All Questions

0
votes
2answers
11 views

Testing equality of two X values in quadratic regression

So let's say we have a quadratic relationship between two variables, y and x. Graphically, it is U-shaped. However, there is also a linear component to it, such that the left curve is lower than the ...
4
votes
3answers
72 views

What is the best way to remember the difference between sensitivity, specificity, precision, accuracy, and recall?

Despite having seen these terms 502847894789 times, I cannot for the life of me remember the difference between sensitivity, specificity, precision, accuracy, and recall. They're pretty simple ...
4
votes
1answer
87 views

Missing at Random Data in GEE

For a continuous outcome being analyzed using GEE with a linear link, you have assurance that standard errors and point estimates are consistent with a first order trend regardless of distribution of ...
1
vote
0answers
6 views

Interpretation of interaction term

I have a model: $$ \ln({\rm earnings}) = a+b_1{\rm female}+b_2{\rm white}+b_3{\rm female}\times{\rm white} $$ 4{\rm female}4 and 4{\rm white}4 are dummy variables. I have interpreted b_1 and b_2: ...
1
vote
1answer
75 views

Smoothing spline with dependent coordinates in R

I have a series of patients in whom I have measured the value of a certain blood quantity at several time points. However, the time points vary a lot and the number of measurements range between 2 and ...
2
votes
1answer
50 views

Time Series Function - Constant vs Piecewise

I have daily data for online marketing $ spend and the number of clicks to the website gained. I want to determine a function that 'maps' the two together. I cannot use normal linear regression ...
2
votes
1answer
2k views

rpart and the printcp function

I don't really understand how the columns "xerror" and "rel error" are calculated. I found out that the printcp() function "gives cross-validation estimates of misclassication error (xerror), ...
3
votes
1answer
17 views

Cointegration - Why can't I estimate a VAR on the differences?

When talking about variables that are I(1) (the first difference is stationary), Lutkepohl book says: "...in general, a VAR process with cointegrated variables does not admit a pure VAR representation ...
1
vote
1answer
25 views

expressing a discrete distribution as a mixture of bernoullis

How would one express a discrete distribution as a probabilistic mixture of Bernoulli random variables? An example of a discrete distribution being something like this: $P(X=1)=0.15$, $P(X=2)=0.45$, ...
0
votes
0answers
3 views

estimate missing values in unbalanced design

I want to estimate the NA values of the table. ...
1
vote
0answers
7 views

Fitting multiple models to a noisy measurement

I have measured a quantity for a set of data contains couple of thousands objects. Since the measurement is very noisy, I need a set of data contains a lot of objects. Then I have a model based on the ...
0
votes
0answers
5 views

r-pnn, normalization and different distance measures for each variable

Since pnn is a NN that uses a Radial kernel to classify data, I think the distance measure is key and, in consequence, the normalization of the data. Am I right? How does pnn package calculate the ...
0
votes
1answer
95 views

Can I subsample a large dataset at every MCMC iteration?

I have a large dataset from which I want to perform a bayesian probit regression using Gibbs sampling 1. Since the dataset has one milion rows, and variables from a truncated normal must be sampled ...
0
votes
0answers
11 views

Bayes nets - calculating probabilities

Given a Bayesian network, say a -> b -> c, all binary random variables (I won't show the CPTs, assume they are given). You are told b and c are true. How do you calculate the P(a=True)?
-1
votes
0answers
15 views

Given some nodes in a Bayes net, what is the probability of another node being true?

By example: Say LC = False, MP = True. What is the probability of CG being true then?
0
votes
0answers
8 views

How to test heteroskedasticity at the independent variable level?

I know how to test the heteroskedasticity of a model's residuals. I am inquiring about how to test for heteroskedasticity for each specific independent variables included in the model. What is the ...
2
votes
1answer
148 views

Factoring simple Markov network

Let $X$ by the joint distribution of the random variables $A$, $B$, $C$, and $D$. Let $(A \perp B) \mid (C, D)$ and $(C \perp D) \mid (A, B)$. I understand that this distribution should factor over ...
0
votes
0answers
13 views

Add a quadratic random effect to a nonlinear mixed model?

