All Questions

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

Can I use UNPAIRED post-hoc analysis for PAIRED omnibus testing?

If I have a omnibus statistical test with unpaired assumption (e.g.Kruskall-Wallis), could I ever use the opposite (paired) post-hoc analysis? (e.g. Wilcoxon signed-rank for post-hoc analysis of ...
0
votes
0answers
3 views

What is the suitable distance function for zero-inflated matrix?

I have a feature matrix, where the columns correspond to the features and the rows are the data points. My matrix is zero-inflated, meaning there are many false-negative zero entries in my matrix. I ...
0
votes
0answers
2 views

Ranking Methodology

I came across an interesting method of ranking entities (products) today, and I wanted to hear some perspectives on this approach. Basically, the assessment asks a set of 30 personal value statements ...
0
votes
0answers
4 views

Does the sum of discrete uniforms coverge to a discrete Gaussian?

Is there some analogous of the Central limit theorem for discrete uniforms and discrete normal distributions? To be more specific, let's say we have identical and independent random random variables $...
1
vote
1answer
5 views

Is the difference between two MSEs significant?

I developed several Elo rankings and used MSEs to compare them on their predictive capacity of the 2018 World Cup. I've been asked to use a statistical test to find if the difference between two of my ...
0
votes
0answers
8 views

Is there a relation between training set size and number of trees in a random forest?

If the number of trees matches training set size, there could be a tree for each case, probably leading to overfitting. Are there recommendations for number of trees based on training set size?
0
votes
0answers
3 views

Tune the input size of the image on known architecture

Known CNN and FCN architecture (in computer vision), such as Inception, Resnet, Alexnet, etc, have a specific input size, that can't be changed once the architecture has been chosen. Everyone that ...
0
votes
1answer
8 views

How to identify relationship between variables from scatterplots?

I want to understand the relationship between a region's health and wellness demographics (% obese, % smokers etc.) and their injury rates, for ex. how does change in a metric say '% obese people' ...
0
votes
0answers
5 views

What statistical distribution test to use for comparing Dataset and its subset?

I have two sets, A and B ,containing height of students. Set A contains height of all students in the class and Set B contains height of some students from the same class. Hence, Set B is a subset of ...
0
votes
0answers
10 views

Two variables are correlated but regression is not significant?

In simple linear regression analysis, is it possible that "two variables are correlated but regression (main effect) is not significant"? What does the result mean? NOTE: My question is different ...
0
votes
0answers
4 views

Can one calculate a Population Attributable Risk for a multilevel categorical variable or for a continuous variable?

According to StatisticsHowto amongst other sources, the Population Attributable Risk (PAR) is computed as: $PAR = \frac{P_e (RR_e-1) }{ [1 + P_e (RR_e-1)}$ Where: $P_e$ = Proportion of exposed ...
0
votes
1answer
8 views

What is the most appropriate way to cluster ranks?

I have ~30 observations of individuals ranking 20 different products from top to bottom (1-20). I would like to have a way to "cluster" these individuals based on their rankings of the different ...
0
votes
0answers
7 views

How to plot empirical densities in the same graphic(with same dimensional as it were plotted alone)

I'm plotting 5 densities in the same graphic, one of them from normal distribution and the others are empirical. When I plot individually, the densities has the right shape, but when I plot together (...
0
votes
0answers
9 views

Using a series of posterior distributions as a response variable

I have a Bayesian model that estimates survival probability of insects at a site. So I have a posterior distribution for survival for each site. I want to test the effect of habitat type on survival....
0
votes
0answers
6 views

Similarity measure/metric for long time series

I'm looking for a similarity measure/metric to cluster long time-series datasets. I feel that Euclidean distance won't do any good for my application, for it is not robust enough to detect patterns ...
0
votes
0answers
8 views

Autocorrelation linear combination

Suppose I have an index $X_t$ over time, which is a linear combination of $N$ other time-series $x_{i,t}$. So $X_t= \sum_i^n w_{i}x_{i,t}$,. Is there a theoretical/statistical formula that decomposes ...
0
votes
0answers
9 views

Which is the right test?

