between -1 and 1. There is nothing known a priori about the probability distribution underlying this \"coin\". What can I do to es... | Random values in fixed interval - how to assign probability distribution? | stats | 2017-07-30T17:38:55.667 |
[
{
"message": "In deep learning papers, data augmentation is often presented as a type of regularization. For example, this is explored in Chiyan Zhang and coauthor's presentation at ICLR17, <a href=\"https://arxiv.org/abs/1611.03530\" rel=\"nofollow noreferrer\">Understanding deep learning requires rethinking g... | Why is data augmentation classified as a type of regularization? | stats | 2017-07-31T11:59:43.700 |
[
{
"message": "I did an experiment with a Mass spectrometer and want to compare the different treatments.Control: Week 0: Immediate measurement of specimens (n=200) after taking the sample. Treatment 1: Specimens (appx. n=120) taken from samples stored at -25°C in 100% ethanol.Sample measured after 1, 2, 3, 5, 7... | How to analyze my data of 3 different treatments. (ANCOVA, U-Test) What model to use? (LM,GLM) | stats | 2017-07-31T12:59:38.583 |
[
{
"message": "Based on visualized decision boundaries, we have to decide what kind of classifier has generated it. One example is shown in the image below - this is from a quadratic kernel Support Vector Machine (SVM), i.e. $K(x,y) = (x^T*y+c)^2$. I know what a quadratic function looks like in two dimensions, b... | How does a quadratic kernel look like? | stats | 2017-07-31T19:06:18.300 |
[
{
"message": "I have a more theoretical question about LDA (Latent Dirichet Allocation).When doing LDA we provide number of topics ourselves. As far as I understand it tries to build topic-word-document distributions to minimize perplexity (which is why we are doing it in iterative manner).So the question - can... | LDA topics number - determining the 'fit' level with current number of topics | stats | 2017-07-31T22:52:49.770 |
[
{
"message": "I have 1000 individuals with measurements of plasmatic HDL levels over the last 15 years. The number of measurements per individual ranges from 1 to 15, and were not taken in the same dates. I would like to compare the HDL levels (quantitative trait) over time in the individuals and make a ranking... | Linear mixed effects model on physiological parameter as function of time | stats | 2017-08-01T02:22:29.047 |
[
{
"message": "I am currently reading the Lawrence 2005 paper \"Probabilistic non-linear Principal Component Analysis with Gaussian Process Latent Variable Models\" available <a href=\"http://www.jmlr.org/papers/volume6/lawrence05a/lawrence05a.pdf\" rel=\"nofollow noreferrer\">here. However I am failing to see h... | Gaussian Marginal Likelihood | stats | 2017-08-01T11:22:28.913 |
[
{
"message": "I have medical data with max value 500 along with values like age and binary values for sex (0 or 1).I will use clustering to find the number of clusters. Which is the best approach among three.Normalize each coloumn,standardize with z scores or do nothing. For z-scores i heard that he data should... | Normalization ,standardization, or do nothing | stats | 2017-08-01T13:46:43.097 |
[
{
"message": "The following data frame <code>df</code> contains observations on two different measures of muscle strength (<code>VAR_1</code> and <code>VAR_2</code>) from 24 males and 16 females. Both variables present a fairly linear relationship: <pre><code>library(\"ggplot2\")ggplot(df, aes(x = VAR_1, y = VA... | How should I treat GENDER factor when exploring the relationships between two given variables? | stats | 2017-08-01T17:24:55.933 |
[
{
"message": "I've read that the KS-test is biased when the pdf parameters are estimated from the same data source. <a href=\"https://stats.stackexchange.com/questions/82530/evaluating-goodness-of-fit-for-distributions-e-g-lognorm-gamma-with-est\">This post on Cross Validated lead me to the paper which has a wo... | check implementation ks test for distribution with estimators fitted from same data | stats | 2017-08-02T08:09:41.997 |
[
{
