All Questions

Filter by
Sorted by
Tagged with
0
votes
0answers
2 views

Could a Hadamard product of 2 matrix also be a dot product of two vectors?

In a 2d Euclidean space, Let point $a=(a_x, a_y)=(1,1)$; Let point $b=(b_x, b_y)=(5,1)$; Let point $c=(c_x, c_y)=(4,4)$; the squared Euclidean distance between point a and point b is equal to $(...
1
vote
1answer
7 views

Does the percentage overlap in confidence intervals matter?

Basic stats question that's been bothering me. Let's say I've put out a survey question with two possible answers, and have gotten back responses that have overlapping confidence intervals (at 95%). ...
0
votes
0answers
5 views

What is difference in sampling distribution and sampling from distribution?

Do sampling distribution and sampling from distribution mean the same thing? I am interested in x~N($\mu$, $\sigma$).
0
votes
1answer
13 views

Why the dot product of two vectors in sklearn is not a scalar?

In a 2d Euclidean space, Let point $a=(a_x, a_y)=(1,1)$; Let point $b=(b_x, b_y)=(5,1)$; Let point $c=(c_x, c_y)=(4,4)$; the squared Euclidean distance between point a and point b is equal to $(...
1
vote
1answer
10 views

Understanding how the determinant of the multidimensional normal likelihood can overrule the prior probability

I am doing Bayesian inference. I have a normal prior probability distribution of some theoretical parameter $\theta$ and I am trying to update my knowledge of $\theta$ using some data $D$ and a model $...
0
votes
0answers
3 views

Looking at training progress of generative adversarial network (GAN) - what to look for?

I'm trying to understand the output of a GAN training process. I can always inspect the visual output (the generated images) to see how the GAN's evolving, but how can I evaluate training based on the ...
1
vote
0answers
12 views

Spearman 𝜌 as a function of Pearson 𝑟

It is common to talk about the linear correlation, Pearson's 𝑟, between two random variables $\{(𝑥_1,𝑦_1),(𝑥_2,𝑦_2),…,(𝑥_𝑛,𝑦_𝑛)\}$ as having two components: a) the copula and b) the marginal ...
-1
votes
0answers
8 views

return values of qqPlot in the car package [on hold]

In the RStudio envirenment, when I use qqPlot function in the car package, it returns a list with two values, and I do not know what these values represent, does anybody know this? The codes were as ...
1
vote
0answers
5 views

Which neural network model to choose between different iterations?

I was running an experiment with neural networks and I could see that training the neural network model with the same input give different results on the test. This should be due to the different ...
0
votes
1answer
18 views

In sklearn, it seems that `dot(x, x)` corresponds to `np.sum(X*X,axis=1)[:, np.newaxis]`, why is that?

In a 2d Euclidean space, Let point $a=(a_x, a_y)=(1,1)$; Let point $b=(b_x, b_y)=(5,1)$; Let point $c=(c_x, c_y)=(4,4)$; the squared Euclidean distance between point a and point b is equal to $(...
0
votes
0answers
9 views

How to impute missing values not at random?

My data consists of 202 cases, each stand for a single interview. The variables reflect the interviewers' and interviewees' behaviours during four different parts of the interview: p1, g1, pA, gA. in ...
0
votes
1answer
11 views

Is a predictive model the best way to generalize about my current data?

Suppose I have a customer dataset. My independent variables are various types of customer attributes (age, where they live, gender, price of the item they are potentially buying) and my dependent ...
0
votes
0answers
3 views

What is the difference between the average class accuracy and average instance accuracy?

In some papers, I find some strange evaluation metrics that did not give a clear explanation, like average class accuracy and average instance accuracy! What is the difference between both? I can not ...
0
votes
0answers
8 views

How to analyze two variable from one sample

Data was collected from 150 patients with lower limb infections. There are 34 patients were newly diagnosed. For diagnosis purposss we used two tools A. HBA1C B. FBS Results 1. HBA1c High with ...
0
votes
0answers
6 views

TensorFlow: What is wrong with my (generalized) dice loss implementation?

