0
votes
0answers
2 views

Selecting priors based on measurement error

How do you calculate the appropriate prior if you have the measurement error of an instrument? This paragraph is from Cressie's book "Statistics for Spatio-Temporal Data": It is often the case ...
0
votes
0answers
6 views

In Graph Transformer Networks, which parameters are tuned during back-propagation?

Referring to the milestone paper "Gradient-Based Learning Applied to Document Recognition" of LeCun, Bottou, Bengio and Haffner, which parameters of the graph transformer networks for global training ...
0
votes
0answers
9 views

Finding MLE when there's constraint that parameters sum to 1

In a total population of $n$, we have $k$ types of people, with $n_1, \dots, n_k$ of them in each corresponding group. The probability of a person belonging in a group is $\theta_1, \dots, \theta_k$, ...
0
votes
0answers
8 views

covariate selection for a cox model by Lasso using glmnet

I would like to use model selection through shrinkage (Lasso) using glmnet. So far I did the following: ...
0
votes
1answer
15 views

A simple question on CLT in possible connection with Berry-Esseen thm

I am curious about the contents while I read a note on machine learning. It could be obvious. So, please let me know if I am missing some fundamental things. $X_1,X_2,...,X_n$ are from an i.i.d. ...
0
votes
0answers
11 views

Multiple Linear Regression: Obtaining a Stable Model

I am working with a data set of ~1200 rows and 60 variables, and I'm trying to build a multiple linear regression model. I do this by separating 10% of the dataset to be used for validation and I use ...
0
votes
0answers
6 views

How to convert parameters of a multivariate lognormal to a multivariate normal

I have the means and the variance-covariance matrix of a multivariate lognormal distribution. How to use them to obtain the means and variance-covariance matrix of the corresponding multivariate ...
0
votes
0answers
7 views

Are there free APIs for searching news articles that I can use to collect trend data in news coverage?

I am working on a data-visualization web application that looks at trends in American news media coverage over time. It takes a keyword (or keywords), a date range, and a time increment as parameters ...
0
votes
0answers
4 views

Squared residuals from VAR as an estimate of conditional variance

The question is how justified it is if I use squared residuals from VAR system as an estimate for conditional variance of low-frequent (quarterly) data? Say there is a system of 2 equations: ...
0
votes
0answers
6 views

Entropy stays the same with a larger distribution?

Based on the given definition of entropy, $H(P(X)) = -\sum_i P(x_i)log_2(P(x_i)$, it appears that if I have a distribution $P_1(x) = [\frac{1}{4},\frac{1}{4},\frac{1}{4},\frac{1}{4}]$ and another ...
0
votes
0answers
7 views

How to write an AR(2) stationary process in the Wold representation

I managed to write an AR(1) process in the Wold representation with help from the geometric series. I am having trouble with a stationary AR(2). How could I do?
0
votes
0answers
11 views

Help in estimation : MLE formulation

The intrinsic dimension (ID) of a data set generated from dynamical system is the minimum number of free variables needed to generate the data. Given a time series expressed in $m$ dimension (ID) we ...
0
votes
0answers
8 views

Help! Stat test to compare groups

I am comparing two counties to see which one has more grandchildren living with grandparents that left the home because of lack of program support. One county has a grandparent support program and one ...
0
votes
0answers
12 views

Changing polynomial degree leads to changing p-values in OLS regression

I have a question about interpreting coefficient $p$-values when fitting a polynomial function with ordinary least squares. When I sequentially fit a linear, then quadratic, then cubic etc. ...
0
votes
1answer
13 views

AFT model with time varying independent variables

I am a newbie in survival analysis and I would like to pose some simple questions, after reading numerous posts regarding how to perform survival analysis in R. So, what I would like to know is: Can ...
0
votes
0answers
8 views

T-Test using MPlus

Is it possible to perform a paired samples t-test in MPlus? I am confused, as I have found on the web that you can run a wald test, but I am not sure if it is the same as a t-test. The reason I want ...
0
votes
0answers
10 views

Experiment design: classifying 3 classes (2 easy, 1 hard)

