160 likes | 193 Views
S519: Evaluation of Information Systems. Social Statistics Ch6: Hypothesis. Last week. This week. The difference between a sample and a population Null and research hypotheses What is a good hypothesis. What is a hypothesis?. Hypothesis An educated guess Research questions hypothesis
E N D
S519: Evaluation of Information Systems Social Statistics Ch6: Hypothesis
This week • The difference between a sample and a population • Null and research hypotheses • What is a good hypothesis
What is a hypothesis? • Hypothesis • An educated guess • Research questions hypothesis • A good hypothesis translates a problem or research question into a form that is more amendable to testing • Practical way: test your hypothesis in a sample and generalize it to the larger population
Research and reality • $$$ • Time • Sampling: • Sample vs. population • Sampling errors measure how well a sample approximates the characteristics of a population.
Sampling • A representative sample • Represent population as close as it can • Ensuring the high similarity of both • Time and $$$ • What is a big sample?
Null hypothesis • Assumes no relationship between two variables that you are going to study • Such as there will be no difference in the average score of 9th graders and the average score of 12th graders on the ABC memory test. • There is no difference between white and black families in the amount of assistance offered to their children in school-related activities.
Null hypothesis • A starting point • In the absence of any other information, guess? • Benchmark against other outcomes • To compare with other observed outcomes to see if these differences are due to some other factor
Research hypothesis • A definite statement that there is a relationship between variables • Null hypothesis research hypothesis • There is no difference between white and black families in the amount of assistance offered to their children in school-related activities. • There is a difference between white and black families in the amount of assistance offered to their children in school-related activities.
Nondirectional research hypothesis • Reflects the difference between groups, but the direction of the difference is not specified (such as more than or less than)
Directional research hypothesis • Reflects the difference between groups, and the direction of the difference is specified. • The average score of 12th graders is greater than the average score of 9th graders on the ABC memory test. • Either • H: X > Y or H: X < Y
Null vs. research hypothesis • Differences? • No relationship vs. has relationship • Refer to population vs. refer to sample • Indirectly tested vs. directly tested • Greek symbols vs. roman symbols
Good hypothesis • Criteria • Stated in a declarative form and not as a question • Posits an expected relationship between variables • Reflects theory or literature • Be brief and to the point • Testable and measureable • Parents who enroll their children in after-school programs will miss fewer days of work in one year and will have a more positive attitude toward work than will parents who do not enroll their children in such programs.
Exercises Lab • Take three empirical research articles, find • What is the null hypothesis • What is the research hypothesis • Create your own null and research hypothesis in your interested area. • Evaluate your hypothesis based on the criteria, • What are hypothesis for your group project