"message": "I have been experimenting with using an augmented state space in which I store / memorise previous states as new variables at the bottom of the state vector when performing discrete Kalman filtering. I can then approximate a high-order discrete model by passing the lagged terms down through the st... | Non-Markov Kalman filtering via an augmented Markov state-space. What are the potential dangers beside increased dimensionality? | stats | 2017-08-02T15:56:09.570 |
[
{
"message": "Have been working on a dataset called Dorothea hosted at UCI. It contains 100,000 features. If I use PCA the top 10 components explain only 4.10% of the variance. Having concluded that PCA will not reduce dimensionality in any significant way, I looked at the dataset in a number of different ways.... | Feature Selection for Machine Learning problem | stats | 2017-08-02T18:44:19.567 |
[
{
"message": "I was reading the Mathworks documentation about the <a href=\"https://www.mathworks.com/help/curvefit/csaps.html\" rel=\"nofollow noreferrer\">CSAPS and <a href=\"https://www.mathworks.com/help/curvefit/tpaps.html\" rel=\"nofollow noreferrer\">TPAPS. I got confused in 2D case where I can't underst... | How does the cubic smoothing spline works in 2D case? | stats | 2017-08-02T20:32:29.530 |
[
{
"message": "I have a classification problem with over 700 predictor variables and training data with 200,000 observations. There is only one response variable.I have a feature selection problem. I am looking for techniques to determine out of the 700 predictors, which are relevant for the model. I am aware of... | Classification Problem with large number of predictors and huge training data | stats | 2017-08-03T07:42:15.563 |
[
{
"message": "The Naive Bayes classifier is the classifier which assigns items $x$ to a class $C$ based on the maximizing the posterior $P(C|x)$ for class-membership, and assumes that the features of the items are independent.The 0-1 loss is the loss which assigns to any miss-classification a loss of \"1\", and... | Why is the naive bayes classifier optimal for 0-1 loss? | stats | 2017-08-03T15:13:48.663 |
[
{
"message": "We have the following loss function for logistic regression, the so called log-loss defined as:$- \\Big[\\sum_i y^{i}\\log(h(x^i))+(1-y^i)\\log(1-h(x^i))\\Big]$We also know that logistic regression assigns a datasample to class y=1 if the posterior probability $h(x)$ of class $y=1$ is bigger than ... | Range of arguments in loss function of logistic regression | stats | 2017-08-03T16:11:32.583 |
[
{
"message": "I'm trying to figure out ROC analysis and have the following question:Assume there is an test instrument that claims to be able to identify cats based on a series of checks (such as: does the animal have four legs? does it eat mice?...).I want to test this instrument using ROC analysis and a sampl... | Area Under the ROC Curve: Comparing identification performance between two values of the same variable | stats | 2017-08-03T16:25:06.160 |
[
{
"message": "I am trying to replicate a cryptoanalysis technique called template attack. I won't enter in details of the attack itself, but the theory behind involves multivariate distribution (more details <a href=\"https://wiki.newae.com/Template_Attacks\" rel=\"nofollow noreferrer\">here).So, I tried to com... | Probability in Multivariate normal distribution (for template attacks) | stats | 2017-08-03T18:51:56.380 |
[
{
"message": "I have a <a href=\"http://scikit-learn.org/stable/modules/generated/sklearn.linear_model.LogisticRegression.html\" rel=\"noreferrer\">Logistic Regression supervised classifier that is trained on <code>n=365 observations</code> and <code>m=179 attributes</code> with <code>c=5 classes</code>. It's ... | How to have a "None of the above" category in a Logistic Regression? | stats | 2017-08-03T19:12:28.600 |
[
{
"message": "I know this is a kind of stupid question but I can not find a specific answer in here and google so I really need your help.I want to convert a degree of freedom of t-distribution to follow a standard deviation of normal distribution to plot a density line. Assume I have a samples (size =14) with ... | Is it possible to convert a degree of freedom in t-distribution follows a standard deviation of normal distribution? | stats | 2017-08-03T21:24:23.727 |
[
{
