Null and Alternate Hypothesis - Statistical Hypothesis Testing - Statistics Course

Share

Summary

This lesson focuses on the crucial first step in hypothesis testing: accurately writing the null and alternate hypotheses. The video demonstrates how to extract pertinent information from word problems to formulate these hypotheses, emphasizing the distinction between mean-based and proportion-based problems, and the importance of correctly interpreting conditions like 'greater than,' 'less than,' 'equal to,' and 'not equal to.'

Highlights

Introduction to Writing Null and Alternate Hypotheses
00:00:01

This section introduces the importance of mastering how to write null and alternate hypotheses before delving into more complex hypothesis testing problems. The video will provide practice in extracting information from real-world scenarios to correctly formulate these hypotheses.

Problem 1: Soda Straw Diameter
00:00:46

A company states their soda straws are, on average, 4mm in diameter. An employee believes this is no longer the case and samples 100 straws for a hypothesis test with 99% confidence. The null hypothesis (H0) is that the mean diameter is 4mm (μ = 4), while the alternate hypothesis (H1) is that the mean diameter is not 4mm (μ ≠ 4).

Understanding Confidence Level and Alpha
00:03:45

For Problem 1, the sample size (n) is 100, and the confidence level (C) is 99% (0.99). The alpha level (α), also known as the level of significance, is calculated as 1 - C, which in this case is 0.01. Alpha and the confidence level always sum to 1.

Problem 2: Teen Sleep Hours
00:05:04

Doctors believe teens sleep no longer than 10 hours per day. A researcher believes they sleep longer. The null hypothesis (H0) states that the average sleep is less than or equal to 10 hours (μ ≤ 10). The alternate hypothesis (H1) states that the average sleep is greater than 10 hours (μ > 10).

Problem 3: Students Bringing Phones to School
00:08:12

The school board claims at least 60% of students bring a phone to school. A teacher believes this number is too high and samples 25 students. This problem involves proportions (percentages). The null hypothesis (H0) is that the proportion (p) is greater than or equal to 0.60 (p ≥ 0.60). The alternate hypothesis (H1) is that the proportion is less than 0.60 (p < 0.60).

Determining Alpha and Confidence for Problem 3
00:11:43

For Problem 3, the level of significance (α) is given as 0.02. The level of confidence (C) is then 1 - α = 1 - 0.02 = 0.98, or 98%. The sample size (n) for this problem is 25 students. The video emphasizes that the direction of the inequality in the alternate hypothesis dictates the specific testing procedure in subsequent steps.

Recently Summarized Articles

Loading...