Research Methods- Date analysis.

Research Methods- Date analysis.

1. Descriptive statistics: Summarising and describing data.

   • Levels of Data:
     • Nominal: Data that consists of numbers of participants that fall into certain categories, e.g. eye colour.
     • Ordinal: Data that can be ranked from lowest to highest. It is measured on scales of unequal intervals.
     • Interval: Data that is measured on a sale of equal intervals, e.g. time.
     • Ratio: Similar to interval data however it can have a meaningful zero point, ie an absolute zero. Time can be ratio data as a value of zero time is meaningful.

2. Probability and significance:

   • Probability: Expressed as 'P' is between 0-1, 0 being when something won't happen and 1 being where it will definitely happen.
     • P= Number of particular outcomes divided by he number of possible outcomes.
   • Statistical Significance: Inferential tests are used to test the statistical significance.
     • This is done to conclude that a result is significant and probably not due to chance factors, supporting the research hypothesis.
       • Significance levels are expressed in terms of the probability that results were produce by chance, expressed a p<a decimal. P stands or the probability that the results are a product of chance factors.
       • Type 1 and Type 2 errors:
         • Type 1 errors occur when a researcher rejects the null hypothesis in favour of the alternative hypothesis , even when the findings are due to chance. In this case P<0.1 (10%) meaning the research is too lenient.
         • Type 2 errors occur when the null hypothesis is retained but the alternate hypothesis is actually correct. P will be less than or equal to 0.01 (1%) here, meaning it is too strict.

3. Statistical Tests: How to choose one.

   • The decision regards whether they are investigating a correlation (relationship), what level of data they have and what design you use.
     • If nominal date is used (categories) then chi-squared test is used.
     • If it is a correlation spearmans rho is used.
     • If independant groups is used the Mann-Whitney U test is used.
     • If repeated measures design is used then Wilcoxon test is used.

4. Using an inferential test:

   • Justifying the choice of test: Explain why you chose that test.
   • Calculate observed value, this is the outcome of a statistical test.
   • Use a table of significance to compare the observed and critical value.
     • Chi-Squared: The calculated value must be greater than or equal to the critical value.
     • Mann-Whitney U: The calculated value must be less than or equal to the critical value.