"message": "I have a survival dataset H.month where I look at hazard per month.<pre><code>> monthly# A tibble: 144 x 11# Groups: company [2] time n.risk n.event n.censor surv std.err upper lower company hazardrate <dbl> <dbl> <dbl> <dbl> <... | Why does lm() estimate different coefficients for polynomial or quadratic terms? | stats | 2017-08-04T12:08:57.160 |
[
{
"message": "I have 31 measurement values for load times of different web sites (100) under different configurations (A,B,C,etc.).Say website A has a median Page Load Time (PLT) of 2000ms with configuration A (baseline) and a median PLT of 1700ms with Configuration B (optimization).Now website B has a median P... | How can i compare Page Load Time of different websites | stats | 2017-08-04T14:51:11.860 |
[
{
"message": "Problem 1: The term $p_{\\theta}(y_{1:N}|x_{1:N})p_{\\theta}(x_{1:N})$ is the joint pdf, also called as the posterior. In EM, the complete data likelihood is the distribution of $x_1,\\ldots,x_N,y_1,\\ldots, y_N$ for which we write the same formulation as I have written. Then what is the differenc... | HElp in understanding difference between EM and MAP estimation methods | stats | 2017-08-04T15:01:48.917 |
[
{
"message": "I have a dynamic mechanical system of the form:$$\\mathbf{M{\\ddot q}+{\\Omega_c}G{\\dot q}+{Kq}=F(t)}$$and I need to introduce some uncertainty for the $K$ parameter, which is a symetric matrix of $q$ degrees of freedom.I did a bit of research of Monte Carlo simulation but I´m a bit confused of h... | How to implement a Monte Carlo Simulation for studying uncertainty in dynamic stiffness? | stats | 2017-08-05T15:50:09.423 |
[
{
"message": "How does one interpret coefficients when you have continuous or categorical independent variables but standardized dependent varaible. For instance if we have K groups in the data and the dependent variable is standardized using the mean and standard deviation of within each group. Now we regress ... | Standardized dependent variable and non standardized independent varaible | stats | 2017-08-05T18:28:36.923 |
[
{
"message": "I am trying to discretize a continuous variable that does not follow a linear relationship with our response variable. I am trying to find the optimal way to discretize this variable to better capture the nonlinear relationship. The method we are using right now is to cut the variable into numer... | Discretizing/Binning Continuous Variable by Continuous Response | stats | 2017-08-05T18:32:59.837 |
[
{
"message": "My question is how can we know that we should use GARCH or EGARCH in the empirical study? Can I claim that EGARCH allows for the asymmetric of bad and good news?I start using the model, but need to study on my own.",
"role": "user"
},
{
"message": "Your first question essentially is a ... | How to choose between EGARCH and GARCH? | stats | 2017-08-05T20:51:12.770 |
[
{
"message": "I have a binary classification problem (i.e. is observation positive or negative) and I'm interested in what information I can obtain about observations in my test set. I don't care about the model parameters or observations in my training set. I have plenty of data and would just use an uninforma... | Extra information at prediction time when using a Bayesian logistic regression vs. normal | stats | 2017-08-06T19:56:45.513 |
[
{
"message": "I was solving logistic regression using IRLS (<a href=\"https://en.wikipedia.org/wiki/Logistic_regression#Iteratively_reweighted_least_squares_.28IRLS.29\" rel=\"nofollow noreferrer\">wiki) described in the wiki link. Now I have a doubt, if $X$ has dependent features then $X^TS_kX$ will not have f... | Iteratively Reweighted Least squares for logistic regression when features are dependent? | stats | 2017-08-07T07:43:05.523 |
[
{
"message": "I am comparing frequency count data for observed behaviours in a 3 minute time frame, between two small groups of people. My hypothesis is that there will be significantly more of certain behaviours in one of the groups. As I understand it, frequency count data is by nature non-normal, so from w... | Which statistical test for count data with small samples? | stats | 2017-08-07T15:49:31.567 |
[
{