I try to find out whether there are significant differences in several Categories between 3 groups groups. If there are differences, in which Category and between which group they occur? My data looks ...
0
votes
0answers
5 views

two condition before/after test with different population sizes

Imagine a stream of patience coming to a clinic. Some of them were targeted by an add (treated) some didn't. users are treated 90% and controlled 10% (by user id) users are not-repeated (every day ...
0
votes
0answers
5 views

Statistical Analysis of 3 groups(parameterisation of same algorithm) under the same dataset: non-repeated measures or repeated-measures?

I'm doing the statistical analysis of the performance of 3 parameterisations of the same algorithm under the same dataset. This performance is user-evaluated under a single Likert-type item (5-values)....
0
votes
0answers
10 views

Matrix inversion in the smoothing splines

The question is about the matrix inversion in the smoothing splines. Given observations (y1, x1), ..., (yn, xn) and a choice of $\lambda \ge 0$, the smoothing spline estimator, $\hat{f}_{\lambda}$ is ...
1
vote
1answer
15 views

What is the meaning of generating data from a probabilistic model such as a naive bayes classifier?

I am studying probabilistic modeling but I am stuck with the concept of generating data from the probabilistic model. Say I have built a naive bayes classification model, what is the point of ...
2
votes
0answers
25 views

Can I include random slope for a fixed effect if I only have 1 sample from a few subject ID's

This is my first post here at Cross Validated. Im new to both R-programming and statistics and I have a few questions regarding the statistics of a clinical study I'm currently working on that relate ...
0
votes
0answers
7 views

Getting standard errors after `esttab` in `mixed` regression [on hold]

I am interested in the variance of a random coefficient, and it's standard error, of a mixed regression. Suppose I estimate as follows: ...
-1
votes
1answer
17 views

ggplot2 simple line plot [on hold]

enter image description here Here is my data. What I want is just to draw a line graph using ggplot2, where x-axis is "year" and y-axis is "Not at all". But I cannot get the line graph right, that is,...
0
votes
0answers
11 views

Statistical Comparison of Algorithms by User Ratings

I have an experimental setting where I compare 3 algorithms on the same dataset(n_sources), through user subjective evaluation of the produced outcomes(each algorithm does a different kind of sound ...
0
votes
1answer
27 views

Is the chi square test one type of univariate analysis?

Somewhere I read that for categorical variables, the univariate analysis includes only descriptive information. What about chi square test? Could not we assume the chi square test as univariate ...
0
votes
0answers
6 views

Using kin.blup function from rrBLUP packge to calculate BLUPs to use in GWAS [on hold]

I need to calculate BLUPs of a trait for 200 wheat lines. The lines BLUP predictions will be used as traits in GWAS. Each of the lines was tested in 8 fields (environments). I wonder if it makes ...
0
votes
0answers
10 views

Is there a simple formula to calculate sample size needed for precision and recall

I have trained a model on 30 towns and this produces good results. I want to apply the model to hundreds of new towns. These are likely similar but I want to measure results and identify any that do ...
0
votes
0answers
14 views

Reverse PCA. How to get reconstructed data? [duplicate]

I am working with PCA in Matlab. I have 651 data points (in grid) which show vertical crustal motion. After PCA i want to reconstruct data from several components (PC1, PC2, PC3,...) for each point ...
0
votes
0answers
4 views

GARCH (1,1) - stationarity in case of insignificant alpha?

the questions are about GARCH-t (1,1) [t-distribution]. The first question in GARCH-t (1,1) model, the alpha (ARCH) is insignificant. How to rewrite the model? The second one, in case of ...
0
votes
0answers
6 views

Sampling: When is it better to use Simple Random Sampling rather than Stratified Random Sampling?

I know that stratified random sampling is almost always preferred over simple random sampling, but I have also read that the Variance of sample mean (x-bar) from stratified random sampling could ...
0
votes
0answers
14 views

Analytical solution of $\sin(exp(\lambda))$? [on hold]

I am trying to solve analytically the function $\sin(exp(\lambda))$, where, Exponential Distribution described as, $f(x;\lambda) = \lambda e^{- \lambda x}$ $\mu = \sigma$, skewness =$2$, and ...
0
votes
0answers
9 views

Difference-in-difference to estimate gradual (i.e. slow) policy effect

I want to evaluate the impact of a policy on a variable $Y$. In the figure, I plot the mean of $Y$ over time in both the control and treatment groups (the vertical line represents the reform). The ...
1
vote
1answer
13 views

Using instance weights in XGBoost

I want to understand whether giving weights to instances across a dataset in XGBoost using the below method makes sense. I switched to this method after trying out a few approaches that didn't fare ...
1
vote
1answer
19 views

Important features for the XGboost algorithm are also the most important for the training of DNN?

