Choosing Stats Test

• What is the first step in choosing a statistical test?

  Identify if testing for difference or correlation
• What are the four levels of measurement mentioned?

  Interval, Nominal, Ordinal
• What is the purpose of inferential statistics?

  To infer conclusions from data
• What does a significant result indicate in hypothesis testing?

  It supports or accepts the hypothesis
• What is the significance level for rejecting the null hypothesis?

  P<0.05 indicates less than 5% chance
• What is a Type 1 error?

  Rejecting the null hypothesis incorrectly
• What is a Type 2 error?

  Accepting the null hypothesis incorrectly
• What is the balance achieved by a 5% probability level?

  It balances Type 1 and Type 2 errors
• What are the three D's of decision-making in choosing a statistical test?

  • Is it testing for a difference or correlation?
  • What is the experimental design?
  • What level of data is being used?
• Which statistical test is appropriate for analyzing the relationship between sick days and stress scores?

  Spearman’s rho
• What test would you use to compare memory scores in the morning vs afternoon?

  Sign test
• Which test is suitable for comparing recovery from depression between CBT and drugs?

  Wilcoxon
• What statistical test would you use for personality type and university course association?

  Chi-Squared
• Which test is appropriate for comparing verbal reasoning test scores between genders?

  Mann-Whitney
• What are the eight statistical tests to know for the exam?

  1. Spearman’s rho
  2. Pearson’s r
  3. Wilcoxon
  4. Mann-Whitney
  5. Related t-test
  6. Unrelated t-test
  7. Chi-Squared test
  8. Sign test
• What factors affect the choice of statistical test?

  • Level of measurement
  • Experimental design
  • Type of data being analyzed
• What is the role of critical values in statistical testing?

  • Determine if results are significant
  • Compare calculated statistics to critical values