"message": "I am very new to design of experiments concept. I would like to design an experiment to understand the relationship between input parameters like amount of various ingredients, cooking temperature, time of cooking, etc. vs. the quality of a cake to be baked.Assuming that all input parameters are c... | Design of Experiments for Baking | stats | 2017-08-08T08:47:12.970 |
[
{
"message": "I'm reading <a href=\"https://stats.stackexchange.com/questions/6502/lasso-assumptions\">here that LASSO makes no particular assumption concerning the distribution of residuals, which somehow confuses me.Consider a linear regression problem with 1 target $y$, $P$ features $\\mathbf{x}$ and a train... | Penalised linear regression - residuals distribution assumptions | stats | 2017-08-08T10:22:32.683 |
[
{
"message": "I have 10 interval data points, measured at 10 different occasions. They are not normally distributed, and the data is the population, not the sample. I want to test whether the mean has increased from start to finish. I thought I should maybe use a paired t-test, but the normality assumption is v... | What statistical test do I need when measuring non-normal population data? | stats | 2017-08-08T12:18:02.783 |
[
{
"message": "In an auctions website I maintain, auctions are listed most-recent-first. There are 20 auctions per page. A user can click <code>next</code> in the footer to view older auctions. It's early days so there's currently no other way to search an auction. The most-recent-first view is the only discover... | Infering relative importance of features in driving a dependent variable | stats | 2017-08-08T16:01:31.087 |
[
{
"message": "When I was talking with a friend, he told me that it is possible to estimate the effect of some variable (a rise, for example) at time $t$ would impact another variable in time $t + n$ where n could be 2,3,4,5... by some $\\beta$ parameter. I am wondering if this type of relationship that is estim... | What time series statistical model can help me check lagged influences among different series? | stats | 2017-08-08T17:59:01.693 |
[
{
"message": "What specific metrics should one use to evaluate the performance of a hidden markov model where the training is unsuperivsed?In essence how does one cross validate a model correctly, with regards to a pre-specified number of states?Furthermore, can you perform feature selection when the training i... | Methods to validate a hidden markov model | stats | 2017-08-09T08:23:19.273 |
[
{
"message": "I'm trying to find a way to estimate the number of weights in a neural network. Let's look a simple example.<code>nnetar(1:10)</code> (from the <a href=\"https://www.rdocumentation.org/packages/forecast/versions/8.1/topics/nnetar\" rel=\"nofollow noreferrer\">forecast package in R) gives me a 1-1-... | Formula for number of weights in neural network | stats | 2017-08-09T08:37:31.277 |
[
{
"message": "My data (see image below) is positively skewed and contains both positive and negative values. I'd like to transform it to achieve normality so I can apply a repeated measures ANOVA, but can't find a technique that works.I've considered the following options:Square-rooting: doesn't keep the signSq... | Transforming positively skewed data with positive and negative values | stats | 2017-08-09T09:50:16.223 |
[
{
"message": "I am trying to do a Canonical correspondence analysis (CCA) using the community data and chemical data. I have my family level taxonomic data as community data. In chemical data I have 18 variables: Ni Cr Cu Pb Cd Co Zn Fe As Ammonia_mean Silicate_mean Phosphate_mean Nitrite_mean ... | How variables (constrained loadings) are selected in a biplot CCA | stats | 2017-08-09T12:43:48.387 |
[
{
"message": "I am constructing a training dataset for a classification problem with three categories: A, B and C. Once estimated/learned, I want to use the classifier to identify observations of types B and C in new data.My problem is that almost 90% of observations are in A, so I get very few training exampl... | How to efficiently handle very high number of false positives in training data? | stats | 2017-08-09T16:26:23.893 |
[
{
