Sorry, you need to enable JavaScript to visit this website.

Effect Size

  • Measures of the size of an effect based on the degree of overlap between groups usually involve calculating the proportion of the variance that can be explained by differences between groups. This resource outlines different approaches to measuring this proportion.

    0
    No votes yet
  • G*Power is a tool to compute statistical power analyses for many different t tests, F tests, χ2 tests, ztests and some exact tests. G*Power can also be used to compute effect sizes and to display graphically the results of power analyses.

    5
    Average: 5 (1 vote)
  • This handout lists the most commonly used effect sizes, adjustments, and rules of thumb concerning sample size calculation. 

    0
    No votes yet
  • Plot the theoretical p-value distribution and power curve for an independent t-test based on the effect size, sample size, and alpha.

    0
    No votes yet
  • In this activity, students explore calculations with simple rates and proportions, and basic time series data, in the context of news coverage of an important statistical study. From 1973 to 1995, a total of 4578 US death penalty cases went through the full course of appeals, with the result that 68% of the sentences were overturned! Reports of the study in various newspapers and magazines fueled public debate about capital punishment.
    0
    No votes yet
  • In this activity, students learn the true nature of the chi-square and F distributions in lecture notes (PowerPoint file) and an Excel simulation. This leads to a discussion of the properties of the two distributions. Once the sum of squares aspect is understood, it is only a short logical step to explain why a sample variance has a chi-square distribution and a ratio of two variances has an F-distribution. In a subsequent activity, instances of when the chi-square and F-distributions are related to the normal or t-distributions (e.g. Chi-square = z2, F = t2) will be illustrated. Finally, the activity will conclude with a brief overview of important applications of chi-square and F distributions, such as goodness-of-fit tests and analysis of variance.
    0
    No votes yet
  • This group activity illustrates the concepts of size and power of a test through simulation. Students simulate binomial data by repeatedly rolling a ten-sided die, and they use their simulated data to estimate the size of a binomial test. They carry out further simulations to estimate the power of the test. After pooling their data with that of other groups, they construct a power curve. A theoretical power curve is also constructed, and the students discuss why there are differences between the expected and estimated curves. Key words: Power, size, hypothesis testing, binomial distribution
    0
    No votes yet
  • This activity allows students to explore the relationship between sample size and the variability of the sampling distribution of the mean. Students use a Java applet to specify the shape of the "parent" distribution and two sample sizes. The simulation then samples from the parent distribution to approximate the sampling distributions for the two sample sizes. Students can see both sampling distributions at the same time making them easy to compare. The activity also allows students to determine the probability of extreme sample means for the different sample sizes so that they can discover that small sample sizes are much more likely than large samples to produce extreme values. Keywords: sampling distribution, sample size, simulation
    0
    No votes yet
  • This interactive lecture activity motivates the need for sampling. "Why sample, why not just take a census?" Under time pressure, students count the number of times the letter F appears in a paragraph. The activity demonstrates that a census, even when it is easy to take, may not give accurate information. Under the time pressure measurement errors are more frequently made in the census rather than in a small sample.
    0
    No votes yet
  • This activity illustrates the convergence of long run relative frequency to the true probability. The psychic ability of a student from the class is studied using an applet. The student is asked to repeatedly guess the outcome of a virtual coin toss. The instructor enters the student's guesses and the applet plots the percentage of correct answers versus the number of attempts. With the applet, many guesses can be entered very quickly. If the student is truly a psychic, the percentage correct will converge to a value above 0.5.
    0
    No votes yet

Pages