Questions tagged [tost]

TOST, an acronym for Two One-Sided Tests, is a straightforward way of constructing a test of the "negativist" null hypothesis that two population statistics differ by no more than a small researcher-selected equivalence threshold.

Filter by
Sorted by
Tagged with
1 vote
1 answer
34 views

Does TOST equivalence test handles subgroups within the group?

I just started on statistics so this is pretty hard for me. I have two identical experiments. Each experiment have gene expressions for 12 samples with different conditions: untreated. Dosage 50. 100. ...
user avatar
0 votes
1 answer
32 views

When are equivalent TOST test possible?

For my end-of-study work in architecture, i am comparing different reconstruction (~10) distances from reference 3D model. I'd like to test if reconstruction are different using statistical tests. On ...
user avatar
0 votes
0 answers
9 views

Equivalence testing for mixed measures (3x3; group X time) in R

Does anyone know how to calculate the statistical equivalence of a mixed measures study design in R? I know there was a thesis paper by Victoria Ng (see link below) that talks about different types of ...
user avatar
  • 1
0 votes
0 answers
24 views

Equivalence test for difference-in-differences regression

The results of my difference-in-differences estimator are insignificant and I was told than an equivalence test could help me to claim that the results are actually null. Even though I got the main ...
user avatar
1 vote
1 answer
47 views

Experimental Design for Equivalence Testing

I'm working on setting up a study that will test how quickly users click on various icons appearing on a computer screen using three different prototype mouse types. Subjects will visit on three ...
user avatar
  • 6,390
0 votes
1 answer
52 views

Simulate Equivalence Test

I am trying to simulate a paired t-test equivalence test. I generate x and y from the same Normal distribution thus I expect to ...
user avatar
  • 6,390
0 votes
1 answer
71 views

Equivalence test for two samples of categorical data

Let's say I have two packets of sweets, which can either be red or black. The packets look different, but I think they were produced at the same factory. I decide that if the distributions of the ...
user avatar
3 votes
1 answer
61 views

Analysing TOST test output

I am given the following R output for a TOST test and would like to confirm whether my understanding is correct: p1 and p[2] are both <0.05 and thus one can reject the null hypothesis that both ...
user avatar
1 vote
0 answers
42 views

Equivalence Testing for Absolute Mean Difference

I have a paired dataset: for each sample $x_i$ I have calculated $\theta^A_i, \theta^B_i$ using models A,B. Let $\xi_i=\theta^A_i - \theta^B_i$ and assuming equal-sized equivalence boundaries $\...
user avatar
  • 2,381
1 vote
1 answer
185 views

Equivalence test for non-normal distribution: how to determine equivalence bounds?

I am trying to conduct a Mann-Whitney equivalence test (as described in Wellek's book Testing Statistical Hypotheses of Equivalence and Noninferiority) with the following code in R: ...
user avatar
1 vote
0 answers
55 views

Sample size determination for TOST

I am currently working on analyzing the behavior of two algorithms on the same input data and am trying to establish whether they are reasonably equivalent to each other within specified bounds to ...
user avatar
0 votes
1 answer
37 views

Sample size for mean comparison

Suppose that I have a new machine so I want to compare it to the older one. I would like to conduct a mean comparison of a parameter, to verify if these 2 machines produce the same results or not. How ...
user avatar
4 votes
1 answer
87 views

TOST and its two null hypotheses

Background I have a device which is used to size potatoes. I want to use statistics to assess how accurate this device is. To that end, I've collected two data sets, $X$ and $Y$, where $X$ is the set ...
user avatar
1 vote
0 answers
59 views

Possible multiplicity issues in equivalence testing

I'm currently looking to compare 3 groups, trying to prove equivalence between them. For this, 5 specific parameters are measured for each group, and a pairwise comparison for each parameter among the ...
user avatar
  • 11
1 vote
1 answer
77 views

In the equivalence test (TOST procedure), why is the null hypothesis the presence of a real effect?

In the test for equivalence (or non-inferiority / non-superiority) we define a "minimal effect size" $d$, and test that the measured effect is not larger that $d$ $$X_1 \sim PDF1$$ $$X_2 \sim PDF2$$...
user avatar
  • 972
4 votes
0 answers
993 views

TOST equivalence test in excel

I had a prof once refer to doing science in excel as doing watch repair with oven mitts. Nevertheless, I'm trying... I'm trying to do a TOST test using excel. I'm basing the equivalence of variances ...
user avatar
  • 41
2 votes
0 answers
563 views

Understanding equivalence testing. Why there are two hypothesis?

I have to two groups and I would like to test that difference between means of these two groups is at least 0.02. I am using TOSTER R package. Here are details: ...
user avatar
6 votes
1 answer
1k views

Equivalence test for binominal data

I want to apply an equivalence test on my sample to infer whether they are equivalent or not. Since my data are bionominal [0,1] I don’t know whether the TOST procedure (tost() in R) can handle my ...
user avatar
3 votes
0 answers
603 views

Kolmogorov–Smirnov TOST based on confidence bands

I am trying to setup a two one-sided test (TOST) version of the Kolmogorov–Smirnov test (KS) based on confidence bands. I would like to know if there is anything wrong with my approach. Similar to ...
user avatar
0 votes
0 answers
425 views

Equivalence testing for repeated measures with two independent variables

I have a repeated measures experiment design with two independent variables ('condition' with 2 levels and 'repeat' with 10 levels) and one dependent variable ('performance'). I'd like to know whether ...
user avatar
  • 13
11 votes
2 answers
501 views

Can we accept the null in noninferiority tests?