Bit of background: I have a problem of classification of 3 classes. Given the training set (80%) and a held-out set (20%), I found out that 2 classes are easy to discriminate/classify. The third class ...
0
votes
0answers
11 views

Neural Networks sigmoid activation with bias updates

I am trying to figure out if I am creating an artificial neural network using the sigmoid activation function and using bias correctly. I want one bias node to input to all hidden nodes with static ...
0
votes
1answer
18 views

Understanding COVARIANCE when using same scale

Assuming that an experiment has 3 variables. Time, Temperature inside, Temperature outside. Also, considering that both the temperatures are measured using the same scale say Degree Celsius. If the ...
0
votes
0answers
3 views

Accessing zoo object from list of lists returned from RJSDMX download of ECB data [migrated]

I am having trouble understanding or finding information on how to access the list elements returned from the European Central Bank download using the RJSDMX package. I am downloading time series for ...
0
votes
0answers
27 views

Prove that exists, and is $\lim_{M\to\infty}\frac{M F'(M)}{1 - F(M)} < \infty$ iff $F(z)$ is a power-law

Standard Definitions Define regularly varying with index $a \in \mathbb{R}$ as $$ \lim_{z\to\infty} \frac{L(t x)}{L(x)} = t^{-a}, \forall t>0 $$ A slowly varying function is nested, where $a=0$. ...
3
votes
1answer
16 views

Comparing between random effects structures in a linear mixed-effects model

During a recently asked question about linear mixed-effects models I was told that one should not compare between models with different random effects structures using likelihood ratio tests. Up until ...
0
votes
0answers
4 views

what is the best forecast interval for tbats?

I used tbats to fit a model to a set of weekly data (but only for weekdays) so I have seasonality of 5 for daily and 261 of annual. I wonder if tbats works better by updating the model using observed ...
1
vote
0answers
12 views

Consequence of order in a survey

Some surveys ask the user to vote for a proposal. The proposal are listed from the highest voted to the lowest. So it's probable that the user will not see all the proposals but his attention will go ...
0
votes
2answers
11 views

Large difference in number of cases in each category of a variable

I want to run an analysis on a data set. However, the primary predictor variable (5 point scale) varies greatly in size of each group. I plan to create a dichotomous variable from these 5 category. ...
0
votes
0answers
6 views

Tree classifier or nested model?

I am new to statistics and was wondering what the right kind of model to use for the following scenario. I have two sets of continuous observations A and B for 50 samples. These 50 samples are ...
0
votes
0answers
13 views

Running K-mean after PCA SPSS [on hold]

Is there a script that computes factor scores using the component score coefficient matrix (SPSS PCA output), that can then be used as the basis for K-means clustering? As an alternative is there a ...
0
votes
0answers
11 views

Model Consistency Metric

When fitting a parametric model to a data set assuming that our selected model class contains the truth, what performance metric should be used so that parameters converge to the truth as sample size ...
0
votes
0answers
7 views

what is the maximum practical number of levels for ANOVA

I'm trying to find a reference on the maximum practical number of levels in a factor for ANOVA. I know theoretically, there is no limit, but I find that after some number of levels, the results ...
2
votes
0answers
13 views

How to draw these t-statistics in R

When determining the necessary sample size for a t test of a difference of mean of two populations a good rule of thumb is typically $$ n = 16 {\sigma^2 \over ...
0
votes
1answer
31 views

How can I run an analysis of variance with one independent variable and multiple dependent variables?

From my limited statistical knowledge, I could use MANOVA if I had multiple independent variables (x1, x2...xn). What can I do (specifically in R) with one "x" variable and multiple "y" groups? I'm ...
1
vote
0answers
4 views

How to model non-linear, linear and crossed random effects in one model

I have a model with fixed and crossed random effects like this: glmer(response~1+var1+var2+var3+var3^2+(1|var4)+(1|var5)+(1|var6), family="poisson") Now, I decided that variable3 is best modelled ...
0
votes
0answers
8 views

How to model data

I am attempting to model a specific variable's sensitivity to a feature set. In concrete terms, I am trying to predict the duration (PAUSE_KS) of a letter (...
0
votes
0answers
3 views

