Questions tagged [bootstrap]

The bootstrap is a resampling method to estimate the sampling distribution of a statistic.

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

“Recency-weighted” block bootstrap methods for time series sampling?

I have an "online learning" kind of application where I'm optimizing parameters for some objective which is calculated as an empirical risk over block-bootstrapped samples of a time series. ...
0
votes
0answers
17 views

Ensemble averaging of statistics [closed]

I want to calculate statistics for 50 different combinations of measurements. For example, I want to calculate the the mean, median, percentiles, standard deviations etc. for 20 different measurements ...
1
vote
1answer
20 views

After running a probit, how can I generate the margins for the whole distribution?

I'm using Stata. I ran a probit of the form $$ \text{outcome}_i = \beta \ f(\text{income}_i) + \gamma\text{ Controls}_i $$ Where $f(\text{income}_i)$ is a fractional polynomial. I'm interested on the ...
0
votes
0answers
16 views

Double bootstrap coverage failure?

I am working on a simulation to compare different bootstrap algorithms, like normal, percentile, BCa. I also include the double bootstrap or bootstrap-t, which requires a second round of bootstrapping ...
0
votes
0answers
10 views

Block Bootstrapping t-tests in R with the residuals from a regression

I'm trying to implement a function for a block bootstrap for the residuals of a regression to then compute new t-statistics. ...
0
votes
0answers
5 views

Bootstrap confidence interval for regression coefficients: Can they be calculated independently?

If y = a + bx the regression of interest and a and b are the parameters that you would like to estimate. From what I understand of bootstrap confidence intervals, the bootstrap is performed B times, ...
0
votes
0answers
17 views

What's the right way to do Bootstrapping Analysis on UserId Randomized A/A?

My motivation is to do A/A analysis using the "Bootstrap" method to calculate the confidence interval of the "sample mean" (of treatment and control) of all metrics. In my A/B ...
3
votes
1answer
144 views

Calculating a statistic via linear regression for a bootstrap procedure in R

I am interested in finding the interval estimate of the mean of my response variable when the predictor variable is equal to a certain value, that is $E[Y|X=x]$. The point estimate for this statistic ...
0
votes
0answers
12 views

How to calculate coverage probability when the true distribution is unknown

I am trying to calculate the coverage probability of my bootstrapping method to know whether the method that I have is valid. However, all that i have is the samples, without knowing the true ...
0
votes
0answers
178 views

Bootstrap confidence interval with mvrnorm - upper value equal to Inf

I am trying to predict a value and CI for two different treatments from a glmmTMB fitted model using posterior predictive simulations (mvrnorm function in the MASS package) as in the Salamander ...
0
votes
0answers
10 views

Random Forest Confidence Interval via Bootstrapping

Background Suppose I have a trained random forest with $N$ decision trees. Given an input vectors $\vec{x}$, the prediction made by the $i$-th decision tree is denoted as $t_{i}(\vec{x})$. The ...
0
votes
1answer
24 views

Boostrap estimator: sample or population?

As stated here: Do we use bootstrapping with population data? "The general idea of bootstrap is that by sampling from your data you re-create the sampling process that happened when sampling your ...
0
votes
0answers
23 views

MonteCarlo function to Simulate and Analyse ARIMA Several Times

Here is the algorithm of what I want to do with R: Simulate 10 time series data set from ARIMA model through ...
0
votes
0answers
30 views

A (new?) bootstrap-based technique to check if a model performs worse on “subpopulation”

This is sort of an ad hoc statistical test I've devised to assess the performance of a prediction model on different subpopulations I have a large sample A with a Subgroup R. I would like to tell if ...
0
votes
0answers
18 views

What is the rational behind bootstrapping a model?

At this point, I understand what bootstrapping is and how it works. What I would like to understand better is the exact properties of the method regarding its test error and, as a related question, ...
1
vote
0answers
47 views

Distribution of bootstrap and central limit theorem

Let's take a simple example: we have 100000 observations, and we want to estimate the mean. In theory, the distribution of the estimator is a normal distribution according to the Central limit theorem....
1
vote
0answers
13 views

test the internal validity of this model / score by Resampling by Bootstraping

I am working on a predictive model of a diagnosis via a logistic regression "glm" Let me clarify right away, I am a medical doctor and researcher, not a mathematician, so sorry if I use ...
0
votes
0answers
10 views

How to Use Parametric Bootstrap to Calculate Covariance Matrix? [migrated]