I know that both a deep neural network (DDN) and the gradient boosting decision tree algorithm Xgboost can be used for the task of classification. I'm using a DNN first and it works fine. With ...
0
votes
0answers
16 views

Minimum number of stores-set cover problem in R [on hold]

I have a list of n products that I want to buy. Also, I know k stores and the availability of products that I want to buy on these stores. I need to find the minimum number of stores to satisfy the ...
0
votes
0answers
11 views

How to describe the results gained from LOOCV

I am using LOOCV as a method to validate a classification algorithm. I have a dataset with 2 observations per case. I use LOOCV and test one observation against the other (because the self-hit from ...
-1
votes
0answers
15 views

Understanding relationships between multi-level categorical variables [on hold]

Updating per request by mods: GLM can be applied to categorical data, where such data has been treated. In the case of R, this is done via factor. However, I have ...
0
votes
0answers
23 views

Median for symmetric distribution

When do the spatial median or the L1-median and the componentwise median coincide ? Does it happen for only a symmetric distribution or other cases too ? Also, are both of them equal to the mean for a ...
1
vote
0answers
11 views

Chi_square test, population and validating results

I have a data set of 200K people. They are not the whole UK population but they are the whole university's population I work with so I suspect they are my population. Am I correct? I created two ...
0
votes
0answers
8 views

How do I use additional features when doing sentiment analysis?

Say I have a dataset of 3 columns: text, topic and sentiment. Each row of the ...
0
votes
0answers
10 views

Effect size for contrasts tests in ezANOVA

My case: R user. I'm conducting 3-way ANOVA with 1 within and 2 between factors using "ez" library. N = 120, balanced-design. I would like to conduct contrasts tests with corresponding Cohen's D ...
0
votes
0answers
12 views

What is the correct formula for calculating Percentile

There are two formulas that are typically given for calculating Rank associated with a percentile. They are as follows $$1) Rank = \frac{Percentile}{100} \cdot (N+1)$$ $$2) Rank = \frac{Percentile}{...
0
votes
0answers
5 views

What are the methods possible for using Unicode for Optical Character Recognition( OCR) using Python? [on hold]

I would like to know on multiple ways on which i can use Unicode for OCR on images(.jpg and .png) using python to extract text. …
0
votes
0answers
7 views

Is there any paper about vanishing-gradients of LSTM?

Some web pages mentioned that LSTM causes the vanishing or exploding gradients if the sequence is too long. These are one of the pages mention the problem: https://machinelearningmastery.com/...
-1
votes
0answers
8 views

What is the most popular Semi-supervised learning algorithm regarding regression?

I want to use many unlabeled samples to get a model to predict price. I want to know what is the most popular and efficient and high-accuracy semi supervised method regarding regression problems ps:...
1
vote
1answer
17 views

Suggest a model from ACF and PACF values

Considera sample of 50 observations from a stationary process with $$\begin{array}{c|c|c|} \text{lag} & \text{acf} & \text{pacf} \\ \hline 1 & 0.9 & 0.9 \\ \hline 2& 0.85 &...
2
votes
2answers
28 views

Best way to pass distribution estimates as a feature into deep learning

I have been googling a lot and somehow cannot find a good answer. Lets say we have deep neural net model, arbitrary topology. Also we have 10 features and for each features we got 1000 observations ...
0
votes
1answer
17 views

Maximum Likelyhood Estimator (MLE) vs. Bias

If we use the MLE methhod to find the estimator of the variance we get: $\hat\sigma ^2 = \frac{\sum(x_i - \mu)^2}{n}$ Where we can plug the MLE estimator for $\mu$ and get: $\hat\sigma ^2 = \frac{\...
0
votes
0answers
12 views

Calibration curve of XGBoost for binary classification

I'm working on a binary classification problem, with imbalanced classes (10:1). Since for binary classification, the objective function of XGBoost is ...

15 30 50 per page