1
vote
0answers
22 views

Numerical integration of a function of an empirical CDF

I have the following equation $y = f(x)$ and I want to invert $f(\cdot)$ to find $x$ numerically. Because the function $f(\cdot)$ is quite complex I will solve $y - f(x) = 0$ instead, using the ...
0
votes
1answer
18 views

Poisson regression with offset vs logistic regression

I am thinking to use Poisson regression with an offset variable instead of a logistic regression in case where event is rare, since p (probability of success) is very small and n (sample size is ...
0
votes
0answers
3 views

Can we do use convenience and purposive sampling at the same time?

Easy accessibility as the reason for choosing the participants but at the same time samples that have been purposely selected
0
votes
0answers
12 views

How to deal with interaction between several dummy variables and one continuous variables in one or two regression models?

I want to know the relationship between revenue and cost in several conditions. Dependent variables is REVENUE.REVENUE is a continuous variable from 0~1000+.I have several key independent variables: ...
0
votes
0answers
11 views

How to perform multiclass SVM classification using k-fold cross-validation and SMO with some kernel method in MATLAB?

I have data matrix X.csv file of size nxd, where n are the observations, and d variables. There are c_1,..., c_m classes. Let, Y be the matrix containing the class labels. There is no header row in ...
0
votes
0answers
23 views

Convergence in hidden markov model

I have a HMM where forward-backward probability increases in Iteration 1, then it decreases and then increases (as well as converges). Probability values after iterations 0,1,2,3,4 are: ...
0
votes
0answers
16 views

Proving that largest root (obtained via P.C.A.) is a symmetric function [on hold]

Suppose, we are given $\textbf{X} = (X_1, X_2, \ldots,X_m)$ and $\textbf{Y} = (Y_1, Y_2, \ldots, Y_n)$. Also, we are given, S = pooled variance. If we implement Principal Component Analysis (P.C.A.) ...
0
votes
3answers
57 views

What is the alternate hypothesis of the null hypothesis β_1=β_2=β_3=0?

Usually with simple hypotheses I will have something like $$H_0: \beta_1 = 0 | H_A: \beta_1 \ne 0$$ But suppose I have a null hypotheis $$H_0: \beta_1 = \beta_2 = \beta_3 = 0$$ Question What is ...
0
votes
0answers
12 views

Reduction of models

In a normal linear model, I have working with 3 categorical factors, $A, B, C$, and my main model is the interactions model $A*B*C$. My question is as follows: If i wanted to see how far I can ...
0
votes
0answers
11 views

Feature selection for an ordered logit model (R)

I'm using an ordered logit model to predict credit ratings/risk (1-8, ordinal) as a function of 126 predictor variables. (See: https://www.kaggle.com/c/prudential-life-insurance-assessment/data for ...
1
vote
0answers
28 views

Non-parametric density estimation: Is it better to estimate a PDF by first finding its CDF?

By better I mean fewer density error against the true PDF. Say that $X$ is the random variable that we wish to find its true PDF $f_X$ by the estimation $\hat f_X$. Then my goal is to find $\hat f_X$ ...
0
votes
0answers
20 views

Principal Component Analysis: Scale reliability and validity

I'm using a popular psychometric scale, the Domain Specific Risk Taking (DoSpeRT) scale, that contains 30 items that measure an individual's risk taking capacity across five different dimensions: ...
0
votes
1answer
23 views

What statistical tests to compare two AUCs from two models on the same dataset?

Let say I build two machine learning classifiers, A and B, on the same dataset. I obtain the ROC curves for both A and B, and the AUCs value. What statistical tests should I use to compare these ...
0
votes
0answers
11 views

Applying Cox Proportional Hazards Model on Discontinuous Variable

I am using coxph in Rstudio to apply Cox Proportional hazards model on my data. This model is easy to use on continuous variable ...
0
votes
2answers
31 views

Is this controversial that in PCA, we want the variance as large as possible, while in bayesian, a large variance means a low precision?

I am wondering about the variance. We say the variance is inverse proportional to precision, then we also say the variance is proportional to the information, which means that a large variance means ...
0
votes
0answers
12 views

Neural net and new data shape

I am studying machine learning, and trying to follow the neural net implementation in this book, but I am having problems with the net effectively rejecting the dimensions of my own dataset. In the ...
0
votes
0answers
5 views

R cut zero-length interval [migrated]

I have a column that has numeric values in the 1--7 range. I would like to use the cut function to split these values into the following intervals: 1 -> 1, ...
0
votes
1answer
30 views

Is imputation needed for $0$'s in regression?