"message": "I have data from a coin flipping experiment. I flipped $N$ coins $M$ times and want to know if the probability of heads is the same across all the coins or if it varies. It might be that one coin has a different bias than all the others or that there $k$ sets of coins each with a unique bias. I am... | How to test if all coins have the same bias | stats | 2017-08-09T17:29:45.827 |
[
{
"message": "I am using <a href=\"https://msdn.microsoft.com/en-us/library/azure/dn905801.aspx\" rel=\"nofollow noreferrer\">Boosted Decision Tree Regression to predict a value. I get a few values where the residual (True Value - Estimated Value) in my training and test sets are large. I have a reason to belie... | Outlier removal before Boosted Decision Tree Regression | stats | 2017-08-09T23:24:03.420 |
[
{
"message": "I am implementing a <code>statsmodels.tsa.arima_model.ARIMA</code> model with daily advertising spend data. I have a dataset that ranges from Jan 1 2016 - present. Using a rolling forecast, I am able to generate fairly accurate next-day predictions.However, when my training data reaches EOM, the m... | ARIMA model has trouble forecasting next month | stats | 2017-08-10T00:28:52.050 |
[
{
"message": "I've tested out various feature selection methods, such as the F-test, Mutual Information and the Extra Tree (Extra Randomised) Forest Classifier (ETC) as well as PCA (which is technically a feature extraction method), with ETC being used solely for feature selection rather than as a classifier, a... | AUC score less than 0.5 for logistic regression | stats | 2017-08-10T11:30:43.820 |
[
{
"message": "I've some demand data, for which I wish to judge what will be the direction in the forecast period (Up/Down). What will be a best ML method to do this? Currently I'm using the data given below -9/4/2016 2419/11/2016 2339/18/2016 2269/25/2016 28210/2/2016 29110/9/2016 28210/16/2016 30... | Directional Forecast | stats | 2017-08-10T14:25:55.227 |
[
{
"message": "In <a href=\"http://www-bcf.usc.edu/~gareth/ISL/\" rel=\"nofollow noreferrer\">Introduction to Statistical Learning, in the part where ridge regression is explained, the authors say that <blockquote> As $\\lambda$ increases, the flexibility of the ridge regression fit decreases, leading to decr... | Ridge Regression -Increase in $\lambda$ leads to a decrease in flexibilty | stats | 2017-08-10T15:32:54.510 |
[
{
"message": "In <a href=\"http://www-bcf.usc.edu/~gareth/ISL/\" rel=\"nofollow noreferrer\">Introduction to Statistical Learning, in the part where ridge regression is explained, the authors say that <blockquote> As $\\lambda$ increases, the flexibility of the ridge regression fit decreases, leading to decr... | Ridge Regression -Increase in $\lambda$ leads to a decrease in flexibilty | stats | 2017-08-10T15:32:54.510 |
[
{
"message": "I am reading about the mediation test example from the lavaan package here:<a href=\"http://lavaan.ugent.be/tutorial/mediation.html\" rel=\"nofollow noreferrer\">http://lavaan.ugent.be/tutorial/mediation.htmlSpecifically, they fit the model:<pre><code>set.seed(1234)X <- rnorm(100)M <- 0.5*X ... | Estimation of direct and total effects with regressions and SEM (lavaan) | stats | 2017-08-10T21:38:59.033 |
[
{
"message": "I have trained two classifiers namely a logistic regression and a decision tree on a data set. When evaluating both models on the testing data set, the decision tree has a ROC AUC = 0.62 but the logistic regression has ROC AUC = 0.91. However both models have similar gain chart and the lift for th... | what it means to have low ROC AUC? | stats | 2017-08-10T22:07:16.980 |
[
{
"message": "Supposing I have two groups of people: <code>Control</code> and <code>Treatment</code>, in which the control group consists 30000 observations, whereas the treatment has 7000.Does it makes sense to compare if the frequency of men is significantly different on controls and treatment groups using a ... | What statistical test can compare frequencies of men among control and treatment groups? | stats | 2017-08-10T23:09:48.880 |
[
{
"message": "I am facing a problem which I'm not sure has a specific answer - theproblem of distributed regression model building: I've got some k stations, each having the same data structure (that is, all of them have the same columns but of course different data) and each able to compute it's own regression... | Combining two distributed regression models | stats | 2017-08-13T08:00:54.330 |