How can one add a quadratic random effect to a nonlinear mixed effect model? I've been trying to do this with nlmer without luck. Any tips would be greatly appreciated! Here's my starting point that ...
1
vote
0answers
10 views

Risk in density estimation: grasping the definition

When generalizing estimators to an entire function what is the space in which we perform the integral to obtain the expected value (with respect to this function)? For example, when estimating ...
0
votes
0answers
7 views

Use Profile Hidden Markov Models in Bioinformatics

If I have new DNA sequence and want to use profile HMM for alignment, What the steps I should to follow with details please?
0
votes
0answers
6 views

On computing the Wolfe's t-Test

I have a sample with $n=1000$ subjects. For each subject I have three variables measured, let's say $X$, $Y$ and $Z$. I have the following correlations: $r_{xz}$ = 0.80 $r_{yz}$ = 0.83 I want to ...
23
votes
2answers
1k views

Intuition behind why Stein's paradox only applies in dimensions $\ge 3$

Stein's Example shows that the maximum likelihood estimate of $n$ normally distributed variables with means $\mu_1,\ldots,\mu_n$ and variances $1$ is inadmissible (under a square loss function) iff ...
3
votes
2answers
84 views

Many dependent variables, few samples: is this an example of “large $p$, small $n$” problem?

"Large $p$, small $n$" typically refers to "many independent variables, few samples". In my case, I have $1$ independent variable, $300$ dependent variables, and $n < 20$ samples. Thus, my case ...
1
vote
1answer
32 views

MANOVA when sample size is smaller than the number of DVs

I need to compare $16$ quantitative variables, measured for two groups, A and B. I thought of applying MANOVA. However, there are only $4$ and $9$ cases for groups A and B respectively. I looked for ...
0
votes
0answers
11 views

Sample size calculation for non-normal data (possibly lognormal)

I am currently trying to rack my brains to find a solution but I seem to be coming up with nothing. I have water quality data with which I want to get a sample size calculation from for a future ...
0
votes
0answers
4 views

AIC or similar selection techniques for Variograms?

I have a very basic question: how does one choose the "best" variogram? It is possible to fit different models to an empirical variogram, e.g. nugget, ...
1
vote
2answers
30 views

Can we learn 3d features using Autoencoder?

Typically, we use Autoencoder to learn 2d features on 2d images (e.g. pen-strokes of digit). For example, if I have 10000 3d 31x31x31 images (e.g. car images). I unroll each of the images, i.e. ...
2
votes
0answers
14 views

Why do the estimated values from a Best Linear Unbiased Predictor (BLUP) differ from a Best Linear Unbiased Estimator (BLUE)?

I understand that the difference between the is related to whether the grouping variable in the model is estimated as a fixed or random effect, but it's not clear to me why they are not the same (if ...
0
votes
0answers
28 views

Unable to formulate MLE for minimum distance estimator

The model generating the observation is of the form $y_n = A^Tx_n + U_n$ where $x$ is the output of a a linear stationary model and it is non-Gaussian, pseudorandom sequence; $U$ is a zero mean ...
4
votes
3answers
85 views

What is the distribution of the conditional mean E(Y|X) in a multiple regression?

Suppose the model is $$ Y = b_0 + b_1X_1 + b_2X_2 + b_3D + b_4X_1D + e \\ e \sim\mathcal N(0, \sigma^2) $$ Where $D$ is a categorical variable. $$ E(Y|X_1, X_2, D=1) \sim\mathcal ?? \\ E(Y|X_1, ...
2
votes
1answer
35 views

Maximizing likelihood versus MCMC sampling: Comparing Parameters and Deviance

I am working in R. I use lm() for maximizing the likelihood in the first analysis, and STAN to sample from the posterior in a second analysis. ...
5
votes
1answer
73 views

Survival analysis where covariates are unavailable for censored data

I am looking at the time required by judges to reach decisions. Each judge assesses a number of applicants and can either approve or not approve the application. The case is finalized when the judge ...
2
votes
0answers
16 views

Methods of fitting a dynamic linear model

I'm taking a time series course and am learning about exchangeable time series form of dynamic linear models (DLMs). This is given by: \begin{align*} \mathbf{y}_t' &= ...
1
vote
2answers
58 views

Any other non-parametric alternative to Kruskal-Wallis?

