All Questions

0
votes
0answers
5 views

Is lmer or glmer appropriate for nested continuous proportion data

I have a reviewer that wants me to analyze my data along the lines: Con_Ratio ~ Range * Latitude * Longitude + (1 | Genotype/Pair). But I'm not sure if this can be done and how. My experimental ...
0
votes
0answers
3 views

Where can I find case studies for predictive modeling?

I'd like to practice predictive modeling. I worked through the labs and exercises in Intro to Statistical Learning by Hastie, Witten, James and Tibshirani. The perfect situation is to have a prompt, ...
0
votes
0answers
3 views

Correcting sample selection bias of binary classifiers

In fraud investigation the number of detected fraud cases can be very small when compared to the total number of cases. This would also apply to rare desease detected in a very small number of people ...
0
votes
0answers
6 views

Interpretation of the rate parameter of a Gamma distribution

I am toying with mixture models, especially in a bayesian context and the Gamma (or the inverse Gamma) distribution appears quite often. For example, inverse Gamma is used as a conjugate prior for the ...
0
votes
0answers
4 views

specific equation for modified wilson confidence interval

I recently read the Brown, Cai, Dasgupta paper on interval estimation for a binomial proportion where they propose the modified wilson method as a better alternative to the standard wald interval. I ...
0
votes
0answers
4 views

Cook's distance - problem with understanding

I have a problem with calculating Cook Distance (I'm trying to understand it). Ok so here is the task and my 'solution'. I'm asking for comment, is it ok, or what do I wrong. We have simple linear ...
0
votes
0answers
4 views

Selection criteria for penalty parameters in the ridge multinomial logit model

I appeal to you for the following doubt. I am adjusting a ridge multinomial logit model but I have problems in the criterion when choosing the lambda parameter that gives better results, besides ...
0
votes
0answers
10 views

How to show that cov(Yi, Y-bar)= (σ(^2) y)/n

I'm trying to figure out how to do this proof, and then use it to show that sample variance is an unbiased estimator.
0
votes
0answers
4 views

Visualizing separability / independence

I’d like to visually ‘see’ the independence of random variables. I tried plotting f(x), f(y), and f(x, y) for independent and dependent pairs of variables. However, the difference is still not ...
0
votes
0answers
5 views

Advice on ML ideas/models for a data set I have

I have a very large marketing data set (300GB in size) and I am wondering what ML models I can apply to it. The dataset consists of transactional data from supermarkets. The type of data I have is the ...
0
votes
0answers
11 views

Correlation above 1 between second-order and first-order latent variable

So I ran CFA on an exhaustion measure comprising of three facets which were specified as first-order latent variables. When I added a secon-order latent variable to the model the correlation between ...
0
votes
0answers
3 views

Data exploration to determine if GAMs are appropriate

How to decide, based on data exploration, between a GAM and a GLM. Linear Models (LM) assume that the relationship between the response and the predictor are linear. Generalized Linear Models (GLM) ...
2
votes
1answer
6 views

How to conduct power analysis for unbalanced one-way ANOVA in R?

I am looking for a way to conduct power analysis for unbalanced one-way ANOVA in R. I found the pwd package; however, it only allows me to calculate power for ...
0
votes
1answer
10 views

Estimating Differential entropy from unbiased samples of a probability distribution

If I can get N unbiased samples $x$ from $p(x)$ how can I approximate the Differential entropy: $$H(X) = -\displaystyle\int_{x} p(x)\log p(x) dx$$ I'm not very knowledgeable in statistics so I'm not ...
0
votes
0answers
9 views

I am facing the same error [on hold]

mydata3=mydata2[,c(2,4,7,9)] set.seed(123) model <- train(fwd_def_status ~., method = "rpart" , data=mydata3) What to do in the case where my dependent var is part of mydata3?
0
votes
0answers
10 views

forget_bias interpretation in tensorflow

In Basic LSTM cell of tensorflow there is an argument named forget_bias. From the documentation of ...
1
vote
0answers
6 views

Unit-root and Johansen- lack of normal distribution. Please help!