[
{
"message": "I understand that given a set of $m$ independent observations $\\mathbb{O}=\\{\\mathbf{o}^{(1)}, . . . , \\mathbf{o}^{(m)}\\}$the <a href=\"http://www.deeplearningbook.org/contents/ml.html\" rel=\"noreferrer\">Maximum Likelihood Estimator (or, equivalently, the MAP with flat/uniform prior) that id... | How meaningful is the connection between MLE and cross entropy in deep learning? | stats | 2017-08-13T19:03:41.417 |
[
{
"message": "I understand that given a set of $m$ independent observations $\\mathbb{O}=\\{\\mathbf{o}^{(1)}, . . . , \\mathbf{o}^{(m)}\\}$the <a href=\"http://www.deeplearningbook.org/contents/ml.html\" rel=\"noreferrer\">Maximum Likelihood Estimator (or, equivalently, the MAP with flat/uniform prior) that id... | How meaningful is the connection between MLE and cross entropy in deep learning? | stats | 2017-08-13T19:03:41.417 |
[
{
"message": "I have a network with over 40k nodes and about 12 million edges (float weights) and have about 10k subsets of this network that I want to test for increased density.I can think of the following options:Binarizing the network and form the problem as a chi square test of local density (sub-region) v... | Hypothesis testing for higher density in subsets of a network/graph | stats | 2017-08-13T23:04:50.767 |
[
{
"message": "I want to have a beta-binomial Bayesian model, with <code>R2jags</code>. I understand I need something like this:<pre><code> for (i in 1:N) { y[i] ~ dbinom(p,n[i]) p ~ dbeta(a,b) }</code></pre>Now suppose I have 2 types of subjects in my observations y, and I want to know whether '... | How do I specify a Bayesian Beta binomial model, with predictor variables, for R2jags? | stats | 2017-08-14T08:34:00.417 |
[
{
"message": "Imagine I have a set of measures and I want to model my data as a multivariate normal distribution. For every measure I have a different mean vector and covariance matrix. So, how can I be sure about what are the parameters that fit better my data? Do I have to compute the log-likelihood for every... | How to maximize likelihood function | stats | 2017-08-14T10:37:45.437 |
[
{
"message": "I have a population in which some have an event A and some other don't. Event A is actually my target class. I also have a set of variables/features for my population which I can use in a modeling (supervised learning) setting. Let's say one of the features/variables is age. What I'd like to find ... | Finding a confidence factor for a calculation? | stats | 2017-08-14T14:07:55.827 |
[
{
"message": "I'm trying to specify a model for predicting lung cancer incidence based on a person's smoking history. Most studies simply use pack-years, a measure of the total cigarettes smoked in one's lifetime. I'd like to incorporate time weights into the calculation of pack-years, where the weights are est... | Effect of smoking on lung cancer incidence with time-weighted pack-years | stats | 2017-08-15T10:05:07.633 |
[
{
"message": "I am a neuroscience researcher without too much background in statistical theory.I have multi recordings from different samples and I want to precisely report the variation across the samples, and I wanted to understand the differences between methods of doing this:(arithmetic) Average of variance... | Differences between methods of reporting variance | stats | 2017-08-15T15:49:15.113 |
[
{
"message": "I'm working on a project from Udacity's ml nd, finding donors, I'm making the initial test using three algorithms:LogisticRegression -> RED<br>GaussianNB -> Green<br>AdaBoostClassifier -> Blue This is the result I'm getting:<a href=\"https://i.stack.imgur.com/K8ysH.png\" rel=\"nofollow noreferre... | How to explain low performance of naive Bayes on a dataset | stats | 2017-08-16T03:29:30.877 |
[
{
"message": "I am trying to understand the given explanation for the below graph. It tries to make a comparison between poission regression with similar representation of a linear model.<a href=\"https://i.stack.imgur.com/YNehP.png\" rel=\"nofollow noreferrer\">1) When fitting a linear model with log transform... | Assumptions of poisson regression and log-transformation of response | stats | 2017-08-16T09:55:20.137 |
