# Statistics

stude322

Please answer each question with at 100 words.

Include the reference/citation you used. Thanks.

1.  Within research there are 2 main types of hypotheses. You have the null and the alternative hypotheses.

Ho indicates the null hypothesis and is defined as there is no differences between the groups. This is always assumed and never stated by the researcher.

Ha or H1 is the alternative hypothesis and is defined as there is a difference between groups. This is always stated by the researcher and the one you want to prove.

Type 1 errors are easier to prevent than type 2, because type 1 is related to the alpha that is set by the researcher. You find statistical significance if your analysis is less than 0.05, 0.01 or 0.001. Using 0.05 as an example, this means that the error rate or type 1 error is 5%. This means that there is a 95% chance you'll be correct and a 5% chance you'll be wrong. Type 2 errors are related to beta. Beta is defined as 1 - power. Power is the ability to find an effect. We typically shoot for a power f 0.8 or above. This means that beta is 1 - 0.8 or 0.2, so 20% of the time we'll make a type 2 error

Explain the significance of having both types of hypotheses?

2.  When we conduct research, we are always concerned with the sample size of our study to ensure that we have adequate power. What some people tend to focus on is the actual size of the sample. There are general guidelines for sample size. As a rule of thumb, if you have 25 people per group that you are testing, then it's likely that the power will be around 0.8. Keep in mind that this is a rule of thumb and a power analysis should be conducted to ensure adequate sample size. Consider the following:

You have received a business research study done by a consultant for a life insurance company. The study is a survey of customer satisfaction based on a sample of 600. You are asked to comment on its quality. What do you look for? Please explain.

3.  The scales of measurement are critically important when discussing statistical analyses. The one thing you will learn is that the scale of measurement you use will dictate the statistical analysis you can conduct.  In general, these scales are hierarchical in nature can be split into qualitative and quantitative scales. Nominal and ordinal are qualitative scales and interval and ratio are quantitative scales.

In the four different scales of measurement, explain the impact on the statistical analysis when you choose a nominal, ordinal, interval, or ratio scale?

4.  Why is it important to ask the right question on surveys?  What role does statistics play in the creation or marketing a product­­­­­?

5.  How do you minimize the major sources of error in communication studies?

6. Advantages and disadvantages of communication approaches.  Why do you think companies might outsource communication study?

• 7 years ago
• 20
Answer(1)

Purchase the answer to view it

• stat_assignment.docx
• stat_assignment.docx