I have a question concerning unit-root data and normal distribution. As an assignment, I am checking the long-term relationship between unemployment rates and labor force participation rate. First I ...
1
vote
0answers
6 views

Weighted covariance with different reliability weights?

Suppose observables $X$ and $Y$ possess different reliability weights $w_{x,i}$ and $w_{y,i}$ for the possible elements $x_i\in X$ and $y_i\in Y$ respectively. Considering a sequence of consecutive ...
1
vote
1answer
22 views

Out-of bag error in Random Forest

I am trying to code my own, simple version od RandomForest function in R for learning purposes. However I have a hard time understanding the concept of the out-of-bag error. Is it simply done by ...
0
votes
1answer
21 views

Is it reasonable to display “percentage data” in a boxplot, why?

I have data that are in fact percentages of C (bound to clay) combusted in a certain temperature interval. Exemplary data: ...
0
votes
1answer
11 views

What test for a 4-level categorical variable and a continuous variable?

I'm currently doing research on whether image quality affect engagement. Image quality is given in 4 categories (bad, benchmark, semi-professional and commercial level) and engagement is in how many ...
1
vote
0answers
14 views

Asymptotically unbiased estimator vs consistent estimator [duplicate]

I'm wondering if there is a difference between an asymptotically unbiased estimator and a consistent estimator. For asymptotically unbiased estimators, the expected value of the estimator converges ...
0
votes
0answers
6 views

how to use Likert Scale to prove hypothesis

How to use data collected from likert scale (five point) to prove hypothesis. For example. Hypothesis 1: Internet marketing is cost efficient. Statement 1: internet marketing required less budget. ...
0
votes
0answers
12 views

Use PCA in order to show impact of variables on clusters

I did a clustering of selected variables. Is it possible to use the PCA (contribution, correlation) in order to show the impact of each variable in the clustering? (cfr. image 1) and add complementary ...
0
votes
0answers
2 views

GWAS genotype/phenotype datasets for supervised learning model testing

I'd like to play around with several ML models and test their predictive power using some good datasets. I need datasets of genotype (a set of SNPs) and phenotype (some trait). If possible, I'd ...
0
votes
0answers
8 views

How many parameters are in this specific model

I am planning on doing Structural Equation modeling on the following model that is pictured: I am trying to calculate my needed sample size. I have read the rule of thumb is 200 for SEM or 20 cases ...
0
votes
1answer
18 views

Do these standardized residuals show heteroskedasticity?

I'm practising in the individuation of heteroskedasticity from the standardized residuals. I know that, if the time series is homoskedastic, the spread of the residuals should be constant and random ...
0
votes
0answers
3 views

What type of R-squared measure should I use? [on hold]

There are several R-squared types out there for generalized linear models. As far as I know, the choice of R-squared depends on the error distribution assumed and the link function used. So my ...
0
votes
0answers
4 views

Nested models and ANOVA: F ratios

I have some commuting data involving a factor B (district) that is nested inside another factor A (city). I am assuming both factors are fixed. I have calculated F ratios involving $MS_A/MS_R$ and $...
0
votes
0answers
5 views

Rescaling Linear Impulse Response Functions, Innovations, and Confidence Bands

all. I am using a VAR model to do a bit of analysis. I obtain cumulative (linear) orthogonalized impulse response functions (COIRF). Because I am conducting similar analysis across different time ...
0
votes
0answers
13 views

Unable to remove heteroscadasticity

This is my model: lm(PCTUI~year+statefips+factor_agecat+factor_sexcat+factor_racecat+factor_iprcat, data = train) I have factorized the categorical variable. ...
0
votes
1answer
19 views

multiple one sample t.test with ANOVA

If I want to see if the mean of 3 different groups is above a specific threshold instead of doing 3 on-sample ttest can I use anova? So instead of 3 ...
0
votes
1answer
11 views

Moving Average Representation of a Stationary Time Series

I was wondering if this equation is considered a Moving Average process of order 13? If so, does that mean that the coefficients at times t-2 to t-11 are 0? As they are clearly not present in this ...
0
votes
0answers
6 views

How to caluclate robust standard errors for a multinomial logistic regression (using the multinom command)?

