STATS FINALS

avatar
Created by
Balbada

Cards (15)

  • The null hypothesis is a statement saying that there is no significant difference between the population parameter and the value that is being claimed. It is the hypothesis to be tested.
  • The alternative
    hypothesis is a statement saying that there is a significant difference between the population parameter and the value that is being claimed. True once the null hypothesis is rejected.
  • P-value is the lowest level of significance at which the observed value of the test statistic is significant.
  • Rejection Rule: reject the null hypothesis when the significant value (p-value) is less than the level of significance (alpha).
  • When H0 is true, but it was rejected, then, it is called type 1 error. When H0 is true and did not reject, then, it is a correct decision.
  • When H0 is false and it was rejected, then, the decision is correct. When H0 is false but did not reject, then, it is called a type 2 error
  • if the study is examining differences between groups of one or more variables and the participants being tested is the same, then, it is a Paired Sample T-test.
  • If the study is comparing two independent samples on one variable, then, it is an Independent Samples t-Test.
  • A One Way ANOVA compares means from three or more independent groups to determine if they are significantly different from each other.
  • if the study is examining differences between groups of one or more variables and the participants are being tested once having two groups, then it is Independent Samplte T-Test and ANOVA
  • PAIRED SAMPLE T-TEST
    if the dependent variable is numerical and the normality is satisfied, then, proceed to use Paired Sample T-Test.
  • PAIRED SAMPLE T-TEST
    If the dependent variable is numerical but is non-normal, use Wilcoxon Signed Rank Test
  • PAIRED SAMPLE T-TEST
    If the dependent variable is ordinal use Wilcoxon Signed Rank Test
  • Wilcoxon Signed Rank Test is the non-parametric alternative test for the Paired Sample T-test.
  • Wilcoxon Signed Rank Test is used to compare two sets of variables that are in an ordinal level of measurement or that are numeric are from paired independently.