Hypothesis testing assesses whether data support a given hypothesis rather than being an effect of random fluctuations or some other process described by an alternative hypothesis.

learn more… | top users | synonyms (4)

0
votes
1answer
28 views

Anderson-Darling test for normality with estimated parameters

I have a set of measurements coming from a manufacturing processes. I want to test if the measurements come from a normal distribution. If I understadn correctly, it's wrong to use K-S test or A-D ...
0
votes
0answers
8 views

Best-fit values for multiple data sets with single model

This is probably so simple the answer should be obvious, but I thought it best to check with better informed people than myself; I have a simple physics model that fits to some four data sets. From ...
1
vote
0answers
19 views

Distinguishing two Bernoulli random sources

I have a source of independent Bernoulli random variables, which is either $(X_i)$ or $(Y_i)$ where $\Pr[X_i=1]=p$ and $\Pr[Y_i=1]=q$. I can sample as many values as I'd like, and would like to figure ...
1
vote
0answers
11 views

How to model a scale and its component subscales

I am investigating the use of psychological strategies (PS) and athlete engagement (AE) in soccer players and what to predict if global / whole PS predicts AE as a whole using SPSS. I also want to ...
2
votes
1answer
36 views

Which one is the correct formula of confidence interval of variance?

I got the following formula of confidence interval of variance in this site $$\frac{(n-1)s^2}{\chi^2_{1-(\alpha/2),n-1}}<\sigma^2<\frac{(n-1)s^2}{\chi^2_{(\alpha/2),n-1}}$$ And this following ...
1
vote
2answers
28 views

What are the assumptions to test on unseen data to use a predictive model?

I am trying to understand what are the assumptions I have to test, to use a predictive model on unseen data. After the validation phase of my predictive model and the estimation of its accuracy on a ...
1
vote
1answer
28 views

What happens when there's a one-tailed hypothesis test and the results are in the other tail?

For example, let's say I'm using a one-tailed t-test to see if a box of Lucky Charms cereal has more than 100 marshmallows. I know the consequences of using a one-tailed t-test and how it wouldn't be ...
0
votes
1answer
21 views

Permutation test for F statistics in the OLS setting

Can anyone explain to me that what is the point of performing a permutation test? For example, in the OLS analysis, we fit $X\beta$ to $Y_i$,for the permutation test, we let $\tau$ be a permutation ...
0
votes
0answers
16 views

How is the confidence interval of variance component calculated?

How is the confidence interval of variance component calculated ? As far I know , confidence interval of variance is calculated as : ...
1
vote
0answers
11 views

How should I test for multivariate GARCH effects for residuals of a model?

I would like to test the multivariate GARCH effect of a multivariate time series. The multivariate Ljung-Box test can do this. However I am also looking for a test to show that a DCC or CCC model can ...
0
votes
1answer
36 views

Quick reality check: using correlation and Chi-square for hypotheses testing

I have two ordinal values on a 5 point Likert scale, let's say "Would you like flowers?" and "Would you like to go out to dinner with me?". My hypotheses is that there is a relationship between the ...
2
votes
0answers
35 views

What is a test that I can use to determine if a time series is first-order stationary?

I need to test that one of the time series in my analysis has a constant mean over time. Is there a standard test I can use to help me determine this? I know that I can use a nonparametric procedure ...
0
votes
0answers
49 views

Conditions to be in a class of Poisson distribution

Ambulance cars are arriving at a traffic signal in accordance to a Poisson process. The arrival rate of ambulance cars is measured at every 1 hour. $\lambda_k$ is defined as $k_{th}$ hour arrival ...
4
votes
1answer
35 views

Family-wise error boundary: Does re-using data sets on different studies of independent questions lead to multiple testing problems?

If a team of researchers perform multiple (hypothesis) tests on a given data set, there is a volume of literature asserting that they should use some form of correction for multiple testing ...
0
votes
1answer
19 views

Ordinal Dependent Variable and Ordinal Independent Variable. Which test to perform analysis with?

