Tagged Questions

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.

67 views

Constructing hypothesis test $\mu=0$

My question is as below: Random sample $Y_1,\dots, Y_n$ from $N(\mu,\sigma^2)$. Let $\bar{y}=\frac{1}{n}\sum Y_i$. (1) $(\bar{y}-\,\mu)/\sigma=a'x$ where $x\in R^n$, $x\sim N(0,1)$. (2) ...
29 views

Unpaired t-test with only summary means

Is it appropriate to conduct an unpaired t-test with only summary means from both groups? For example, let's say you want to compare: a. Professor A's scores received on a evaluation by his ...
139 views

Avoiding p-values and reporting t-values instead. References?

I was wondering if I could get some opinions on an issue. I'm analyzing my data using mixed-effects modeling in R (lme4 package). My model has by-subject and by-item intercepts and slopes, and random ...
38 views

Two sided permutation test

I'm trying to write a two sided permutation test to test the alternative hypothesis there is a difference in the medians of 2 independent samples. My question is this: am I calculating the p-value ...
27 views

Symmetry of alternative hypotheses of pairwise t-tests with p-value correction?

So I'm using R's pairwise.t.test on 4 populations with a Hochberg p-value correction and an alternative hypothesis that the population on the row has a higher mean ...
154 views

60 views

How to correctly measure effect on heavy-tailed distribution

I ran an experiment on my website where I randomly assigned users to either the treatment or control group, and have two questions about how to correctly compute significance of the results. Some ...
31 views

ADF Test on Volatile Series. Expected results?

I tried performing the Augmented Dickey-Fuller Test on SP500 data from MASS library and got the following results: ...
39 views

Which of these two ways is better to report comparison of paired data?

Suppose I am comparing the computational time of two algorithms A and B. They are solving randomized problem P. Let's say I solved the problem for seeds $1, 2, \dots, n$ with both A and B and got ...
81 views

24 views

What is the best non-parametric test for ratio, two-sample clinical trial data?

Clinical trials are a field I am quite interested in and since I have trouble accepting that every clinical trial's data will follow a normal distribution with sufficient sample size I was curious as ...