Escolha o teste estatístico adequado considerando a natureza dos seus dados e a pergunta de pesquisa. Avalie se os dados são paramétricos ou não paramétricos e selecione o teste que corresponda à sua hipótese.

Choosing the right statistical test for your hypothesis involves a systematic approach to ensure that the test is appropriate for your data type and research question. Here’s a step-by-step guide to help you select the correct statistical test: 1. Understand Your Research Question and Hypothesis 2. Identify the Type of Data You Have 3. Determine the Number of Groups or Variables 4. Consider the Sample Size and Data Distribution 5. Select the Appropriate Statistical Test 6. Check Assumptions of the Chosen Test 7. Consult Statistical Resources and Tools

Choosing the right statistical test for your hypothesis depends on several factors, including the type of data you have, the number of groups or conditions you're comparing, the distribution of the data, and the specific hypothesis you are testing.

> Determine the Types of Variables: Identify if your variables are categorical, ordinal, or continuous. > Define the Hypothesis: Clarify if you are testing for differences, associations, or predictions. > Check Assumptions: Ensure your data meets the test assumptions. > Select the Test: Use parametric tests for normally distributed data and non-parametric test for non-normal data. By following these steps, you can choose a test that aligns with your data and research question.

Or you can just make up the data as appears to have been done in testing the relationship between global surface temperatures and net cumulative carbon emissions. Or be selective in choosing your end points.

Zur Überprüfung der Normalverteilung kommen Verfahren wie Kolmogorov-Smirnov Test, der Shapiro- Wilk Test und der Anderson Darling Test in Frage.

Testing assumptions is very important, especially in parametric tests as it can affect the accuracy of your results, most statistical tests we perform are based on a set of assumptions so be careful when these assumptions are violated, the results of the analysis can be misleading or completely erroneous, one of the assumptions for the parametric tests is the distribution of the data represented by the normality, you can calculate the skewness and kurtosis, checking visually the shape of the data by creating an histogram or conducting the normality test using the Shapiro-Wilk or Kolmogorov-Smirnov test.

Sample size greatly influences the choice of statistical test. Larger samples suit parametric tests, meeting assumptions better. Small samples may require nonparametric tests, ensuring adequate power to detect effects. Always consider sample size for accurate hypothesis testing.

When you define well your hypothesis, so it will be clear for the statistician to decide what statistical test he wants to use, you might want to check if there a significance difference in the mean scores across levels or you want to check the relationship between categorical variables.

When you are conducting parametric tests such as independent t-test or one-way ANOVA for example, you need to check also the homogeneity of variances as it is a second assumption, so if this assumption is violated you need to use another test such as the Welch test.