Questions tagged [method-comparison]

Questions about comparisons of different statistical methods

Filter by
Sorted by
Tagged with
1
vote
0answers
10 views

GLM Model comparison and selection with different response distribution

I am proposing for my thesis... Pls help. I have Y=weight of Baby, X1=Age of Mother X2=Age of Baby and X3=Sex of baby. I assume Y~Normal with Identity link. Also I assume Y~Binomial with logit link ...
2
votes
1answer
88 views

The reason (and intuition) behind why stochastic gradient descent can get stuck on a local minimum

Suppose you want to find $k$ that minimises your cost function $J(k)$. We may want to apply batch gradient descent or stochastic gradient descent. Let's deliberately initialise $k$ with the same ...
0
votes
0answers
40 views

How to compare 2 p-values?

I have 2 continuous outcome (independent) variables, A and B, and 1 dependent variable (biomarker) that are all very correlated (i.e., p_A = 0.01, p_B= 0.000001). I would like compare the outcome ...
0
votes
0answers
8 views

Compare two correlation coefficients - or do I want moderation? Or something else entirely?

I'm trying to assess the impact of the UK government's differing approach to managing COVID-19 on healthcare outcomes. For example, I can consider weekly patients presenting with COVID-19, and weekly ...
0
votes
1answer
30 views

How to compare two texts with different order of words?

I have two texts, one ground truth and one OCR result, and I want to measure to what accuracy the result matches the ground truth. But since the text source is non-linear, both texts have a different ...
5
votes
0answers
42 views

Is it wrong to compare multiple models on the same test set and choose the best model?

Suppose we split a dataset into 3 parts (train, validation, and test). I know that it's important to make sure the test set doesn't influence our decisions during model selection or hyperparameter ...
0
votes
0answers
33 views

request reference on the superiority of Gaussian processes in small-data regime

It seems to be widely accepted that Gaussian processes are superior to neural networks in the small data regime. Are there any references (whether books or papers) that make such claims and justify ...
0
votes
0answers
17 views

How and what to test: symptom limited test without symptoms?

I'll try to explain the question as easy as possible with two example patients of my $\approx 100$ patient groups. All patients had a specific operation, prior and a year after operation they ...
2
votes
1answer
53 views

Contour plot comparison [closed]

What are the ways to compare two different maps? I was thinking of taking the matrices of each map and then quantify their spatial differences by plotting the map of the differences of the two ...
2
votes
2answers
154 views

Fair comparison of machine learning methods with different parameterization

Let us assume the following scenario: The goal is to forecast the additional number of customers of a set of companies. To do this, you use a basic set of characteristics (e.g., company-specific ...
1
vote
2answers
245 views

McNemar-Bowker exact test in R: difficulty interpreting the results

I am trying to use the McNemar-Bowker test to test the difference in performance for 2 classifiers. Since my input matrix is sparse and the sum of some of the symmetric cells is less than 10, I am ...
3
votes
1answer
40 views

Comparing the accuracy of binary classifiers using iterated cross-validation

Let's say that you want to compare two binary classifiers (e.g., LDA and linear SVM) for a given research question, the question being "which one will probably perform best for the problem at ...
1
vote
1answer
32 views

Overlapping quinquennial data - How to compare?

I actually do not know if this is the right place to ask, but I hope someone can help me. I have a dataset that provides the number of newborns in quinquennial periods. For instance, I have the number ...
0
votes
0answers
17 views

covariance estimation method comparison

There seem to be a bunch of ways to estimate the covariance and precision matrices (in sklearn there are several, including MinCovDet and graphical lasso, but also including primitive (which does not ...
0
votes
0answers
6 views

Comparing differences between three or more unpaired groups (DV categorical and non-normal continuous) and describing used tests

I have a made-up table as follows, including a footnote describing given p-values. P-value shows the differences between all subgroups, and it was derived from the Kruskal-Wallis test for continuous ...
1
vote
1answer
89 views

Do XBGoost and LightGBM only use trees as base learners?