It looks like Kruskal-Wallis is the standard nonparametric test for more than two groups. The problem is that it does not tell which groups are different, except that whether there exists significant ...
2
votes
1answer
77 views

Finding the cluster centers in kernel k-means clustering

I think this is the most easily understood topic in Kernel K Means Clustering. But assuming that I am not an expert in Machine Learning, can someone tell me how does someone calculate Kernel K means ...
2
votes
0answers
16 views

Is there any use of having dual error bars in bar charts to show both descriptive and inferential statistics?

I would like to display information both about the distribution of the population and the certainty in the measurements in the same plot. Would there be any use of having dual error bars in a barchart ...
0
votes
1answer
159 views

Generating IMA(1,1) series

I'd like to generate a series that follows an IMA(1,1) process, where $θ$ is the moving average parameter. I generated the series based on different representations and I got different results, I'm ...
1
vote
1answer
23 views

Logistic Regression using fractional polynomials in R

I have been developing a model based on trauma data of head injury in the UK. The key outcome is 30 day mortality (denoted as "Survival" measure). In a dataset of 2134 patients, there are other ...
2
votes
0answers
78 views

Discrete Fourier Transform and uneven sampling

In this blog article an example is given of one can use the DFT to detect frequencies much higher than the sample rate. In the comments sections I asked how it was done, since DFT normally requires ...
0
votes
1answer
30 views

Repeated measures ANOVA and uneven number of trials

Suppose I have multiple responses from each subject in three different conditions (A, B, C). If I would decide to run a repeated measures ANOVA, I would first average over the repetitions from each ...
0
votes
0answers
5 views

Confidence interval on replicates from multinomial distribution with bimodal outcomes

I have a Java model which tracks the numbers of 6 types (A-F) of individuals. I am interested in the distribution of different types of individual across simulations with different parameter values. ...
3
votes
1answer
68 views

Sum of truncated normal with two normal distributions

Suppose I have one normal distribution $W \sim N(\mu_{w},\sigma_{w}^2)$ with a known cuttoff point (percentile) on this distribution called $c$. The first part of $W \in [-\infty,c[$ needs to be ...
1
vote
1answer
1k views

Z score transformation for testing group differences in correlations

SPSS Help provides the following help for testing group differences in a correlation, using the GLM approach. See link. It first requires that X and Y are transformed into z scores. Question: When ...
0
votes
1answer
57 views

GBM Bootstrap Prediction Interval Code Error

based on code presented in thread: How to find a GBM Prediction Interval I am trying to apply this to my dataset. Below is my full code, and I am having issues with the bootstrap function. ...
2
votes
0answers
20 views

Latent Class Analysis vs. Cluster Analysis - differences in inferences?

What are the differences in inferences that can be made from a latent class analysis (LCA) versus a cluster analysis? Is it correct that a LCA assumes an underlying latent variable that gives rise to ...
1
vote
1answer
13 views

Naive ElasticNet in the glmnet package

In the R package glmnet, does it calculate the Naive form of ElasticNet or is the output rescaled with the term (1 + lambda)?
2
votes
2answers
28 views

Name for outer product of gradient approximation of Hessian

Is there a name for approximating the Hessian as the outer product of the gradient with itself? If one is approximating the Hessian of the log-loss, then the outer product of the gradient with itself ...
0
votes
2answers
618 views

R time-series forecasting with neural network, auto.arima and ets

I've heard a bit about using neural networks to forecast time series. How can I compare, which method for forecasting my time-series (daily retail data) is better: auto.arima(x), ets(x) or ...
4
votes
3answers
209 views

Distance metric for all categorical data

I have categorical data in the form of Y/N of 23 attributes and containing 200+ records. I need to compute the distance between the attributes with their class label. Which metric can be used?
-1
votes
1answer
26 views

Statistical analysis of variable data

I have the statistical research data. I have 6 treatments with 3 boxes for each treatment. I am raining on the treatments every week and collecting data. The data is variable within boxes and also ...

15 30 50 per page