I use TensorFlow 1.12 for semantic (image) segmentation based on materials. With a multinomial cross-entropy loss function, this yields okay-ish results, especially considering the sparse amount of ...
1
vote
0answers
8 views

A comparison of the global optimal binwidth and local optimal binwidth of the histogram estimator

Suppose we have $X_1, \dots, X_n$ to be an i.i.d sample with unknown pdf $f(x)$ and cdf $F(x)$, and define $\hat{f} (x)$ to be the histogram estimator. We also define its Mean Integrated Square Error ...
0
votes
0answers
5 views

EM Imputation and missing age data

I've completed an EM imputation to replace a small amount of missing data. One of the missing data was within my age variable (age range of 20 - 54). My question is... the new score that has been ...
0
votes
1answer
11 views

Can Kruskal-Wallis test be used in groups of different size?

I am trying to compare Likert-scale answers to a survey applied in 3 different cities: A, B and C. I arbitrarily chose twice as many respondents from A, for a total of 500 answered questionnaires in ...
1
vote
0answers
8 views

Comparing predictability of outcomes across leagues

From time to time I encounter newspaper articles with titles like “Unpredictable English Premier League Keeps Us Guessing”, which make claims about the difference in predictability of outcomes across ...
0
votes
0answers
6 views

Minimum population size for a comparison of treatments

Is there a rule for minimum population size for horticultural experiments and trials? For example, growing a plant variety in 5 different soil types in 5 different locations. My apologies if my ...
2
votes
1answer
23 views

Kolmogorov-Smirnov (ks_2samp) p-value not as expected - Wrong test or understanding?

Context I am using scipy's ks_samp in order to apply the Kolmogorov-Smirnov-test. The data I use is twofold: I have a dataset ...
3
votes
0answers
22 views

How can you measure probability with a regression model? [on hold]

Classifier-based machine learning models have a corresponding "confidence" associated with each prediction. How can you get a confidence measure for a regression model?
3
votes
1answer
34 views

When rolling a dice N times, what is the probability of an $X$ appearing before the last $Y$? [on hold]

So a valid state is when the lowest index of an $X$ is smaller than the biggest index of a $Y$. For example $N = 5$, $X = 1$, $Y = 2$ (Roll dice 5 times, 1 appearing before 2) 1 4 2 3 1 2 1 3 4 2 ...
1
vote
0answers
22 views

Long-run covariance matrix estimators with Ledoit-Wolf (2004) shrinkage; what methods exist?

Ledoit and Wolf ("A Well-Conditioned Estimator for Large-Dimensional Covariance Matrices", 2004) proposed an estimator for the covariance matrix of a data set, $S^* = p I_d + (1 - p) \hat{S}$ with $p \...
0
votes
0answers
10 views

Bayesian regression not normal

Let's say Im trying to do a bayesian linear regression and I have some strong prior on the parameters x1,...,xn. However, after collecting my data I can clearly see the residuals are not normally ...
1
vote
0answers
8 views

Resampling methods or statistical tests for variables that comprise dependent and independent observations

I am currently working with a dataset that comprises measurements of multiple participants on two variables. I'd like to test the mean difference between both variables on statistical significance. ...
0
votes
1answer
12 views

Interactions between categorical and continuous independent variables

Im going to investigate if a disease have a negative impact on the development of children. The disease is the independent variable with additionally 10 confounders. Do I have to check for ...
1
vote
1answer
11 views

geeglm y ~ x1 + I(x^2)

In glm if a model is specified as ...
0
votes
0answers
9 views

Do these two Bellman equations express the same idea?

I am currently trying to wrap my head around the Bellman equation and found the following two definitions. The first one is taken from cs229 Stanford - link to the sources is avaiable below. The ...
7
votes
3answers
126 views

Do Bayesian credible intervals treat the estimated parameter as a random variable?

I read the following paragraph on Wikipedia recently: Bayesian intervals treat their bounds as fixed and the estimated parameter as a random variable, whereas frequentist confidence intervals treat ...
0
votes
1answer
4 views

Box Cox Transformation Is it possible to transform every kind of distribution into a normal distribution?

I would like to do a python script for estimating population parameters by means of a sample. The data contained into my sample are measurements. Nevertheless I know that all my measurements are not ...
0
votes
0answers
8 views

SEM output with a DWLS est - non normal distributed variables: feedback, possible overfitting?

I have a sem model with non-normal distributed indicators measured with Likert-scale (7 points - agreement). I have 4 LVs and 1 observed (N=287, data collection still in progress). As variables in my ...
7
votes
1answer
137 views

The No-Free-Lunch Theorem and K-NN consistency

In computational learning, The NFL theorem states that there is no universal learner. For every learning algorithm , there is a distribution that causes the learner output a hypotesis with a large ...
1
vote
0answers
17 views

Isolation Forest and average/expected depth formula

The Isolation Forest algorithm (Liu, Fei Tony, Kai Ming Ting, and Zhi-Hua Zhou. "Isolation forest." 2008 Eighth IEEE International Conference on Data Mining. IEEE, 2008. - link: https://cs.nju.edu.cn/...
2
votes
1answer
21 views

What are some of the most correct/accepted ways to tune and compare different models in an academic context?

