Questions tagged [hypothesis-testing]

Hypothesis testing assesses whether data are inconsistent with a given hypothesis rather than being an effect of random fluctuations.

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

Minimum sample size for AB testing on a proportion derived from an extremely rare event

I am running an online experiment on a proportion that is the rate of an extremely rare event. 95.5% of the observations have 0 for this event. The majority of the rest have 1 for that event. Hence ...
user avatar
  • 76
0 votes
0 answers
13 views

Is a split-plot ANCOVA the right test?

I am writing my master's thesis and I just can't find no peace of mind.. I hope you can help me with understanding whether the chosen statistical test works or let me know if there's a better ...
user avatar
0 votes
0 answers
27 views

Are two likelihoods statistically different?

Here is an example that will help me ask my question. Let's say, I have the red and blue distributions as below, both of which are normal distributions (n = number of observations): Then I introduce ...
user avatar
  • 1
1 vote
2 answers
32 views

How is t-test on non-normal distribution justified?

I have heard that when the sample size n is large enough, we can apply the t-test to non-normal distribution due to the CLT. But as far as I can see, the CLT only justify the normality of the sample ...
user avatar
0 votes
0 answers
43 views

Which statistical Test should I use/ Comparing 2 groups

I am new to statistics, can someone guide me regarding the test I should use to compare the foot dimensions of 9 subjects to footwear dimensions (we have 2 footwear brands). So, to simplify, I have ...
user avatar
1 vote
1 answer
105 views

Can we apply hypothesis testing to not-actively sampled groups?

For argument's sake, in the below please assume that the hypothesis test we'd be considering would be a simple z-test to check whether an observed difference between two groups' means or proportions ...
user avatar
  • 11
1 vote
0 answers
15 views

How to account for overlap in individual studies in meta-analysis of meta-analyses (umbrella analysis)

I want to conduct a meta-analysis of meta-analyses (aka umbrella analysis). A potential issue is that within each individual meta-analysis I want to include there is some overlap between the studies. ...
user avatar
  • 51
1 vote
1 answer
26 views

Compare subgroups on before and after intervention

Assume the following research experience. A group of researchers went to a school. On the first day, they gave a questionnaire about a topic for the students to fill. The next day, the researchers ...
user avatar
2 votes
0 answers
8 views

How to perform significance test for a time dependent multiple linear regression equation?

Let me describe the problem: The general form of multi-variate regression model is given by $$Y = b_0 + b_1x_1 + b_2x_2 + b_3x_3 +....+ eta$$ And the statistic to test the significance of coefficient ...
user avatar
  • 21
1 vote
2 answers
37 views

Are T-tests good choices here?

I would like to test if two groups of participants (dark-eyed and light-eyed individuals) respond to a drug differently over time. The hypothesis is that the drug reaches its peak effects sooner but ...
user avatar
  • 11
2 votes
2 answers
105 views

Statistical Signifance Test for discrete data

I'm fairly new to statistics and want to perform a statistical analysis (calculation of p value) for data I collected, but I'm unsure if I'm doing it correctly and would like some feedback/help. I ...
user avatar
  • 23
1 vote
1 answer
48 views

What metric does the 95% confidence interval of a 2-sample t-test cover?

I'm trying to better understand what the 95% confidence interval is supposed to cover (in the context of a two-sample t-test). I had always been under the impression that the 95% confidence interval ...
user avatar
0 votes
0 answers
29 views

How to apply probability / bayes theory to classification issue?

I have a system of Codes which is updated every year, so some codes are deleted and some new codes are added. So here we have 4 versions of this system. Now, I received a list which contains some of ...
user avatar
0 votes
0 answers
14 views

How to apply probability / bayes theory? [duplicate]

I have a system of Codes which is updated every year, so some codes are deleted and some new codes are added. So here we have 4 versions of this system. Now, I received a list which contains some of ...
user avatar
0 votes
0 answers
26 views

What statistical test to choose weekday vs weekend occurrence

I have categorical data which shows the number of occurrences per day of the week, with 0 being Monday and 6 = Sunday ...
user avatar
0 votes
0 answers
21 views

How to compare two groups of discrete states?

The dataset includes 25 patients in one group (low intensity of a certain parameter) and 27 people in another group (high intensity of the same parameter). One or more teeth were treated for each ...
user avatar
0 votes
0 answers
32 views

Hypothesis testing with two means: How to do it properly?

I have a dataset which looks like the following: Value A Value B 1.2 100 1.3 200 1.4 300 1.1 433 1.3 320 1.2 210 1.5 108 I want to test the following hypothesis: *If I take an n-dimensional ...
user avatar
  • 103
0 votes
0 answers
48 views

How can I improve the results of such a binomial test? Was it a good choice for this problem?