From my understanding of GBM is that it can take not only decision trees as base learners, but different weak learners as well (e.g., linear models), since it relies on sequential gradient descent. ...
1
vote
2answers
135 views

Comparison of Bayesian and Classical estimates

Is it correct to compare Bayesian and Classical estimates using Mean Squared Error (MSE)? MSE is a criterion that is used in the classical paradigm. For example: I am comparing the performance of ...
1
vote
0answers
48 views

Which regression analysis to use?

I have percentage change data compared to a baseline of public and private transport activity over 1 year. With the help of one or two independent variables I want to analyze if there is a switch ...
0
votes
0answers
24 views

Need to test heteroscedasticity before using the Kruskal-Wallis test

My question is whether or not I have to test heterodasticity before using the Kruskal-Wallis test. What I understand is that if I want to compare medians, then I have to check for heteroscedasticity, ...
0
votes
0answers
12 views

Compare the means of dependent samples that are not paired? Group size of dolphins sighted?

I'm looking for a statistic way to compare the means of dependent samples which are not paired. Context: I study a dolphin population in which individuals are clearly identified. My data consists in ...
2
votes
5answers
203 views

Interval Estimation for a Change in a Binomial Proportion

I'm not sure how to estimate the confidence interval (CI) for a change in a small sample size binomial proportion using the same sample set both times. I have two methods that I would like to compare (...
0
votes
1answer
30 views

Statistical Significance on shops performances with a marketing promotion

I have data regarding the performances of shops on a certain time period: in this data some shops had an active marketing promotion, and some didn't. I would like to understand whether the shops with ...
0
votes
0answers
189 views

Comparing two clustering methods with adjusted Rand index - How to make labels match

I have a set of data (countries), and I use a clustering method (Kmeans) to create two partitions on them based on different data (diet and covid stats). So I get two groups of partitions, and I want ...
9
votes
2answers
237 views

Propensity score matching vs non-parametric regression

I am trying to understand the benefit of propensity matching over non-parametric regression for causal inference from non-experimental data. As background: the way I understand it, parametric ...
1
vote
0answers
35 views

Efficient way to compare algorithms performance with missing samples

I'm currently doing some experiments to compare more than 70 different configurations (different parameters of an evolutionary algorithms) that have 30 runs each (repeated due to stochastic results). ...
2
votes
1answer
261 views

What is the difference between simulated annealing and deterministic annealing?

Not sure if this is the right place, but I was wondering if someone could briefly explain to me the differences & similarities between simulated annealing and deterministic annealing? I know that ...
1
vote
2answers
507 views

How can I tell if images are from the same distribution?

What are some tests I could run on two groups of imagery to see if they're from the same distribution? Imagine, for example, that you want to augment a dataset with another, and you want to make sure ...
1
vote
0answers
1k views

R: Caret package: AUC ("ROC") standard error from cross validation

This seems like a basic questions, so I'm likely missing the big picture here... I would like to know the AUC of each fold of a cross-validation performed in Caret's train function, in order to ...
0
votes
1answer
52 views

Statistical tests for comparing (black box) model performance on two datasets

Introduction I have two datasets, dataA (real images) and dataB (generated images). I also have a model that has been trained on dataC. dataC might have some overlap with dataA but for certain does ...
2
votes
1answer
291 views

Comparing different model with the same output

I work on developing 3 different models for predicting land surface temperatures in an area (validation is done with images taken by a thermal drone). The models are: A thermodynamic mechanistic ...
0
votes
1answer
208 views

compare correlation between two matrices

We have two algorithms that assign a score to the foreground of how well it fits the background. And we want to know which algorithm is closer to human perception. Then we collect an evaluation set ...
7
votes
2answers
121 views

What is better in Monte Carlo integration: product of means or mean of products?

Let $X$ and $Y$ be two independent continuous random variables with pdfs $f_X$ and $f_Y$, respectively. Let $\varphi_1$ and $\varphi_2$ be two continuous functions from ${\mathbb R}$ to ${\mathbb R}$. ...
0
votes
0answers
52 views

why the result of primal sim is not the same as linear kernel?

