Is a property of a hypothesis testing method: the probability of rejecting the null hypothesis given that it is false. The power of a test depends on sample size, effect size, and the significance ($\alpha$) level of the test.
2
votes
0answers
21 views
Asymptotic vs. bootstrap test statistic, size and power properties
I am running a VAR based Granger non-causality tests. I've obtained asymptotic and bootstrap p values for Wald joint test of 0 restriction on a set of lagged variables. It appears, bootstrap based ...
0
votes
1answer
23 views
T-test shows no differences, but the experiment group shows tendency more benefit in all variables measured than control group
I've just finished an animal experiment. I compared 1 control group and 1 experimental group, the only difference between the two is type of diet. For statistical analysis I used the independent ...
2
votes
1answer
27 views
Power analysis for minimum sample size for 6 continuous predictors and 1 dichotomous criterion
My study has 6 continuous predictor variables and a dichotomous criterion variable. The IRB wants me to provide a power analysis, which I take to mean how I decided on number of participants to ...
0
votes
1answer
23 views
Power Calculation for Disease Modeling in iPS cells
I apologize in advance if the question is rather simple, but I have been having a difficult time figuring it out.
I am an experimental scientist interested in modeling human disease with induced ...
9
votes
1answer
96 views
Is there a general definition of the effect size?
The effect-size tag has no wiki. The wikipedia page about the effect size does not provide a precise general definition. And I have never seen a general definition ...
0
votes
1answer
26 views
Repeated measures within factors settings for G*Power power calculation
I'm trying to perform a power calculation with G*Power.
There are two quite important options, the meaning of which is not clear to me:
"Number of groups" - what is this? I have a 2x2 repeated ...
1
vote
0answers
27 views
Computing $\eta_P^2$ from $\eta_G^2$ generalized eta for G*Power
I am trying to perform a power calculation using G*Power. I need $\eta_P^2$, but the ez package for R gives me $\eta_G^2$. I understand the reasons for it doing this, but I still need $\eta_P^2$ for a ...
1
vote
3answers
63 views
When do Post-hoc tests require an adjustment for multiple comparisons
What happens to the Type 1 error rate, the Type 2 error rate, and Power if you do
not adjust for multiple comparisons when you should? What happens to these as a result
of using something like ...
0
votes
0answers
17 views
What test to asses the complication a treatment has with a small sample size(80) and only 5-10% complication rate?
I am assessing the benefit of using a therapeutic intervention in a population of 80 people split evenly into two groups. The benefit is to decrease a certain complication which only has a incidence ...
0
votes
1answer
55 views
2 x 2 between-subjects design ANCOVA with non-sig. interaction effect; but profile plot shows curves crossing
I'm running a 2X2 between-subjects design ANCOVA and wonder about one peculiar thing: The ANCOVA output table reveals no significant interaction effect, albeit the profile plot shows two lines that ...
0
votes
0answers
29 views
Nonquestion: Low power of neuroscience research and consequences thereof [closed]
* THIS IS NOT A QUESTION *
I thought this might be of interest to readers of this list, but I apologize if this is considered offtopic or abuse. I will not post anything further in reply to any ...
5
votes
3answers
221 views
Simulation of Fisher's exact test is underestimating power
Summary: My simulations don't match my power calculation.
(This question has become rather long, so you might not read to the bottom. I think it's a sample size problem.)
I'm running some ...
1
vote
0answers
24 views
Equivalence tests for STP3 - location of maximum power
Lehmann and Romano show in their Th 3.7.1 (Lehmann and Romano 2005, p81) when a UMP equivalence test $\phi_1$ exists and that it has a power that is maximised at some point $\theta^\star$ inside the ...
-1
votes
1answer
89 views
Two independent random variables for Binomial distribution with different probabilities of success [closed]
Assuming that we have observed two independent random values $X \text{~} Bin(8; p)$ and
$Y \text{~}Bin(4; p^2)$.
Using the sample $(X; Y )$, I want to test the statistical hypothesis $H_0 : p \ge ...
1
vote
0answers
236 views
G*Power-Repeated measures MANOVA “number of measurements” input field
I am trying to calculate the sample size needed with G*Power for my dissertation study. I will be doing a Repeated Measures MANOVA within/between interaction. My question is in the field "number of ...
0
votes
0answers
46 views
How to calculate vector-valued power to detect significant coefficients in a multiple logistic regression?