Using the following dataset "data": load(url("https://www.math.ntnu.no/emner/TMA4315/2020h/hoge-veluwe.Rdata")) I have fit a poisson GLM ...
0
votes
1answer
19 views

Empirical distribution in bootstrap method

Fushiki (2005) states that [...] a nonparametric bootstrap sample $x^{* N}=\left\{x_{1}^{*}, \ldots, x_{N}^{*}\right\}$ [is] independently obtained from the empirical distribution \begin{equation} \...
1
vote
0answers
15 views

Estimating distribution of tied ranks for tie correction to Wilcoxon-Mann-Whitney U test

Tests based on ranking elements, such as Mann, H. B.; Whitney, D. R. On a Test of Whether one of Two Random Variables is Stochastically Larger than the Other. Ann. Math. Statist. 18(1):50-60, 1947, ...
1
vote
0answers
13 views

bootstrap gives conflicting results when simulate is used (LMER)

I perform a parametric bootstrap in 2 ways. first method: fit dataset in a H1 and H0 model(H1 contains all effects and HO has a certain effect omitted). retrieve the log likelihood ratio (call it here ...
0
votes
0answers
16 views

Mann whitney and boostrap confidence intervals provide contradictory results

We are doing some a/b testing and have non-normal metrics so our typical t-test aren't appropriate. I typically use bootstrap CI and/or Mann whitney tests to determine the true effect. In this case ...
2
votes
1answer
106 views

Can I replace mean with median if using the Central Limit Theorem and calculating p-value

I was reading this article ,article link here, about the Central Limit Theorem, CLT, and how it can be used to determine if a cohort of interest is significantly different than the population (I might ...
7
votes
2answers
492 views

Why Bootstrapping standard errors and 95% confidence intervals change each time I re-conducted the analysis [duplicate]

I was using respondent-driven sampling analysis tool (RDSAT) to get bootstrapping confidence intervals. But each time I re-did the analysis, I noticed the bootstrapping standard errors and confidence ...
21
votes
1answer
2k views

After bootstrapping regression analysis, all p-values are multiple of 0.001996

I'm running various multiple regression analyses in SPSS 27, and with those that are not bootstrapped, the p-values vary such that I do not find the same p-value twice within a regression (e.g., the p-...
2
votes
1answer
28 views

Bootstraping with R, how to find possible bootstrap samples for a given vector

Consider the vector our_names <- c("John","Ciprian","Brian") a. List all possible bootstrap samples of our_names. b. How many ...
1
vote
1answer
24 views

Use bootstrap mean to remove bias from the statistic?

I have a data sample on which I apply a statistic called "$\alpha$". I then use a standard bootstrap analysis on the data which results in something like this: As can be seen, the bootstrap ...
0
votes
0answers
12 views

What is the distribution of the actual parameter given an estimate with credible interval or confidence interval?

Let's assume we have a variable $X$. Some authors said that X is distributed normally with mean $X_m$ with credible interval $(X_{m1},X_{m2})$ and SD $X_s$ with credible interval $(X_{s1},X_{s2})$. We ...
1
vote
2answers
40 views

Estimating error when bootstrapping results are skewed

I'm trying to figure out the most robust way to estimate the error on the best-fit parameters of an exponential model ($y = x^a$) for some data. I have heard that bootstrapping is a solid way to ...
0
votes
0answers
8 views

Bootstrap test stat for a vector of coefficients from several models

I have two non-nested multiple regression models say $A$ and $B$, and 10 different outcome variables on the same treatment units: $y_1,...,y_{10}$ and want to test whether the vector of 10 estimated ...
0
votes
0answers
23 views

Do you have to set.seed when splitting data?

More specifically, in cases of bootstrap and cross-validation, we often tend to put a set.seed() randomly, either a number people like or more often 12 or 123. This ...
0
votes
0answers
18 views

boundary (singular) fit: see ?isSingular during some iterations of bootstrap

I am performing a parametric bootstrap following this paper(section 4.5 step 4b): https://onlinelibrary-wiley-com.vu-nl.idm.oclc.org/doi/full/10.1002/cem.3232 when I iterate in my bootstrap, I ...
2
votes
1answer
36 views

