When you analyze your data using statistics, you should know what aspect of your data you want to test. The statement that embodies your test is called your hypothesis.
- [Instructor] One way to analyze data is a method called hypothesis testing. You can't really prove or disprove a hypothesis, which is a guess about your data, but you can decide whether the data that you have collected supports your hypothesis or not. When you formulate a hypothesis, you are making an educated guess about a relationship between two sets of data. For example, you might suspect that individuals who drive to your store will tend to spend more if they drive from farther away and the guess about the relationship is that individuals who want to shop at your store want to spend money and then they want to take the items home with them rather than paying for shipping.
Your first step should be to state the null hypothesis, and the null hypothesis basically says that factor A has no effect on B. In this case, the null hypothesis might be that the distance driven by a customer to come to the store has no effect on the amount that they spend. The alternative hypothesis is that factor A does affect factor B, and this is the guess that we made before, that the farther a customer drives, the more they are likely to spend.
The alternative hypothesis can be either directional or non-directional. The alternative hypothesis I stated earlier that the farther someone drives, the more they are likely to spend, is a directional alternative hypothesis. We're looking to see if customers spend more the farther they drive. In this case, a non-directional alternative hypothesis might be that individuals who drive to your store from farther away spend either more or less, that is, they spend differently than individuals who live close.
That doesn't make a lot of sense in this scenario, but I'm sure you can see other scenarios where it might. So how do you create an effective alternative hypothesis? Well, the first is that you must state there is a relationship between the variables. You believe that A leads to B. Second, you base your alternative hypothesis on your knowledge of the world. And again, that could be that the farther someone drives to come to your store, the more they are likely to spend so they can save on shipping. You should be able to express your hypothesis simply and briefly, and you must make sure that you can test your alternative hypothesis.
In other words, it is a conclusion that your data would support. If the data you collect cannot reasonably support your alternative hypothesis, than any conclusion that you come to will be invalid.
- Distinguish between the mean, median, and mode.
- Describe the relationship between variance and standard deviation.
- Identify a nondirectional hypothesis.
- Point out the difference between COVARIANCE.P and COVARIANCE.S.
- Explain correlation.
- Analyze Bayes’ rule.