In most applied studies, however, we're pretty clueless about such population parameters. In the previous example, our scientists had an exact alternative hypothesis because they had very specific ideas regarding population means and standard deviations. Like we just saw, estimating power requires specifying *Compute left (lct) and right (rct) critical t-values and power. *Enter chosen alpha and expected NCP as raw data. The exact calculation can be replicated from the SPSS syntax below. So this is roughly the probability of rejecting H 0 -or the power (1 - β)- for our first scenario.Ī minor note here is that we'd also reject H 0 if t < -2.02 but this probability is almost zero for our first scenario. Under this noncentral t-distribution, the probability of finding t > 2.02 ≈ 0.637.If our alternative hypothesis H A is exactly true, t follows a noncentral t-distribution with df = 38 and NCP = 2.37.If we test at α = 0.05 (2-tailed), we'll reject H 0 if t 2.02 (right critical value).First off, our H 0 is tested using a central t-distribution with df = 38.The figure below illustrates how this works. The NCP tells us how t is distributed under some exact alternative hypothesis and thus allows us to estimate the power for some test. Now, this expected (or average) t = 2.37 under the alternative hypothesis H a is known as a noncentrality parameter or NCP. We expect to find t = 2.37 if the population mean difference is 6 mmHg (160 - 154). This is based on a t-distribution with df = 38 degrees of freedom (total sample size N = 40 - 2). We expect p = 0.023 so we expect to reject H 0. Compute t-test for expected sample sizes, means and SD's in Excel So let's for a moment pretend that we'll find exactly these and enter them into a t-test calculator. However, we do know the most likely outcomes: they're our population estimates. Obviously, nobody knows the outcomes for this study until it's finished. Or -alternatively- what's the probability of rejecting H 0 that the mean blood pressure is equal between treated and untreated populations? they plan to use an independent samples t-test at α = 0.05 with N = 20 for either subsample.the standard deviation should be around 8 mmHg (both populations).they expect their medicine to lower this to roughly 154 mmHg.the average blood pressure in some untreated population is 160 mmHg.Power Calculation ExampleĪ pharmaceutical company wants to demonstrate that their medicine against high blood pressure actually works. But before taking a look at factors affecting power, let's first try and understand how a power calculation actually works. This results in the 4 scenarios outlined below.Ĭorrect decision Probability = (1 - β) = powerĪs you probably guess, we usually want the power for our tests to be as high as possible. Type I and Type II ErrorsĪny null hypothesis may be true or false and we may or may not reject it. Not rejecting a false H 0 is known as a committing a type II error. So even though H 0 is false, we've little power to actually reject it. The probability of finding this is only 0.058. If a population correlation ρ = 0.10 and we sample N = 10 respondents, then we need to find an absolute sample correlation of |r| > 0.63 for rejecting H 0 at α = 0.05. For the aforementioned example, (1 - β) is only 0.058 (roughly 6%) as shown below. This probability is known as power and denoted as (1 - β) in statistics. What's the probability of correctly rejecting the null hypothesis? Now, given a sample size of N = 10 and a population correlation ρ = 0.10, Since p > 0.05, his chosen alpha level, he does not reject his (false) null hypothesis that ρ = 0.The significance level for this test, p = 0.68. He tests the (false) null hypothesis H 0 that ρ = 0.A scientist examines a sample of N = 10 people and finds a sample correlation r = 0.15.In some country, IQ and salary have a population correlation ρ = 0.10.Software for Power Calculations - G*Power.In statistics, power is the probability of rejecting Power – A Quick Introduction By Ruben Geert van den Berg under Statistics A-Z
0 Comments
Leave a Reply. |