[Scott Hartshorn] Hypothesis Testing: A Visual Introduction to Statistical Significance
Download as PPTX, PDF0 likes854 views
Hypothesis testing is used to determine if an observed outcome is statistically significant by calculating how many standard deviations it is from the average and finding the probability of it occurring by random chance. Standard deviation measures the variation or spread of measured values, with a low standard deviation meaning values are clustered together and a high one meaning more variation. While we care about the standard deviation of individual measurements, what's more important for statistical significance is the standard deviation of the average value, which can change with additional measurements.
![[Scott Hartshorn] Hypothesis Testing: A Visual Introduction to Statistical Significance](https://image.slidesharecdn.com/scotthartshornhypothesistesting-avisualintroductiontostatisticalsignificance-170918150515/85/Scott-Hartshorn-Hypothesis-Testing-A-Visual-Introduction-to-Statistical-Significance-6-320.jpg)
[Scott Hartshorn] Hypothesis Testing: A Visual Introduction to Statistical Significance
- 1. Hypothesis Testing: A Visual Introduction to Statistical Significance Scott Hartshorn Summarized by Enrico Hugo
- 2. What is Statistical Significance? How unlikely would this outcome have been if it just happened by random chance?
- 3. Standard Deviation • Standard deviation is a way of measuring how spread out your measured values are • Low SD means the values you measured are clustered together • High SD means the values have a lot variation in measurements
- 4. The Most Important Concept “We do not care about the standard deviation of our data. What we care about is the standard deviation of the average value of all of our measurements. And that standard deviation of the average can change as you make additional measurements.”
- 5. Finding Statistical Significance The overall process of finding statistical significance: 1. Determine how many standard deviations our outcome is from the average outcome. 2. Look up that level of standard deviation in a probability table to find how unlikely it is that the outcome would occur by random chance.
Editor's Notes
- #3: For instance, say you are a farmer trying out a new type of pig food. You are trying to determine if the new food makes the pigs gain weight faster. To do this test, you try the new food on 10 pigs, and the old food on 10 pigs. After a month, you measure the weight of all the pigs and find that the pigs who ate the new food gained more weight. Does that mean the new food caused the increased weight gain? Well, maybe. Maybe the new food caused that result, or maybe you just happened to give the new food to the 10 pigs that were always going to gain the most weight no matter what. How can you tell? What we are doing with statistical significance calculations is determining how unlikely an outcome was to occur by random chance, and then deciding if that probability is unlikely enough that we can conclude something other than random chance caused that outcome.
- #4: As an example, pick a coin from your pocket, for instance, a quarter if you are in the United States. If you measure the weight of 10 of those coins, they will probably all weigh about the same. After all, they were all manufactured to be similar. Now if you go outside and find 10 rocks approximately the size of those coins and measure the weight of those rocks, there will be a lot more variation in the weight of the rocks. The standard deviation of the weight of the rocks is higher than it is for the coins.