I am working on a dataset of 2000 records using SAS Enterprise Miner in order to predict insurance payment (compensation) from insurer, a motor insurance company, to its customers. Though there are no ...
1
vote
0answers
20 views

Restricted Maximum Likelihood (REML) Estimate of Variance Component

Let, $$\mathbf y_i = \mathbf X_i\mathbf\beta + \mathbf Z_i\mathbf b_i+ \mathbf\epsilon_i,$$ where $\mathbf y_i\sim N(\mathbf X_i\mathbf\beta, \Sigma_i=\sigma^2\mathbf I_{n_i}+\mathbf Z_i \mathbf ...
2
votes
2answers
54 views

What to take in consideration when we use Bayesian Methods on Big Data problems?

I was reading the book Bayesian Methods for Hackers by Cameron Davidson-Pilon. He use PyMC for examples. As an experiment, I created a ...
2
votes
0answers
39 views

Multilevel Model versus Linear Regression?

In short: I wonder when I would ever want to use a multilevel model as opposed to a linear regression with appropriate structure. In detail: When I look at Wikipedia, I understand that multilevel ...
1
vote
0answers
14 views

Binary outcome estimation from n “measurements”

Assume you have a binary parameter $y$ which is either $0$ or $1$, and have $n$ measurements $\tilde{y_k}$ of it, each with a different probability $p_k$ of being correct (equal to $y$). With ...
0
votes
0answers
8 views

Reference for forecasting nonstationary variables

My goal is to extrapolate / forecast data up to 10, 20, 100 years depending on certain independent variables. Is there like a publication or a book that I could follow that specifically pertains to ...
2
votes
1answer
29 views

Reporting focal strain (high MI) for CFA models with good model fit?

According to Brown (2015), one is expected to examine and report localized areas of ill fit (e.g. modification indices (MI)) as part of the model evaluation. I have a number of questions about ...
0
votes
0answers
15 views

Threshold cointegration

I have a panel data N=45 T=25. Engle-Granger test confirms co-integration between two I(1) variables. I would like to test for threshold cointegration between these two vars. Is there a user written ...
0
votes
0answers
9 views

Finding the correct model to infill streamflow data gaps

I have 15-minute streamflow observations for a small stream, but the dataset has some gaps in it. I want to fill the gaps with a regression using observations from a nearby stream (and quantify the ...
3
votes
2answers
55 views

Optimize starting parameters for Bayesian Linear Regression?

I'm using PyMC3 in Python 3 and I'm not sure exactly how to optimize my starting parameters. The example uses the regression ...
0
votes
0answers
16 views

Detect an indecomposable distribution through its Laplace transform?

I would like to decide whether a random variable $X$ is an indecomposable distribution. In this situation $X$ is obtained from real-life measurements - say $(x_n)_n$ - so it's not a particular closed ...
3
votes
2answers
27 views

Relationship between categorical factors

I am not sure what this is called in English, but if we have two categorical factors, we can say that one of them (A) is finer than the other (B) if it holds true that if two observations belong to ...
0
votes
0answers
13 views

Parameter Estimates and redundancy

I was wondering if someone can help report the finding on this table. I'm so confused with my Exp(B) being so high and theme nations being redundant. Thank you
0
votes
0answers
14 views

Sample size for testing an output distribution

Please excuse the lack proper mathmatical notation. This is mostly from intuition about the underlying logic. Given a function $f(x)\rightarrow$ A or B randomly The function should return a ...
0
votes
0answers
41 views

Intuition behind using Noise Contrastive Divergence in neural language models

I am going over this paper which uses NCE to avoid dealing with the normalization constant of a log bilinear model, when maximizing the likelihood. The problem is clear, but I don't understand what is ...
0
votes
0answers
5 views

How to translate theorem into R code properly? (ruin probability of a discrete-time bi-risk model) [migrated]

We're having trouble with the realization of this theorem (recurrence relation for estimating ruin probability of a discrete-time bi-risk model). Basically, here you can see the theorem itself with ...
0
votes
0answers
11 views

categorical weighted vector [on hold]