I've estimated a multinomial logistic regression model using the nnet package and the multinom command. Now I would like to calculate robust standard errors for my coefficients but I don't know how to ...
0
votes
1answer
5 views

Why resolution is not important for pre-trained models

As far as I understand (and even successfully applied in Kaggle competition), it's possible to feed images of any resolution into the pre-trained model (e.g. ResNet34). But I do not understand, why it ...
1
vote
1answer
6 views

how should I specify a deterministic trend in my time series data?

How can I specify a trend (term) in my time series data? does it have a logical procedure or is it totally base on visual interpretation of historical plot?
0
votes
0answers
8 views

GAMM mgcv shifts in partial residuals when random effects are included

When running a gamm and seing its plots I found the residuals locations are shifted according random effects inclusion/exclusion. I am not understanding how its possible to change data points location ...
1
vote
0answers
11 views

Is my interpretation correct for these residuals plots?

In preparation for my exam, I'm trying to interpret the residuals in order to understand if the time series has been modelled correctly. Otherwise, I have to suggest an improvement. Here is the text: ...
-1
votes
0answers
31 views

PDF of $\frac{(X_1-X_2)^{2}}{2}$ where X1 and X2 are independent standard normal [on hold]

I'm trying to find the PDF of $$\frac{(X_1-X_2)^{2}}{2}$$ where X1 and X2 are independent standard normal. Any hints on how to proceed with this?
0
votes
0answers
4 views

Questions about the interpretation of system-dynamic simulation in R

I try understand simulation modeling in R using DeSolved package. As source i used this article https://api.rpubs.com/rsmard05/sysDynR. It is detailed, but some things are incomprehensible to me from ...
0
votes
0answers
6 views

Transposing data: from repeated measures to independent samples

Assume that I conducted an experiment with 20 questions. The questions 1-10 are Type A questions whereas questions 11-20 are Type B questions. I am wondering whether two types of questions differ ...
0
votes
1answer
13 views

Generative model to generate hidden activations coming from a previously trained hidden layer

I need to train a generative model to generate vectors which resemble the activations of a particular hidden layer of a neural network which has been previously trained. In particular, the hidden ...
0
votes
1answer
10 views

What is the difference between SSIM and MS-SSIM?

I would like to know what is the difference between SSIM and MS-SSIM? Also, there is a built-in function in Tensorflow for both of them, I am curious to know when should I use SSIM and when MS-SSIM? ...
0
votes
0answers
7 views

Slope after scaling transformation [on hold]

I want to take up on slope in scaling transformation where I asked whether it is allowed to transform back the calculated slope from a logarithmical transformation. The background is: Let it be ...
0
votes
1answer
19 views

One-hot-encoding gives untractable amount of classes

I'm performing regression on the price of bycicles based on their brand, model and submodel. These features are hierarchical: one model belongs only to one brand but one brand can have many models. ...
-1
votes
0answers
13 views

bsts posterior distributions

some basic questions re bsts - not how to run the programme but what it is actually computing. I cannot get the answers by typing bsts, which leads to Call("analysis_common_r_fit_bsts_model_"...) ...
0
votes
0answers
14 views

Experimental design for simulation experiment

I'm interested in investigating the effect of a treatment on survival times of a patient. The "patient" is a complex program with many interacting categorical and continuous variables. It also has a ...
1
vote
0answers
4 views

Do propensity score matching methods need to factor in the index date in a matched cohort context?

I am working on a comparative effectiveness study where we estimated the propensity of treatment between two groups and are exploring matching on the propensity score. The study period is long, ...
0
votes
0answers
13 views

Regression in R [on hold]

I run a script, but R give me a message: ...
0
votes
1answer
23 views

Help creating a formula for a probability problem

I was thinking of a probability problem, but I'm having trouble thinking about what the formula would be to solve it. Say you need 10 events to win a game. 10% of the time you press a button, it ...

15 30 50 per page