Permutation Hypothesis Testing procedure

I'm not strong in statistics and I'm looking for a help. I work with real estate data and I want to compare apartment prices in 2 districts: district "A" and district "B". Data ...
2
votes
1answer
28 views

confidence intervals for fixed effects with reML

I am trying to asses wheter certain effects are significant in my mixed model. First I tried the confint function with the profile method and the Wald method. Both are somewhat similaire, now I want ...
0
votes
0answers
37 views

Approximating Bayesian Posterior with Weighted Likelihood Bootstrap (WLB)

$\DeclareMathOperator*{\argmax}{arg\,max}$Given a set of $N$ i.i.d. observations $X=\left\{x_1, \ldots, x_N\right\}$, we train a model $p(x|\boldsymbol{\theta})$ by maximizing marginal log-likelihood $...
1
vote
1answer
22 views

Small paired samples comparison: which approach should I prefer?

I have the following small dataset, that consists of scores before and after a certain treatment for 15 individuals: ...
0
votes
0answers
14 views

Subsampling for odds ratio estimation?

I want to know how valid is to use a subsampling bootstrap for estimating the odds ratio. Here are the details: I have a large sample ($N \approx 7\times10^6$ ) with cases and controls ($cases/...
1
vote
1answer
24 views

Why residual bootstrap does not work for GLM?

My lecture note says Since we add residuals to the fitted model, this residual bootstrap only works for a homoscedastic regression model, where the error distribution does not depend on the ...
2
votes
1answer
57 views

When and why should we bootstrap the standard error in regression?

I have a linear regression model: $$Y_i = \alpha + \beta_0T_i D_i + \beta_1D_i + \beta_2T_i + \delta x_i + \epsilon_i$$ where $Y$ is a continuous outcome variable, $D$ is the binary treatment variable ...
0
votes
1answer
24 views

Creating a biased sample with two variables matching distributions from another dataset

I have a biased sample from a user activity dataset with known distributions of two variables, the amount of times a user logged in during last week (poisson distribution) and user's weekly revenue (...
1
vote
1answer
33 views

What is the purpose of using duplicated data in resampling techniques (e.g., bagging/bootstrapping)?

With bootstrapping and bagging, we resample from the dataset and end up building a model or estimating some sample statistic using the sampled data, which typically consists of at least $33\%$ ...
1
vote
0answers
23 views

How are bootstrap predictions properly reported?

I'm presently working on a paper in which bootstrapping is to be used. We plan to bootstrap our model's predictions and present these, as well as confidence intervals for the model predictions. When I ...
0
votes
1answer
22 views

Correlated data series with single repeated value with a few outliers

I'm dealing with about 4,000 stationary time series, most of which I was able to reasonably fit to a distribution based on the KS test. About 200 of the time series, however, were not so well-behaved ...
1
vote
0answers
15 views

Bootstrap for nonlinear regression and ranked explanatory variable

I've been wondering how the bootstrap method works in the case of nonlinear regression models where the order of the x-axis (suppose just 1 explanatory variable) matters. In the case of univariate ...
2
votes
0answers
25 views

On Nonparametric bootstrap predictive distributions

Consider a model $p(x|\boldsymbol{\theta})$ which is trained using $N$ i.i.d. observations $X=\left\{x_1, \ldots, x_N\right\}$. Bayesian predictive distribution is defined as \begin{equation} p(\bar{x}...
1
vote
1answer
39 views

Variance and CI for the difference in medians

One way to obtain a (1-alpha)% confidence interval for the difference in medians for two samples is to use bootstrapping. Generate 10,000 bootstrap samples of both group's samples and find the ...
1
vote
0answers
52 views

An out of bag testing procedure I developed. Is it biased?

Trying to estimate the error of a prediction model trained on a combined group vs a subset of interest within that group (for example, Men) My procedure is First simulate a random subset like the ...
1
vote
0answers
41 views

Obtaining p-value from bootstrapped Pearson's correlation using R

I am trying to carry out a bootstrapped Pearson's correlation using R software. I have 13 observations and originally I obtained: ...
0
votes
0answers
35 views

Convergence of bootstrap standard error estimate (one of the problems from Efron's book)

I am trying to solve problem 2.5 from the Efron/Tibshirani book, An Introduction to the Bootstrap (page 16). The problem asks to show that by applying the weak law of large numbers, the bootstrap ...
0
votes
0answers
25 views

bootstrap rows of a regression data frame even though the predictors are not random variables?

I got some inspiration from a question that was posted this morning. Let's design an experiment where we have three factors, each with two levels (e.g. male/female). This gives a total of eight groups,...

1
2 3 4 5
31