Part 1: Hypothesis Testing| Null & Alternative Hypothesis| Level of Significance | Type-I & II Error

In this video, we're discussing hypothesis testing, including null and alternative hypotheses, Type I and Type II errors, significance levels, and confidence levels. We aim to demystify these complex concepts with examples, useful for anyone in research fields such as pharmacy or engineering. We start with population sampling to determine average percentages, using previous year data for comparisons.

The concept of hypothesis involves null and alternative hypotheses to test differences. In a classroom example, checking if last year's results were better through hypothesis testing is highlighted. Key components include setting up the hypothesis, understanding Type I errors (rejecting a true null hypothesis), and acknowledging significance levels in testing scenarios.

Proceeding with hypothesis setup involves selecting null and alternative hypotheses, utilizing sample size and decision-making based on selected tests. Various test methods (t-tests, z-tests) are outlined depending on sample size. This segment focuses on understanding the criteria for test selection and execution based on different hypothesis scenarios.

Further explanation on Type I and Type II errors, with regards to hypothesis outcomes. Importance of correct decision making is highlighted. Discussion transitions into significance levels and confidence intervals—key measures in hypothesis testing. Emphasis on differentiating between normal occurrences and significant variances in experiment results.