I have a dataset that looks like this: initial final division fsa hrs_prev fsa/hrs_prev 2020-01 2020-06 A 0 168 0 2020-01 2020-06 B 14,29 177,45 2020-02 2020-07 A 9,52 177,45 0,054 and so on <...
user avatar
  • 13
0 votes
0 answers
9 views

If in the Fisher's exact test, one did not condition on the margin totals, how would the margin totals be factored in the calulation?

It states in the following post What does the assumption of the Fisher test that "The row and column totals should be fixed" mean? that: Fisher's exact test conditions on the margin totals, ...
user avatar
  • 2,673
1 vote
2 answers
32 views

Hypothesis testing: Calculate beta without PDF of H1

I've found pages that show how to mechanically calculate beta as 1 minus alpha and/or show beta in the context of a PDF for the alternative hypothesis (H1 or Ha). If you don't have a conjectured mean ...
user avatar
0 votes
0 answers
27 views

Help with interpreting a q-q plot [duplicate]

This is the q-q plot I got when testing residuals for Normality in a simple regression. Would you say that residuals are normally distributed or not? Should the data be transformed? I would say that ...
user avatar
  • 1
0 votes
0 answers
27 views

Best approximation for the size of a test

Let $X \sim \mathrm{Bernoulli}(\vartheta)$ for some unknown $\vartheta \in (0,1)$, and let $(X_1, …, X_n)$ be a moderately large IID sample for $X$. Let $\vartheta_0 \in (0,1)$. I want to test $H_0 \...
user avatar
  • 101
0 votes
0 answers
18 views

UMP Test and UMVUE when there are nuisance parameters

Consider $X_1,...,X_n \sim Weibull(\theta, c)$ where $c>0$ is unknown. Several textbook examples consider when $c$ is known, but here, we consider when $c$ is unknown. Suppose now we wanted to find ...
user avatar
  • 79
1 vote
1 answer
28 views

A/B experimental design with strata or blocks?

I have two approaches I wish to evaluate conversions (currently at ~2%). As in many situations, I cannot assume equal likelihood of conversions of instances which any number of individuals can be ...
user avatar
  • 4,693
1 vote
1 answer
36 views

Hypothesis testing: Use t-test when sample size is small or variance is unknown, but not both

The t-test is often used in hypothesis testing when the sample size is small (less than 30) because its parameterization by degrees of freedom allows the greater uncertainty to be accounted for. Many ...
user avatar
0 votes
0 answers
14 views

Scatter Plot of the Ranks of spearman vs Hoeffding [closed]

Could anyone tell me why the answer is AccountBal
user avatar
-1 votes
0 answers
20 views

Is there any definition of oversampling in regression? [closed]

Is there any definition of oversampling in regression? like the ratio : 90:10; 80:20; 70:30; 50:50
user avatar
1 vote
0 answers
11 views

Two sided binomial hypothesis test interpretation, what is the meaning of the two sided test?

I am on the Binomial Test entry in Wikipedia and in it, there is an example where a die is rolled 235 times, and 6 comes up 51 times. They claim there are two ways to construct a two-sided hypothesis ...
user avatar
  • 2,673
0 votes
0 answers
16 views

Nested factorial design for three factors [closed]

I want to design an experiment with three factors. Factor 1 shall have two levels (say, A and B), factor 2 has two levels (say, C and D) and factor 3 has two levels (say, E and F). By design, factor 2 ...
user avatar
0 votes
0 answers
17 views

What is the implication of conditioning on the margins in the Fisher's Exact Test? [duplicate]

In the following post: Chi-square test or Fisher's Exact test, it was mentioned by Glen_b that You don't have to have fixed margins to use the Fisher exact test, you only need to be willing to ...
user avatar
  • 2,673
0 votes
0 answers
17 views

Is the Karlin-Rubin theorem test the same as a one-sided monotone likelihood-ratio test?

Is the test described in the Karlin-Rubin theorem test the same as a one-sided monotone likelihood-ratio test?
user avatar
  • 503
1 vote
1 answer
18 views

Is it possible to use cross-validation to estimate the reliability of a specific predictor?

I have a big dataset with many predictors. I would like to know the quality of these predictors using cross-validation. However, what I am finding is more so methods that test the reliability of the ...
user avatar
  • 1,661
0 votes
0 answers
25 views

Which statistical test should I use to compare two models (multiple runs) on the same (big) dataset?

I want to compare the performance of two stocastic models on the same datasets (>10k samples). To this end, I run 5 runs for each model (different seed) and I can compute the mean and std for each ...
user avatar
  • 53
0 votes
0 answers
32 views

Do wald and score-tests work when we have nuisance parameters?