In a usual t-test of means, using the usual hypothesis testing methods, we either reject the null or fail to reject the null but we never accept the null. One reason for this is that if we got more ...
user avatar
-2 votes
2 answers
1k views

R - what is magnitude of region of similarity (epsilon) when using tost() from equivalence package

I have two vectors: ...
user avatar
7 votes
1 answer
276 views

equivalence test - why isn't it more common?

Often in frequentist hypothesis testing, the null hypothesis is of the form: $H_0: \theta = 0$ I've seen many posts about how the p-value when doing tests against this null hypothesis is just a ...
user avatar
1 vote
2 answers
1k views

TOST for equivalence test

Let's say that we are measuring the tracking position error of two controllers and we want to know if both controllers are similar (we already perform a "differences" test but we are requested to ...
user avatar
2 votes
1 answer
1k views

Equivalence testing and difference-in-difference measures

I have some data from a recent experiment that requires slightly more sophisticated testing than I'm used to. Any advice would be most appreciated! The setup: There are control (C) a treatment (T) ...
user avatar
7 votes
3 answers
980 views

What is the best method of reporting multiple tests of equivalence?

I am doing a study which will involve multiple tests of equivalence. Is there a standard table for reporting such results? EDIT with more detail: It is a longitudinal study with 5 time points. Our ...
user avatar
2 votes
0 answers
417 views

Calculating epsilon for two one sided t-tests

I am using the equivalence::tost method in R. It takes a parameter epsilon, but I am unsure of how to calculate this when I require a test for non-zero Difference%. Currently, I do this by using the ...
user avatar
8 votes
1 answer
1k views

Can you use the Kolmogorov-Smirnov test to directly test for equivalence of two distributions?

There has been talk on other questions of how one might use the Two One-Sided Tests (TOST) approach for the Kolmogorov-Smirnov (KS) test, but I was wondering whether it was possible to directly use ...
user avatar
0 votes
3 answers
1k views

Paired two one-sided t-tests (TOST) with unequal sample sizes

I have data from two populations (let's call them "before" and "after"), collected in a paired fashion. That is, I take a measurement under one set of conditions before, and then I can take multiple ...
user avatar
  • 76
9 votes
2 answers
3k views

Equivalence testing - tost method - why CI of 90%?

In testing for equivalence via the two one-sided test approach with confidence intervals, a (1–2α) × 100% confidence interval is calculated to check for equivalence. I assume this is because you ...
user avatar
  • 1,212
5 votes
1 answer
203 views

Point hypothesis and equivalence hypothesis at once

Sometimes researchers (especially in collaborations) have two opposite but sound theories: There is a difference between two groups or there is only negligible difference. Now they ask their ...
user avatar
13 votes
2 answers
2k views

Is there a simple equivalence test version of the Kolmogorov–Smirnov test?

Has two one-sided tests for equivalence (TOST) been framed for the Kolmogorov–Smirnov test to test the negativist null hypothesis that two distributions differ by at least some researcher-specified ...
user avatar
  • 26.7k
2 votes
0 answers
164 views

What ANOVA non-superiority test corresponds to an omnibus set of TOST equivalence tests?

I am not sure if such a beast exists, but is there some non-superiority test for a oneway ANOVA of $k$ groups, probably based on a $\Delta^{2}$ equivalence threshold, for $m=\left[k(k-1)\right]/2$ ...
user avatar
  • 26.7k
10 votes
1 answer
2k views

Intuitive explanation of differences between TOST and UMP tests for equivalence

Hypothesis tests for equivalence differ from the more common hypothesis tests for difference. In tests for difference, the null hypothesis is some form of "separate quantities are the same", and ...
user avatar
  • 26.7k
56 votes
4 answers
17k views

Why do statisticians say a non-significant result means "you can't reject the null" as opposed to accepting the null hypothesis?

Traditional statistical tests, like the two sample t-test, focus on trying to eliminate the hypothesis that there is no difference between a function of two independent samples. Then, we choose a ...
user avatar
  • 2,290
6 votes
1 answer
1k views

Use of Wilcoxon test for non-normal data akin to Two One Sided T-test

I'm analysing paired data for equivalency and it's not normally distributed, i.e., the difference of the paired result is not normally distributed due to, amongst other things, outliers. If it were ...
user avatar
  • 119
12 votes
1 answer
576 views

Null hypothesis of equivalence

Suppose $X_1, X_2, \, ... \, , X_n$ are a simple random sample from a Normal$(\mu,\sigma^2)$ distribution. I'm interested in doing the following hypothesis test: $$ H_0: | \mu| \le c \\ H_1: |\mu| &...
user avatar
  • 121
9 votes
3 answers
5k views

Equivalence tests for non-normal data?

I have some data that I can't necessarily assume to be drawn from normal distributions, and I would like to conduct tests of equivalence between groups. For normal data, there are techniques like TOST ...
user avatar
3 votes
0 answers
657 views

How do I estimate sample size for a single-sample equivalence test?

From literature I have a theoretically proposed value for human performance in a particular task. I want to experimentally measure performance in this task across a sample of humans and test whether ...
user avatar
41 votes
8 answers
23k views

How to test hypothesis of no group differences?

Imagine you have a study with two groups (e.g., males and females) looking at a numeric dependent variable (e.g., intelligence test scores) and you have the hypothesis that there are no group ...
user avatar