[
{
"message": "all:I am considering a question regarding the calculation of the probability limit for an inverse matrix.Specifically, suppose we have a non-singular and squared matrix $M$ with dimension $2\\times 2$, and let $a_{ij}$ be the $ij$th element in $M$. Assume that for all i and j = 1,2, the probabilit... | The probability limit of an inverse matrix | stats | 2017-08-16T18:22:23.027 |
[
{
"message": "Suppose I have 5 distinctly numbered balls that I have to distribute in 3 pails. All 5 must be placed in the pails. In how many ways can this be done? I think I'm missing a counting trick here that I am unaware of, like weeks ago when I learned that there was such a thing as !n thanks to this site... | Counting problem | stats | 2017-08-16T23:37:13.590 |
[
{
"message": "In computing sample size for qualitative research (e.g. a confidence interval for an estimated proportion) as follows:<blockquote> $$n=\\frac{Z^2P(1-P)}{d^2}$$ \\begin{eqnarray}\\text{where }\\,n&=&\\text{ sample size,}\\\\ Z&=&\\text{ Z statistic for a level of confidence,}... | An intuitive example for why sample size is maximum when probability is 0.5 | stats | 2017-08-17T07:56:02.030 |
[
{
"message": "I am trying to figure out a way to run a hypothesis test based on binomially distributed random variable, using R.I have a control sample with size 1000. Random variable is binary. The probability if successes found in this sample is 1.0., i.e., all 1000 values equal one.I have a test sample of si... | Limit Case (1.0 prob) in Binomial Distribution Hypothesis Testing | stats | 2017-08-17T10:05:33.587 |
[
{
"message": "I am analyzing the results of a survey on R. The questionnaire is a series of questions that participants answer using a Likert scale (<a href=\"https://en.wikipedia.org/wiki/Likert_scale\" rel=\"nofollow noreferrer\">https://en.wikipedia.org/wiki/Likert_scale). I have obtained frequency tables fo... | Confidence intervals for frequency tables | stats | 2017-08-17T11:39:19.617 |
[
{
"message": "I'm looking at the documentation for scipy's optimize minimize module as seen <a href=\"https://docs.scipy.org/doc/scipy/reference/tutorial/optimize.html#constrained-minimization-of-multivariate-scalar-functions-minimize\" rel=\"nofollow noreferrer\">here. The problem supposes a function as well a... | Why take the derivative when using slsqp algoritm? | stats | 2017-08-17T13:19:47.803 |
[
{
"message": "I work with spatial ecology, and have calculated distances from one island to its neighboring islands.I want to transform these distances to index values between 0 and 1, where the closest islands are given values close to 1 and the most distant islands get values close to zero. I also want a logi... | How to calculate an index value between 1 and 0 for distance, based on a logistic function | stats | 2017-08-17T15:13:15.530 |
[
{
"message": "If my multivariate analysis of covariance shows that my covariate does not account for significant differences is it wrong to follow up with a standard multiple regression? I know MANCOVA is under the umbrella of regression, but it doesn't give me the extra bit of information I need. I will explai... | Am I fishing for significance? | stats | 2017-08-18T04:29:18.440 |
[
{
"message": "Apologies if this is not an appropriate question for this forum. I haven't been able to find a good answer elsewhere.As per subject really, where do people go to look for academic statistical jobs (not data science)? Full disclosure: We're recruiting, but struggling to get candidates.Edit: I'm bas... | Which are the favoured places to look for jobs? | stats | 2017-08-18T09:13:09.257 |
[
{
"message": "Hello to the CrossValidated community. I could use some help.I am struggling with the analysis of an experiment, specifically with deciding and defining in code the structure of a mixed model for analysing it.The experimental design is as follows:We wanted to see if there are any differences on th... | How to define a mixed model in R. Repeated measures or time-series ? Which effect should be random? | stats | 2017-08-18T11:18:13.370 |