I have a question regarding Ordinal data. I have measured 'Attitude towards a product' using Likert scale and I have measured 'Purchase Intentions to buy the product' also using Likert scale. Now I ...
0
votes
0answers
17 views

How do I perform a Kolmogorov test for the beta distribution, in Stata? [on hold]

I'm trying to perform the Kolmogorov test for a beta model in Stata, however as far as I can find so far, in Stata I can only do this test for a normal distribution. So, does anyone know if the ...
0
votes
0answers
9 views

How can you make the Kolmogorov-Smirnov test on stata for a beta model? [on hold]

I need to make the Kolmogorov-Smirnov test in stata for a beta model, and i don´t know what is the command for this model. Thanks
1
vote
0answers
8 views

Statistically verifying distribution of users within an A/B Test

Hoping you can help me determine the best way to statistically verify that an A/B test was set up in an unbiased way. The A/B test was set up to split users on my website 50/50 into a test/control ...
1
vote
3answers
79 views

What follows if we fail to reject the null hypthesis?

What conclusions can we draw if p>alpha? Does not rejecting the H0 mean anything?
0
votes
1answer
26 views

Why are the Wald standard errors often very poor estimates of the uncertainty of variances?

As from this post as @Ben Bolker pointed out that : .. note that these (as often pointed out by Doug Bates) the Wald standard errors are often very poor estimates of the uncertainty of variances, ...
0
votes
0answers
15 views

Wald confidence interval

Are Wald Type confidence interval and confidence interval based on asymptotic standard normal distribution synonymous ? Can you please give me some reference ?
39
votes
14answers
2k views

Why would parametric statistics ever be preferred over nonparametric?

This may be a stupid question but it's been bugging me for years. Can someone explain to me why would anyone choose a parametric over a nonparametric statistical method for hypothesis testing or ...
0
votes
0answers
15 views

Statistical significance of the Lorenz curve (Gini index)

What would be the best way to statistically compare results from the Lorenz curves (a number of curves plotted on the same graph)? I know that these curves can be expressed in terms of Gini indices, ...
1
vote
3answers
70 views

How to test $ H_0: \mu=0 \quad \text{vs.} \quad H_a: \mu=1$?

The Statement of the Problem: Let $X_1,..., X_n$ be a random sample from $N(\mu, 1)$. Consider testing $$ H_0: \mu=0 \quad \text{vs.} \quad H_a: \mu=1. $$ Let the rejection region be $C = ...
0
votes
1answer
18 views

Statistic test for comparing two methods? [closed]

I don't have very good knowledge about statistical testing. Accept my apology if my question sounds stupid. I have developed two methods for competing discomfort level of communities. one is static ...
1
vote
0answers
8 views

What is the purpose of specifying a “control” in an A/B/N split test?

I define control as the currently accepted, best known variation. The test to be performed would introduce n new variations. Each variation will be served randomly for the duration of the test. I am ...
0
votes
0answers
14 views

Aggregate Pseudo-Paired T-Tests

I would like to determine whether there is a significant difference between two different servers with regard to run-time. My data is split into subgroups each of which is a different Page. The same ...
0
votes
0answers
22 views

Statistical test with unequal sample sizes

If I have two samples with vastly different sample sizes (say n1 = 800 and n2 = 21,000) what statistical test would give me the most reliable results? I've been using the Mann Witney U test. Is the ...
0
votes
0answers
23 views

Accepting or rejecting hypothesis in two tail test

I have calculated the $t$ value and $p$ value which is 2.08 and 0.045 on the basis of two different samples having different number of observations, mean, and variance. Can I conclude that the ...
0
votes
1answer
22 views

compare multiple algorithms in the same dataset

I want to do a comparison between multiple algorithms when they applied to the same dataset. For example, I have a set of texts in Arabic and another version translated to English. I did a sentiment ...
0
votes
0answers
21 views

Custom Tables: How does SPSS treat multi response sets differently from categorical vars? [on hold]

I have come across an SPSS-specific scenario where I cannot understand how SPSS is calculating its proportions test results. The scenario only takes place when applying t-tests and z-tests on "SPSS ...
2
votes
1answer
24 views

Can I use a Bayes factor to compare cells in a contingency table?

I'm trying to compare which features of a website more active and less active users make use of. I've divided up the users into "active" and "inactive" and there are several page types they can visit. ...
0
votes
0answers
31 views

How to analyze survey data, interval or ordinal, and how to account for nonresponse bias?

