Shulou(Shulou.com)06/02 Report--

This article shows you how to use JASP to easily calculate cohen's d effect indicators, the content is concise and easy to understand, it will definitely brighten your eyes. I hope you can get something through the detailed introduction of this article.

At present, some periodical papers require that when the significance test P value is significant (P < 0.05), the effect index should also be reported. The so-called effect amount, which is called Effect size in English, is used to measure the correlation strength between independent variables and dependent variables, which is almost not affected by the sample size.

In t-test and analysis of variance, the effect quantity shows the degree of difference of the mean. The Cohen's d effect index is commonly used in the t test, indicating the standard difference between the two means, while η ^ 2 (partial η ^ 2) is mainly used in ANOVA, indicating the change ratio of variable Y related to the horizontal change of variable X.

In the common SPSS statistical software, the t-test process does not provide the calculation of Cohen's d index, so when it is necessary to report the effect index, we need to calculate it by hand or use other statistical software to complete it.

Good news, JASP statistics software can easily output Cohen's d effect!

JASP is a new statistical software, it is completely free and does not need to write code, and SPSS can easily achieve statistical analysis through mouse clicks and drag menu parameters, Xiaobing has begun to use and continue to output relevant case practices.

Case practice

Forty athletes with similar basic conditions were randomly divided into two groups with 20 athletes in each group and given different training methods. Pre-examine whether there are differences in the performance of athletes under different training methods.

First of all, we will immediately do the description statistics of the groups to understand the basic situation of the two groups of data.

The test scores of group 1 and group 2 were (63.590 ±13.509) and (73.568 ±10.609) respectively. It is obvious that the average score of group 2 is 10 points higher than that of group 1.

Then the homogeneous test of normal distribution and variance shows that the data are normal and the variance is homogeneous, which satisfies two basic conditions.

Now let's look at the results of the t-test.

The test scores of group 1 and group 2 were (63.590 ±13.509) and (73.568 ±10.609) respectively. It is considered that there is a statistically significant difference in the influence of two different training methods on the test results (tasking music 2.600 and 0.013 < 0.05).

Cohen's d effect index

Finally, we report on the Cohen's d effect indicator.

Just check Effect size in the parameter options area, check Cohen's d, and check one more confidence interval if necessary.

End result:

JASP adds 3 columns to the t-test table, which are the statistical value of Cohen's d index and its 95% confidence interval respectively.

How do you interpret it? If you take the absolute value directly, Cohen's dice is 0.822 at this time.

Generally speaking, the value of Cohen's d is 0.2-0.5 for small effect, 0.5-0.8 for moderate effect, and 0.8 for large effect.

In this case, the Cohen's dice 0.822 is more than 0.8, so it is considered that the mean difference between the two groups is significant (Cohen's dice 0.822). The above content is how to use JASP to easily calculate the cohen's d effect indicator. Have you learned the knowledge or skills? If you want to learn more skills or enrich your knowledge reserve, you are welcome to follow the industry information channel.

Welcome to subscribe "Shulou Technology Information " to get latest news, interesting things and hot topics in the IT industry, and controls the hottest and latest Internet news, technology news and IT industry trends.