I have 4 variables Each variable is an ordered categorical variable The range of values for each variable is ...
2
votes
2answers
23 views

Detecting a difference in the direction of two groups of vectors

I have two groups of patients, one group obese, one non-obese. I have vectors representing the longitudinal axis of the kidneys in each patient. I am comparing the orientation of the right kidneys ...
0
votes
0answers
14 views

Conflicting results between GLMM and Post-hoc lsmeans

I'm studying the effect of pH and cross-types on mortality of fish. Treatment is categorical (2 levels: control and low pH) and cross-types is also categorical (4 levels: parents wild male x wild ...
3
votes
0answers
55 views

Hierarchical linear modeling of Brinley plot data

My question pertains to using hierarchical linear modeling / mixed modeling using lme4 in R on Brinley plot data. I have experience with R, but no experience with HLM, and limited experience with ...
0
votes
1answer
31 views

Is there an Equivalent of “proc surveylogistic” in R?

A colleague told me about "proc surveylogistic" in SAS -- see details here -- is there an equivalent function in R?
0
votes
1answer
14 views

Probability distribution on a subset of a simplex

I want to define a probability distribution on a subset of a simplex. for example, on a 3-simplex, we know that $x_1+x_2+x_3+x_4=1$ and $X \sim Dirichlet$. Would it be possible to constraint $X$ more ...
0
votes
0answers
9 views

How to assess the significant level of a sample difference per number of element

I have 3 samples of 28 paired elements which have been tested for normality and they are not normal due to biomodal distributions. I carried out a Friedman test and is not significant. However I know ...
5
votes
4answers
287 views

Should I use an average to summarize ordinal data?

I need to work out a "average" (for lack of knowing a better word) of ratings or perhaps I could call them labels. Basically, I have a list of words that have been rated 1 - 3 for difficulty. 1 being ...
0
votes
0answers
12 views

Neural Network - Learning accuracy drops heavily after a couple of epochs

I designed a neural network to classify some images into 28 classes. Here are the parameters : Weight Decay : 0.005 Momentum : 0.01 Learning Rate : 0.001 and 0.005 Learning Decay : 1 Input : 100x100 ...
0
votes
0answers
16 views

How to update latent discrete variables in MCMC?

Most of the discussion on Bayesian model with latent variables that I've seen fall into two classes: continuous latent variable underlying the observed discrete outcome (e.g. probit model (Albert ...
1
vote
1answer
26 views

Heteroskedasticity Question

I have a model that's affected by Heteroskedasticity: bptest(m1) studentized Breusch-Pagan test data: m1 BP = 65.055, ...
1
vote
1answer
15 views

Regression Using Surveys with Unequal Number of Responses

I am trying to figure out how to properly do regression analysis on a data set from a peer-review survey where individuals in the survey have an unequal number of responses. Below is description of my ...
0
votes
1answer
17 views

Generalized model with different kinds of variables

I'm working with captive jaguars behavioral data to answer how several independent variables affect the incidence of a certain behavior "E". My dependent variable is the number of times the behavior E ...
2
votes
0answers
26 views

Logistic Regression: Should I include a non-significant variable that notably increases the OR of a significant variable?

I am studying the effect of different pollutants on the probability of a genetic mutation. My binary logistic regression models are as follows: Model 1: Dependent variable: genetic mutation (binary ...
0
votes
0answers
7 views

How many parameters required to approximate quadratic function with NN

How many layers do you need to build a RELU network (1-layer or deep) to approximate x^2 function on [0,1] with 1e-6 accuracy. What is the practical result on the same, say with Tensorflow ...
0
votes
1answer
22 views

How to compare total effect of three variables across two regressions that use different subsamples?

I am running the following regression in Stata on two sub-samples (Low and High groups): \begin{equation} \begin{split} {ln(1+New\:co-investors)}_{i,t} = \alpha_0 &+ \alpha_{1}PreSuccess_{i,t-1} ...
0
votes
0answers
6 views

Equal Error Rate (EER) and Receiver Operating Characteristic (ROC) curve

I have a one-vs-all classifier set. This set consists of, let's say, 3 classifiers (LibSVM SVMs) each trained on data for a class and all other class data. The current setup for a sample is that the ...

15 30 50 per page