I have a question regarding a survey. I gave a test to people and they were asked to rate the tester on a scale of 1 to 5, 5 being they liked it and gave it the highest rating, with 1 being the ...
1
vote
1answer
20 views

hypothesis test one-sample vs two-sample

An industrial process is in place that increases the strength of a metal component. We are tuning a couple of settings on the system to optimize the strength. There are already some settings in place, ...
1
vote
1answer
35 views

t-test in large, unequal sample size + additional info such as effect size

I have 2 samples, named "1" and "3": (1) n = 1282, mean = 14.77, sd = 8.27 (3) n = 5360, mean = 15.88, sd = 8.55 Their distribution look: ...
0
votes
2answers
87 views

What is a statistical book that focus on showing that statistical test work?

What is a book that tells how can we evaluate how well hypothesis tests work, and and compare them? For example: 1)To investigate the significance of the difference between a frequency distribution ...
1
vote
0answers
20 views

Is it possible to use spatial autocorrelation test to determine the tuning parameter in the thin plate spline smoother?

I am currently working with some insurance data and try to estimate spatial structure of claims frequencies. The common approach is to perform some kind of regression on the non-spatial data then ...
0
votes
0answers
7 views

Statistical significance of difference between samples given total success rate when test was applied by group

I am comparing treatments that select members to receive some email, and we are measuring the response to that email. The emails are similar, but are sent to a different group of members and a ...
0
votes
1answer
63 views

Multiple regresssion K-S test in R

As suggested, this question first appeared on SO but was now merged across to CV So we can run a K-S test to assess if we have a difference in the distribution of two datasets, as outlined here. So ...
0
votes
1answer
33 views

Difference between multi-factor ANOVA and Cox proportional hazard model?

I am wondering what is the difference between multi-factor ANOVA and Cox proportional hazard model? As I understood both of them test the significance of some independent factors on a dependent ...
1
vote
0answers
22 views

A/B Testing (Pearson Ch-Square Test) with Unequal Sample Sizes

We have run A/B tests in the past using a 50/50 split, and have used the power prop function for calculating the sample size using the power.prop.test in R. My question is how do I calculate what my ...
3
votes
1answer
87 views

How to determine the strongest player in a team game

I have an idea for a "King of the Hill" contest in the Programming Puzzles and Code Golf Stack Exchange (http://codegolf.stackexchange.com/). The game I have in mind has four players divided into two ...
2
votes
1answer
16 views

Comparing performance of a single classifier on two datasets

I'm using a single classifier on two different datasets, consisting of non-overlapping set of observations. The performance on one dataset is higher than the other, and I want to show that the ...
1
vote
2answers
16 views

Hypothesis test for mutually exclusive samples from a single population?

Let's say I gave 100,000 people a survey on their favorite fruit, where they can bubble in "Apple" or "Pear" (but not both). They can also leave it blank. The results are 90,000 people left it blank, ...
1
vote
0answers
14 views

Feedback on Experiment: bosses and meetings

As my context is rather specific, I'll try to write an analogy that sounds more natural and preserves all characteristics of the original problem. It goes like this: A certain company has around 2k ...
0
votes
0answers
18 views

Nonparametric equal variance tests

I have two large, non-normal samples as evidenced by the Kolmogorov-Smirnov test. I now wish to test for equality of variance nonparametrically. I'm confused as to which nonparametric test is ...
0
votes
1answer
33 views

Non parametric: How to detect different groups

I have data sets for different serial numbers of devices. Those data are not following a normal distribution. I would like to know which serial numbers are behaving differently from the overall ...
1
vote
0answers
25 views

Seperate regressions approach vs. interaction term approach

I am writing my thesis in finance, and my thesis advisor want me to do a categorical analysis, where I include control variables. He tells me I cannot simply include interaction terms (i.e. category x ...
0
votes
0answers
17 views

Sampling non-normal (near power-law) distribution

Context: I have a population that shows three distinct behaviors (slope) on a cumulative distribution function (survival proportion over time) and I want to find factors that may explain these ...
0
votes
1answer
30 views

Converting a 5-point Likert scale to 0 to 30 range

Hi thanks for viewing my question. In my research I want to adopt a measure from prior work and apply it to a new context. The question related to a 5- point likert-scale, however, further reading ...