Add statistical tests

[ack2406]

After the tool for interpreting analysis results is created (see #18), we need to add relevant statistical tests to better understand and compare the speech frequency data across different languages. These tests will help identify significant differences between the analyzed languages and provide more insight into the results.

Tasks:

• Identify which statistical tests would be useful for this kind of speech frequency analysis.
• Consider tests like:
  • T-test
  • ANOVA
  • Chi-Square Test
  • Correlation Analysis
  • Post-hoc Tests
• Implement these tests in the tool created in #18 .
• Make sure to document the interpretation of these tests in the notebook or script, so the results are clear.

[ack2406]

I think we could do:

1. anova tests
2. t-tests between genders? (and comparing those differences to other languages)
3. correlation tests (maybe done in exploration notebook)
4. output p-values of each test

I dont really know