I have a data set with 36000 rows and 9 columns. so n<< m. this is multi classification SVM. I solved this by primal model in OSQP. then I used R package e710 and svm with linear kernel. the ...
2
votes
1answer
91 views

When to use the full and the conditional likelihood

In the context of estimating parameters of a time series model, we may consider either the full likelihood or the conditional likelihood. I was wondering in what situations the full ...
0
votes
2answers
41 views

Evaluate methods across datasets based on distance metrics

I want to evaluate $n$ methods, says $M_1,\cdots,M_n$ on $m$ datasets $D_1, \ldots, D_m$. For each method $M$, I have a score function $f(M,D) \in [0, \infty)$ for dataset $D$. A perfect method will ...
1
vote
1answer
18 views

if different methods have difference 0.5 in third decimal place while finding accuracy then what to conclude?

For the comparison of different feature selection methods and evaluating performance metrics. After evaluation when their is only 0.5 difference in third decimal place. Is this difference is ...
2
votes
1answer
985 views

Which method is correct for calculating total deviance explained for boosted regression trees?

I have the following output from a boosted regression trees model and I would like to calculate the total deviance explained. ...
1
vote
1answer
1k views

Can you compare the mean of one data set with the median of another?

I’m having an argument with another numerically literate person. We both saw a news site state that under no circumstances should you compare the median of one set with the mean of another. It’s ...
2
votes
0answers
65 views

comparison of machine learning models

I’m struggling with a statistical problem in machine learning: I’m using event-related fMRI responses (voxels) evoked by graded painful stimulations as feature. The targets are the scores (labels) of ...
3
votes
2answers
622 views

Reasons for different parameters via MoM and MLE

I got a study of 210 samples and I tried fitting gamma distribution to them. I used method of moments and maximum likelihood estimation to calculate the parameters, but parameters came out quite ...
1
vote
0answers
7 views

Evaluating a set of algorithms based on daily performance

I work in a production system which can use three competing algorithms, say $A_1,A_2,A_3$ for a customer on a daily basis. On each day, for a given customer, the production system looks at how much ...
2
votes
1answer
49 views

Multiple classifier comparison with Bayesian statistics

I've been recently working on some classifier comparisons. I've come to realize, the critical distance diagrams introduced $\approx$ 10 years ago might not be the most relevant solution for this ...
3
votes
2answers
744 views

Compare clustering results with different attributes and number of clusters

I used K-means to cluster a large data set that has millions of samples. I tried to create the clusters with different sets of attributes, which, as a result, generated different optimal number of ...
1
vote
0answers
57 views

Statistical difference of machine learning predictions

I am applying a machine learning classification method to two difference scenarios for my boss (in this context, I am using a random forest). Due to the nature of the problem, there is high class ...
2
votes
0answers
83 views

Analysis of Pre-post Likert-type scales: Intervention vs. Control group

I gathered the following data: Intervention group (n= 24, received treatment): pre- and post- scores of different psychometric questionnaires Control group (n=23, inactive): same questionnaires, same ...
5
votes
1answer
42 views

Bayesian and frequency tail estimation

The tail probability can be estimated by two methods: In Bayesian method: $$P_B(X>a)=\int^{\infty}_{-\infty}\pi(\theta|x)[1-F(a|\theta)]d\theta$$ In Plug-in frequency method: $$P_F(X>a)=1-F(a|\...
1
vote
0answers
38 views

How to compare my model's performance with that of others?

I'm building an audio classifier and would like to compare my model's performance with that of others. I use the Urban Sound Dataset. I searched for already existing results on this dataset but couldn'...
1
vote
0answers
139 views

comparison of two estimators

Assume we have a data set $\mathbf{x}_{n} = (x_{1}, \dots, x_{n})$. Let $\delta_{1}(\mathbf{x}_{n})$ and $\delta_{2}(\mathbf{x}_{n})$ be two consistent estimators of some parameter $\theta \in R^{k}$. ...
2
votes
2answers
1k views

How to compare two levels of one factor

I´ve run a GLMM model with the following variables: Response variable: continuous (with positive, negative and zero values; Explanatory variable: 1 factor with 6 levels (DB, DF, NDB, NDF, BB, BF); ...
8
votes
3answers
1k views

Clarification on how to perform nested cross-validation

I'm currently trying to get lifetables for our population based on death and population counts. My first idea was to follow this paper methodology but after some discussions we are planning to use ...