Average multiple precision recall curves

I have a binary classifier that I evaluate using cross validation. The classifier gives me a score for each observation and for each of the test sets I use a varying threshold to compute precision and ...
0
votes
0answers
27 views

Linear regression with dummy variables: p-value calculation

The standard procedure for finding p-values for linear regression coefficients is usually like this: $$Y=b_{0}+b_{1}X+\epsilon$$ Since $\hat{ b_{1} }=\frac{\sum Y_{i}(x_{i}-\overline{ x ...
0
votes
0answers
9 views

Parameter estimation for dynamic regression models with correlated noise ARMA errors

I'm reading the Dynamic Regression Models chapter ( https://www.otexts.org/fpp/9/1 ) in Professor Hyndman's book, and I couldn't understand how to fit the regression model when the error is modeled ...
0
votes
0answers
17 views

Find variable k when given 2 marginal distributions

Given $f_x(x) = \frac{k}{1+4x}, -\infty<x<\infty$ and $f_y(y) = \frac{k}{1+4y} , -\infty<y<\infty$, find $k$. $x,y$ are independent random variables. What I've tried: Since the variables ...
1
vote
1answer
18 views

Seasonal adjustment for a series that has already been adjusted

A dataset I am working with (from the OECD), for harmonised unemployment seems to be seasonally adjusted: The unemployment rates shown here are calculated as the number of unemployed persons as a ...
0
votes
1answer
16 views

Does the calculation of error bars in lme4 require the Cosineau (2005) correction?

In Cosineau (2005) a method for calculating within-subject design error bars which removes the between subjects variance before calculating confidence intervals, error bars and so on is suggested. I ...
1
vote
0answers
16 views

Calculating n: Determining r

I have to calculate n for my research. I'm using a calculator (this one: http://www.cct.cuhk.edu.hk/stat/other/correlation.htm). α = 0.05 β = .2 r = ... I have trouble figuring out what r is. I get ...
1
vote
0answers
7 views

Relative weights in regression analysis in SPSS: Matrix-approach vs. factor and regression

I am trying to perfome a relative weight analysis as described by Johnson (2000). I have 13 predictors to a more general indicator. Initially, I started by: running a principal component analysis ...
0
votes
0answers
9 views

SPSS question: Calculating a variance within one record [on hold]

How can I compute a variance for several scale scores, within people? Say I have 100 people and they have scores on 5 variables, say math, verbal, mechanical, reasoning, and memory. I would like to ...
1
vote
1answer
20 views

How to deal with heteroscedasticty: choosing between White, WLS or Log linear model?

I am dealing with heteroscedasticity, and as we learned several methods to deal with the issue, I would like your help in choosing which one. The problem comes out of the econometrics book of ...
1
vote
1answer
14 views

Statistical test for power law samples

What is the t-test analog for testing against the null hypothesis that two samples come from the same distribution, if the two samples are distributed according to power law and have different number ...
0
votes
0answers
7 views

Implementing DLM in R [on hold]

I am new to R and DLM. I want to implement a DLM model in R. I have a time varying data set with me in excel where I have 1 dependent and multiple independent variables. Any help is appreciated.
1
vote
0answers
9 views

When to use minimum mean square error (MMSE) estimate instead of maximum a posteriori (MAP) estimate

What are the advantages and disadvantages of MMSE estimates and MAP estimates?
0
votes
0answers
12 views

Determining number of clusters K-means

I would like to automatically determine the number of clusters for K-means. I have read that elbow method could be used for that. The thing that confuses me is - I have to rerun algorithm while ...
1
vote
1answer
23 views

Reporting t-tests instead of simple linear regressions

Many papers in health research use the following format: Does A cause B? t-test A vs B multiple linear regression of B on A, adjusted for suspected confounders make heroic inferences Why is ...
0
votes
0answers
22 views

posterior distribution if I dont Know likelihood [on hold]

How can I find posterior if I know prior is Gamma(a,b) and likelihood is augmented ~~~~~~~~~~~~~~~~~~~~~~~~~~~
0
votes
0answers
13 views

Multivariate Multiple Logistic Regression in R

I have several dependent and independent variables. All my dependent variables are binary, therefore, I want to perform a multivariate multiple logistic regression, is that possible to do in R?

15 30 50 per page