Do wald and score-tests work when we have nuisance parameters? In statistics, a nuisance parameter is any parameter which is unspecified ${ }^{[1]}$ but which must be accounted for in the hypothesis ...
user avatar
  • 503
1 vote
0 answers
10 views

Power calculation for observational study vs using propensity score matching estimating treatment effect

For case-control study study, one can calculate sample size to determine power of the study with respect to particular estimator of interest. Suppose I am interested in treatment effect in case ...
user avatar
  • 1,057
0 votes
1 answer
29 views

What to do when we have a p-value below significance level but we didn't reach statistical power at the reported effect size observed?

Suppose we have an AB test running for enough time to observe an effect size of at least 3% on certain variable X. When checking the results, we obtain that the p-value is below the significance level ...
user avatar
  • 21
0 votes
0 answers
9 views

Are there restrictions on the use of modified Thompson Tau?

I've been running an experiment in which I apply Modified Thompson-Tau to samples drawn from a standard normal distribution, the goal being to understand how $\alpha$ and the sample size [draw_size in ...
user avatar
-1 votes
0 answers
30 views

Neyman Pearson Lemma on Gamma distributions [closed]

There are two classes W1 and W2 and I have two different gamma distributions with known parameters: $p(x\mid w_1)=\frac{\alpha_1^{\beta_1}}{\Gamma(\alpha_1)}x^{\alpha_1-1}e^{-\beta_1x}$ $p(x\mid w_2)=\...
user avatar
  • 1
7 votes
1 answer
255 views

Hypothesis testing of two dependent samples when pair information is not given

For two samples equal sample size $(n\ =\ 100)$ that are randomly selected and dependent, only the sample means$(\overline x_1, \overline x_2)$ and sample standard deviations($ s_1,s_2 $) for both ...
user avatar
1 vote
1 answer
22 views

The concept of a specification test

There is a confusing facet of the concept of a specification test. According to many textbooks, a specification test is roughly a statistical test investigating whether assumptions in a statistical ...
user avatar
  • 619
1 vote
0 answers
41 views

Portmanteau statistic explanation

I am trying to test the autocorrelation of a VAR model using the Portmanteau statistic. I am using the R function serial.test(). I would like to fully understand ...
user avatar
0 votes
0 answers
25 views

Is log-rank parametric or non-parametric test, and why?

How is the log-rank test a "non-parametric test" according to wikipedia.org if one has to specify the parametric survival model for this test? We may run log-rank under the assumption of ...
user avatar
  • 503
1 vote
0 answers
16 views

On a survey, when checking for effect some answers have on other answers, do we always need to check for effect of random question sets?

Say someone runs a survey with, 100 binary question to which 10,000 randomly selected people responded. For 5 of those each questions (#20 to #24), answers looked like this (lets call this set of ...
user avatar
  • 291
0 votes
0 answers
35 views

Does Fisher's exact test give any answers about proportions?

I have a table that looks like this: initial final fsa_top hours_top fsa_bot hours_bot 2020-01 2020-06 1540.33 35222.21 984.5 28765.22 2020-02 2020-07 1765.43 36782.99 976.22 27666.07 and so on I ...
user avatar
  • 13
0 votes
0 answers
22 views

How should one re-formulate hypothesis after hypothesis testing or whether or not to discard data after significance testing or archive it?

@Nalzook summarized what he thinks Ronald Fisher did. Ask a question. Propose a null hypothesis based on the question. Do some experiments, and collect some data. Assuming the null is true, calculate ...
user avatar
  • 503
0 votes
0 answers
14 views

How to assess effect of a treatment on different groups, if groups have an effect on the measured variable and each group only receives one treatment?

Let's say I want to assess the effect of a treatment (A or B) on a continuous variable measured on subjects. The subjects I want to experiment on are organized into "groups". It has been ...
user avatar
0 votes
0 answers
19 views

What does Kolmogov-Smirnov tells us when the p value is high?

I have a dataset which seems to be uniform by eye-examination. I want to verify if this distribution is indeed uniform. I saw a couple of questions in here which suggested using a Kolmogorov-Smirnov ...
user avatar
0 votes
0 answers
17 views

Binomial test for absenteeism

I have a dataset that looks like this: Company hrs_prev fsa fsa/hrs_prev A 140 5 0,035 B 145 2 0,01379 C 140 60 0,4286 A 155 20 0,0129 A 180 25 0,1389 B 120 0 0 B 130 0 0 etc etc etc etc ...
user avatar
  • 13
1 vote
1 answer
40 views

Not sure on how to interpret the p-value for a permutation test

I was running a permutation test on my data. My goal was to test difference in means in two samples, by resampling one of them. I got results like these: And From my understanding, the p-value here ...
user avatar
  • 13
5 votes
2 answers
608 views

Chi squared test with reasonable sample size results in R warning

I am trying to identify whether a specific sample is likely coming from a certain data population using the chi squared test. I use R to do the calculation and my ...
user avatar
  • 165

1
2 3 4 5
193