Inferential stats

• Inferential statistics is often the part of research methods that students dread and there are a fair few complex terms that we're going to use in this video
• The statistics questions in the exam are often the ones that give you the most points for the least amount of writing so definitely worth getting right
• The only statistical test we need to calculate is the sign test and I'll show you how to do that in this video
• For the other seven tests we just need to know their names and when to use them
• Inferential statistics


  Go beyond the sample, they generalize the results and make inferences about the behavior of the entire target population from the data collected from the sample
• Descriptive statistics


  Techniques like measuring the central tendency or dispersion that summarize and describe raw data collected from the sample
• The researcher needs to ask how confident they are that the data collected from the sample is strong enough to support their inference that the same behavior is found in the target population
• If the likelihood of the results being due to chance is less than 1 in 20 (p is less than 0.05), then the data collected from the sample is considered to be significant and accepted
• Statistical tests are the tools that researchers use to work out if the results are significant
• Correlation


  The research just measures two covariables and looks for a relationship
• Test of difference


  An experiment where the researcher is testing for a difference in the dependent variable as a result of manipulating the independent variable
• Independent data


  Data from an independent groups design where the groups are measured independently
• Related data


  Data from a repeated measures or matched pairs design where each data point in one condition has a related data point in the other condition
• Levels of measurement


  • Nominal
  • Ordinal
  • Interval
• Ratio data is treated as interval data
• Statistical tests


  • Pearson's
  • Spearman's rho
  • Chi-squared
  • Mann-Whitney
  • Unrelated t-test
  • Related t-test
  • Wilcoxon
  • Sign test
• The statistical test to use depends on the dependent variable's level of measurement or in a correlation, the covariable with the lowest level of measurement
• To justify the choice of statistical test, you need to explain the experimental design, the levels of measurement, and whether it is a correlation or a test of difference
• To determine if the test is significant, you need to compare the calculated value to the critical value in a critical values table, considering the degrees of freedom and the level of significance
• Calculating the sign test

  1. Subtract condition B from condition A for each participant

  2. Record the sign (positive or negative) for each difference

  3. Count the number of participants with a difference (n)

  4. Identify the least frequent sign (s)

  5. Compare s to the critical value in a table to determine significance
• The sign test is the only statistical test that students are expected to calculate in the exam