I'm running an experiment. Once I gather my data, I'm going to fit the model
$$
pr(y=1) = \Lambda[\alpha + \beta_1T_1 + \beta_2T_2 + \beta_3T_3 + X'\gamma +\epsilon]
$$
where $\Lambda$ indicates ...
2
votes
1answer
134 views
Computing type II error $\beta$
In hypothesis testing for the value of the population mean, when computing type II error $\beta$, if the alternative hypothesis includes many possibilities, is it always the case that $\beta$ is ...
1
vote
0answers
38 views
In general which runs test is more powerful?
There are several tests for randomness, one is runs up and down, another is run against mean or some other values, of cause, Bartel's rank test can also be used.
There are studies shows where ...
1
vote
1answer
174 views
Figuring out an effect size with a P value for a t-test, sample means, and sample sizes
An author did not report an effect size so I am hoping you might be able to help me calculate it.
I know the Means are:
Condition 1: 326
Condition 2: 558
Sample size:
Cond1: 11
Cond2: 12
T-test p ...
3
votes
2answers
100 views
What does statistical power mean when we are interested in the probability of correctly not rejecting the null hypothesis?
It seems that statisticians are usually only interested in statistical power. In other words, they are interested in the probability of correctly rejecting the null hypothesis.
What if we are ...
0
votes
0answers
50 views
Can widths of confidence intervals be used to assess statistical power?
Suppose you repeatedly sample from a normal population with mean $\mu$ and variance $\sigma^2$. Is there a way of estimating statistical power from the widths of the confidence intervals of the sample ...
5
votes
1answer
121 views
How statistical packages calculate power
How do statistical packages calculate power? For example, suppose we have a sample $X$ of $100$ observations. We assume that they are from a normally distributed population (iid). Our hypothesis test ...
2
votes
0answers
72 views
Power analysis ordinal probit regression
Suppose I have $n=100$ observations of ordinal data and get threshold coefficients $b_1, \dots, b_3$ and probit slope $b_4$. I want to test the hypothesis $H_{0}: \frac{b_{3}}{b_{4}} = \frac{1}{2}$ ...
-1
votes
1answer
69 views
Measure to use in experiment
Suppose we have $100$ people and we obtain the average blood pressure $x$. Now suppose we have another group of $40$ people and they have an average blood pressure $\approx x$. How do we quantify the ...
2
votes
1answer
69 views
How does power analysis differ between paired sample and independent groups t-test?
Suppose in group 1 there are $n$ people and in group 2 there are $n$ people. If we conduct a 2 sample t test versus a paired t test, would we use $2n$ for power calculations in the two sample t test ...
2
votes
3answers
170 views
Two fair coins, why increasing trials in prop.test not reduce false positive?
I am simulating two fair coins and running a prop.test, how come increasing number of trials doesn't decrease false positive? I'm suspecting it's in some underlying ...
7
votes
1answer
524 views
Is significance of the p-value reliable with extremely small sample sizes?
As I'm completely new to statistics and clinical trials, I would ask you for help and clarification.
Let's assume we have 2 really small samples (each of n = 2, or so) derived from two normally ...
3
votes
1answer
50 views
Sources for sampling in case-control studies
In my previous job as a statistics teacher, I was involved in studies mostly as an advisor on a general level. Not that much hands-on experience from doing the actual sampling or data cleaning, ...
1
vote
1answer
45 views
Consequences of high power for our belief in the null hypothesis?
Suppose that we choose the size of the test to be $\alpha = 0.05$, and based on our sample size $n$ and magnitude of the absolute value of the estimate, we determine that the test's power (i.e., 1 - ...
0
votes
0answers
51 views
continous moderator in a within subject design
I'm a first year PhD student and I am a bit at a loss regarding which test to use, and how to calculate power for a grant proposal. Any help will be much appreciated!
I'm running all my participants ...
1
vote
0answers
62 views
How to compare task completion times in a crossover study
Ten participants have completed a task using two different methods A and B. The first five participants completed the task first using method A then B. The remaining participants completed the same ...
0
votes
0answers
261 views
Calculate Beta from t-value, independent samples
I have seen two formulas without explanation online:
$$Z_{\beta} = t - Z_{\alpha}$$
and
$$Z_{\beta} = \frac{t - \text{EffectSize}}{\sqrt{1 + t^2 / (2 \text{df})}}$$
Of course the simplicity of ...
1
vote
0answers
97 views
Minimum sample size determination for difference of two normally distributed populations
This is homework, but I am rather stuck and the TA for the class has yet to make his solutions. Any help with moving me in the proper direction would be most appreciated.