[
{
"message": "I have the population data about the spread of animals in country (sheep, goat, cattle etc) by ranches. Can i use ANOVA to see the difference between the means of animals by ranch type or can annova be only applied to a sample of the populationNote: the population distribution is not normal. Thank... | ANOVA on population | stats | 2017-08-18T13:01:23.053 |
[
{
"message": "Is it wrong that splines are only available in GAM-models, and not in GLM-models? I heard this a while back, and wonder if this is just a misconception, or has some truth to it. Here is an illustration:<a href=\"https://i.stack.imgur.com/DMT6Z.png\" rel=\"noreferrer\">",
"role": "user"
},
... | Splines in GLM and GAM | stats | 2017-08-19T18:17:53.107 |
[
{
"message": "I am taking an online Deep learning class from Andrew Ng and it starts with optimising a classifier based on Logistic Regression. During the online assignment there was one paragraph which does not make sense to me:<blockquote> You can see the cost decreasing. It shows that the parameters are be... | effect of increasing the number of iterations while optimising logistic regression cost function | stats | 2017-08-19T19:56:04.980 |
[
{
"message": "I am familiar with softmax regression being written by:$$P(Y=y\\mid X=x)=\\frac{e^{[Wx+b]_{y}}}{\\sum_{\\forall i}e^{[Wx+b]_{i}}}$$for the change of the class of $Y$ being $y$,given observations of $X$ as being $x$.and using subscripts to denote selecting the ith column of a matrix, and the ith el... | Why is softmax regression often written without the bias term? | stats | 2017-08-21T08:00:29.247 |
[
{
"message": "I'm currently looking into some data that was produced by an MC simulation I wrote - I expect the values to be normally distributed. Naturally I plotted a histogram and it looks reasonable (I guess?): <a href=\"https://i.stack.imgur.com/tSm3P.png\" rel=\"noreferrer\"> [Top left: histogram with <c... | Inconsistent normality tests: Kolmogorov-Smirnov vs Shapiro-Wilk | stats | 2017-08-21T12:33:37.853 |
[
{
"message": "I've split my data into a training and test set (75% and 25% split respectively), and have subsequently performed a 5-fold cross validation on the training set using GridSearchCV in order to find the optimal hyperparameters for four different classification models (LR, RF, SVM and k-NN). I have th... | k-fold cross validation AUC score vs test AUC score | stats | 2017-08-21T17:27:35.407 |
[
{
"message": "One approach to model comparison in a Bayesian framework uses a Bernoulli indicator variable to determine which of two models is likely to be the \"true model\". When applying MCMC-based tools for fitting such a model, it is common to use pseudo-priors to improve mixing in the chains. See <a href=... | Using pseudo-priors properly in Bayesian model selection | stats | 2017-08-21T23:58:00.770 |
[
{
"message": "Suppose we have data matrix $X$ which is $n\\times p$ matrix ($n$ data points, and $p$ features including intercept), i.e., we already add the intercept term (append $1$ column) to $X$For logistic regression (binary classification), the model parameters / regression coefficients $\\beta$ is a leng... | Relationship between logistic regression and Softmax Regression with 2 classes | stats | 2017-08-22T02:37:05.540 |
[
{
"message": "In a simple linear regression $y=a+ \\beta X$, the ordinary least square or maximum likelihood (ML) estimation gives $\\textrm{var}(\\hat{\\beta })=\\sigma ^{2}(X{'}X)^{-1}$, where $\\sigma ^{2}$ is the residual variance. In a case of one predictor x, $\\textrm{var}(\\hat{\\beta })=\\sigma^{2}/\\s... | Intuitive explanation of the relationship between standard error of model coefficient and residual variance | stats | 2017-08-22T10:59:20.493 |
[
{
"message": "Let $p(x)$ be some \"true\" distribution which we want to model using a simpler distribution $q(x)$. Why is the KL divergence $$KL(q||p)=\\int q(x)\\log{\\frac{q(x)}{p(x)}}$$ a good way to represents the loss of information in using $q$ instead of $p$? Is the KL divergence some \"ad hoc method\" o... | Where does the Kullback-Leibler come from? | stats | 2017-08-22T12:07:53.533 |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.