Those days, I have been reviewing different academic papers which mainly compare the performance of different machine learning methods on a particular problem. And I was surprised by the variety of ...
2
votes
3answers
36 views

“Magical” variance reduction problem

I recently came across this toy problem: You have two sticks of unknown lengths $a>b$ and a measuring device with constant variance $1$ that you can only use twice. How can you construct ...
1
vote
1answer
14 views

hyper parameter tuning AFTER Nested cross-validation

I have read very well the awesome answers and suggestions by @cbeleites and @Dikran Marsupial here for nested CV but I am still confused about something: Basically now I understand that nested CV is ...
1
vote
0answers
7 views

Can three-level meta analysis be random-effects model and/or fixed effects model?

I am learning three-level meta-analysis and trying to deeply understand how this new relatively new approach fits into the more commonly used general meta-analysis (...
0
votes
0answers
6 views

Within subjects error bars in GLM [on hold]

My question is about calculating the within subject error bars in data I analyzed using a generalized mixed model. The dependent measure is accuracy (binary - correct/incorrect), and the fixed factors ...
0
votes
0answers
7 views

Relationship between sub sample and full sample coefficients

Consider a linear regression model: $$ y_{i}=\boldsymbol{x_{i}'\beta}+\epsilon_{i} $$ where $\boldsymbol{x_{i}'}$ is a column vector of covariates and $i$ is individual for a total of $N$ individual. ...
1
vote
1answer
18 views

Interpreting predictive models in the presence of omitted variables

Suppose the best predictive model from a set of possible models is a univariable model, due to lots of moderate correlations with other variables for example. However, if I use this model for ...
0
votes
1answer
27 views

When developing the Yule-Walker equations, why can we assume $E(X_{t-k} \cdot Z_t) = 0$

I have a AR(1) process $X_t = 0.4X_{t-1} + Z_t$. I want to derive the Yule-Walker equation. I multiplied by $X_{t-k}$, took the expectation of both sides, and got: $$E(X_{t-k}X_t) = 0.4E(X_{t-k}X_{t-...
0
votes
1answer
23 views

Why does the Yule-Walker equation for AR(1) only hold for $k \ge 1$?

I have a AR(1) process $X_t = 0.4X_{t-1} + Z_t$. I multiplied by $X_{t-k}$, took the expectation of both sides, divided by the variance (which I assume is stationary), and got the Yule-Walker equation:...
0
votes
0answers
10 views

Plotting simple slopes in RMANOVA?

I have an experiment that measures behavior across 4 blocks. I have a between-subjects continuous physiological variable that interacts with this block effect: physiology x quadratic block effect. I ...
0
votes
1answer
29 views

Question about PDF's for Random Variables

"Suppose we have the random sample of n independent and identically distributed random variables with a normal distribution. The probability density function of each Xi is..." If our variable was e....
0
votes
0answers
10 views

How to tackle package building problem in compiling R [on hold]

My question is about how to compile R on windows. I tried compiling R 3.6.1 with OpenBLAS 0.3.7 on windows 10 x64 using Rtools 3.5, but the process stopped due to a mistake: ...
1
vote
1answer
9 views

How do i re-train a final model after using oversampling?

I am a bit puzzled about the process of experimenting with a model and oversampling and then translating it to the final version of the model that will be used: I oversample the data (only the ...
2
votes
0answers
7 views

Learning a target feature from data

I have a dataset of customers (infos about them, as well as their buying behavior) to whom ads are sent regularly. How can I design a target feature that will result in a good model that predicts when ...
1
vote
1answer
37 views

What does Deviance mean in lmer

Probably a rather silly question, but I would like to have a clear explanation of what deviance in linear mixed models (using lmer) is. For instance, how do I interpret it along AIC, BIC, and LOgLik ...
7
votes
2answers
242 views

Can RMSE and MAE have the same value?

I am implementing cross validation and calculating error metrics such as RMSE, $R^2$, MAE, MSE, etc. Can RMSE and MAE have the same value?

15 30 50 per page