I am having some difficulty ...
4
votes
3answers
182 views
Efficiency and the number of regressors?
An econometrician told me that I shouldn't keep adding new variables to the model even if I have reason to believe they're relevant to the response variable, as it "reduces the efficiency of the other ...
1
vote
0answers
49 views
How can I calculate the statistical power of a MI based likelihood ratio test with many df?
I'd like to calculate the statistical power of a likelihood ratio test based on mutual information.
I'm using the asymptotic property that the test statistic $G = 2NI$ where $N$ is the sample size ...
2
votes
2answers
53 views
Conditions under which the power curve is not smooth or continuous in Hypothesis testing
Not sure if this is a valid question.
I was wondering if there is are good answers to this question:
Under what conditions is the power curve not smooth or continuous in Hypothesis testing?
...
1
vote
0answers
100 views
Retrospective power analysis of samples from Poisson distributions
I understand how the simulation at Power calculation for likelihood ratio test can compute the alpha, using prop.test, and the power from a direct count of simulation values, for two Poisson ...
2
votes
1answer
139 views
The impact of non-normality (contaminated normal) on type 1 error and power when sigma is known
When sigma is unknown, contaminated normal distributions tend to have (1) the issue of the actual Type 1 error rate being lower than the nominal level and (2) the issue of reduced power. This pattern ...
5
votes
1answer
127 views
Showing that the power of a test approaches 1 as the sample size approaches infinity
I'm working on some exercises for my econometrics class and I'm a little confused. I'm meant to consider a model
$$Y=\beta_0 +\beta_1X+u$$
and propose a test (test statistic and critical value) of ...
0
votes
2answers
835 views
How to calculate power (or sample size) for a multiple comparison experiment?
CrossValidated Folks
I collected data on 20 groups (of 30 elements each). A multiple comparison procedure (pairwise t test with Holm correction) shows that in general there are three set of groups: ...
4
votes
2answers
676 views
Power analysis for binomial data when the null hypothesis is that $p = 0$
I'd like to do a power analysis for a single sample from binomial data, with $H_0: p = 0$, vs. $H_1: p = 0.001$, where $p$ is the proportion of successes in the population. If $0 < p <1$, I ...
0
votes
1answer
129 views
Sample size determination/verification
I am going to conduct a survey in order to collect information for two variables and then calculate the correlation between them.
If we assume that $alpha$ = 0.05, $power=0.80$. Can someone show me a ...
16
votes
4answers
7k views
Is there a minimum sample size required for the t-test to be valid?
I'm currently working on a quasi-experimental research paper. I only have a sample size of 15 due to low population within the chosen area and that only 15 fit my criteria. Is 15 the minimum sample ...
0
votes
0answers
420 views
g*power: two-way ANOVA post-hoc power analysis
We had 19 participants undergo 2 conditions and collected 6 measurements (5-min separated) for each condition. We have analyzed our data with an ANOVA repeated measures for within factors. Now we want ...
0
votes
0answers
64 views
Power Calculations for Median in a Clustered Trial
I'm currently performing power calculations for an NGO wanting to evaluate a sanitation program. They've asked us to look at the distributional effects of their intervention. I know that I can appeal ...
2
votes
1answer
165 views
Repeated measures ANOVAs instead of repeated measures MANOVA w/ small N?
I have 3 variables that have been measured on 4 occasions and a sample size of 16. I was considering a repeated measures MANOVA to ascertain if the changes over time were statistically significant. ...
1
vote
2answers
71 views
Testing count variables with size as a covariate
I think linear regression could handle this but I am asking myself if that method has good statistical power.
Let's think of circles with different radii and let there be points inside those circles.
...
1
vote
1answer
52 views
How many data points for my new product do I need to tell if my new product performs differently to the old?
We've been using the old formula to produce a product for years. We take a sample every quarter or so and run it through 8 different quality tests (every quarter because it takes that long for the ...
1
vote
1answer
275 views
Can statistical significance be obtained in an underpowered study?
Excuse my ignorance. I tried to look up the questions but couldn't find it. I had a discussion today whether it is possible that a study result will have a p<0.05 yet that would be caused by chance ...
3
votes
1answer
147 views
The organization as a unit of analysis and sampling issue
I'm doing a quantitative study entitled "Technology Transfer and Competitive Advantages in Oil and Gas Companies".
In my study, the unit of analysis is the organization and there are only 9 oil and ...
