There are two comments in regards to Performing a hypothesis test in regards to business statistics and an example of a hypothesis test.. Please respond with an opinion of how you feel about the post and support your opinion with examples. Each comment should be a total of 100+ words and all examples, resources etc must be based in USA.
|
|
The basic premise of hypothesis testing is simple; come up with an idea of a property a population should contain, then prove or disprove it using sampling techniques. The idea, or assumption, to be proven is known as the null hypothesis. Once the tester has created the assumption they are looking for, the null hypothesis, they then must decide on an alternate outcome if the sample disproves the first assumption. This second outcome is called the alternative hypothesis.
The most difficult aspect to hypothesis is often coming up with these two opposing ideas. As our test notes “It is not always obvious how the null and alternative hypotheses should be formatted. Care must be taken to structure the hypotheses appropriately so that the hypothesis testing conclusion provides the information the researcher or decision maker wants” (Anderson. D., Sweeney, D., & Williams, T., p. 350, 2012).
It is often useful to actually begin gathering information in support of the alternative hypothesis and use that information to arrive at the null hypothesis. Again, the text says sometimes “In some situations it is easier to identify the alternative hypothesis first and then develop the null hypothesis. In other situations it is easier to identify the null hypothesis first” (Anderson. D., Sweeney, D., & Williams, T., p. 350, 2012). Whichever works best for developing the idea is what is important.
After the null and alternative hypotheses are figured out, sampling is done of the population being considered. The sampling should result in either proving the hull hypothesis or the alternative hypothesis, but not both. If this does not happen there are two types of errors to be considered, aptly named Type I and Type II errors. These errors, along with the two hypotheses, help the researcher make conclusions about his test population.
An example in my work would be examining the education of Realtors in America to see how many have a 4-year degree or higher. By randomly sampling the Realtors in my area, the null hypothesis could be that 30% or less have a 4-year college degree and the alternative hypothesis would then be more than 30% have a degree. Whatever the results of this sampling would then allow us to make conclusions for the entire country.
Anderson. D., Sweeney, D., & Williams, T. (2012)
Statistics for Business and Economics,
Mason, OH South-Western Cengage Learning |
|
Hypothesis testing is a systematic method used to evaluate data and aid the decision making process. One of the first steps is to form a null hypothesis which is expressed as Ho. The null hypothesis is either rejected or fails to be rejected. The null hypothesis is assumed to be true unless there is statistically overwhelming evidence to the contrary. The alternative hypothesis H1 is an assertion that holds if the null hypothesis is false. For a given test the null and alternative hypotheses include all possible values of the population parameter, so either one or the other must be false. The following is a typical series of steps involved in hypothesis testing:
1) State the hypotheses of interest
2) Determine the appropriate test statistic
3) Specify the level of statistical significance
4) Determine the decision rule for rejecting
5) Collect the data and perform the needed calculations
6) Decide to reject or not reject the null hypothesis
There are three possible choices for the set of null and alternative hypotheses to be used for a given test. They are =, =, =. This will determine whether or not to reject or not reject the null hypothesis.
An example of hypotheses testing would be examining stated loan programs mortgage lenders were using. These programs were supposed to be design for self-employed individuals however they also became very popular for W-2 wage earners. The null hypothesis could be that 60% or more W-2 wage earners have defaulted due to this program and the alternative hypothesis is that 60% or less has defaulted. Whatever the outcome it would allow mortgage companies to develop programs better suited for individuals.