ENV100Y5 Lecture Notes - Lecture 4: Null Hypothesis, Endocrine System, Cancer Cluster
Module 1: May 7-18
Date: Thursday, May 10
SESSION 4: HOW SCIENCE IS DONE: AN ASIDE ON HYPOTHESES
Readings: Chapter 2
Not all scientific studies involve hypothesis tests
● Some studies are purely descriptive
○ E.g. spatial patterns, temporal patterns
● Meaningful descriptive studies should lead to hypothesis tests
● Need to pass the “so what?” test
What is a hypothesis?
● A provisional (an idea) statement that proposes a possible explanation for a particular
observed phenomenon
● Superstitions are primitive hypotheses
● Null Hypothesis: A statement of “no effect”.
○ Experimental results are analyzed to see whether they support the (alternate)
hypothesis or the null; no relationship or arbitrary (random) - not the opposite
Environmental Science
● We propose and test hypotheses to understand patterns and relationships in nature, and
to understand the effects and consequences of human activities on the environment
Good Hypotheses “Breed”
● When tested, give rise to lots of other hypotheses
○ Create more questions
Hypothesis v. Null Hypothesis
● Hypothesis (HA): Cigarette smoking increases the probability of developing certain types
of lung cancer
● Null Hypothesis (H0): Cigarette smoking has no effect on the probability of developing
certain types of lung cancer
Predictions
● What you expect to happen if your hypothesis is true (in terms of measurable
results)
● Ex. IF cigarette smoking increases the probability of developing certain types of lung
cancer, THEN the incidence of lung cancer should be higher in a group of heavy, lifetime
smokers than in a comparable group of non-smokers.
Predictions give rise to study designs
find more resources at oneclass.com
find more resources at oneclass.com
69
ENV100Y5 Full Course Notes
Verified Note
69 documents
Document Summary
Session 4: how science is done: an aside on hypotheses. Meaningful descriptive studies should lead to hypothesis tests. Need to pass the so what? test. A provisional (an idea) statement that proposes a possible explanation for a particular observed phenomenon. Null hypothesis: a statement of no effect . Experimental results are analyzed to see whether they support the (alternate) hypothesis or the null; no relationship or arbitrary (random) - not the opposite. We propose and test hypotheses to understand patterns and relationships in nature, and to understand the effects and consequences of human activities on the environment. When tested, give rise to lots of other hypotheses. Hypothesis (ha): cigarette smoking increases the probability of developing certain types of lung cancer. Null hypothesis (h0): cigarette smoking has no effect on the probability of developing certain types of lung cancer. What you expect to happen if your hypothesis is true (in terms of measurable results)
