Texts: Goals:
1. To collect, organize, display, and summarize a set of data in order to describe and make conclusions regarding what the data shows about individuals from which the data was collected. Optionally, students can disaggregate the data, create displays and summaries of the subgroups, and then compare and contrast the subgroups to uncover hidden facts from the data.
2. To apply principles and procedures of an inference test to a real-world application.
Details and Deadlines:
Week 1
Decide on an accessible population to target (of at least 300 individuals) and one quantitative (real or interval level) and one qualitative variable (which should have 2-4 categories) to study. Write in complete sentences and explain why you chose this population, how it is accessible, and the variables that will be studied.
Example: The population to be studied is countries or provinces (such as US states) of the world. The quantitative variable will be the birth rate (per 1000 people) in the country/province and the qualitative variable will be the continent.
Example: The population to be studied will be students at Mercer's Regional Academic Centers. The quantitative variable will be the person's age and the qualitative variable will be their race (using categories of Caucasian, Person of Color, Hispanic, Asian, Other). Note: Make sure you can access this population.
Example: The population to be studied will be employees in the company in which I work. The quantitative variable will be the commuting time (in minutes) for the employee and the qualitative variable will be their type of vehicle (using the categories of compact car, larger sedan, SUV/van, truck, motorcycle or other).
Week 2
Develop plans to collect values for the two study variables from 30-50 individuals from the target population, chosen so that, ideally, the sample is representative of the population. Explain and discuss your sampling methodology.
Ex. Suppose the population is high school students in Douglas County, GA, and your variables are their score on a mathematics attitude survey and their race. So, to collect the data, you intend to call up the five high schools in Douglas County and ask school officials if they will allow 10 randomly chosen students to take the survey, hoping that at least three of the five schools will allow you to do so. For the race, you include a question to ascertain their race among given choices.
Weeks 3-5
Collect data according to your plan for sampling, discussing any difficulties in data collection. For the quantitative variable, follow procedures discussed in class and in class notes to produce a frequency table with appropriately-chosen classes (intervals) and histogram. Discuss the shape of the distribution of the quantitative variable and any irregularities. Also, calculate summary statistics (measures of center and measures of variation) and include these in your data description. Optionally, if you have 50 individuals, disaggregate individuals into 2-4 groups according to the qualitative variable, and then produce histograms and summary statistics for the groups separately. Contrast these groups using the histograms and statistics, discussing possible reasons for differences.
Week 6
If possible, from the internet or established source, locate a population parameter which can be used to compare one of your sample statistics with this population parameter. Determine a hypothesis (inference) test that would be appropriate to compare the above-mentioned quantities, then write proper null and alternative hypotheses. Explain why you believe the test chosen would be appropriate.
Week 7
Write a rough draft of your hypothesis test, including all aspects (use the outline from the template used in class notes). The professor will give feedback to you before the final draft is due on the last day of class, to help ensure that you have all major aspects correct.
Week 8
Produce a final project report (paper) using the following outline:
I. Background and Introduction to the Data (including identification of the population and study variables)
II. Data Collection and Sampling Methodology
Explain the procedures used to choose your sample, obtain the data, and any issues encountered in this process. Also, comment on the extent that you believe the sample represents the population.
III. Data Analysis and Visualization
Describe the data collected in the sample, including a frequency table, histogram, and summary statistics used to create this description. If you did the optional segment, include this analysis in this section as well.
IV. Inference Test
A. Research Question, Hypothesis, and Level of Significance (include the population parameter to be compared and its source).
B. Type of Inference Test and Required Conditions
Explain why the chosen test was used and show that conditions for this test have been met or explain why there is an issue with a condition.
C. Equations and Calculations (of the test statistic and p-value of the test)
D. Statistical Decision and Conclusion in the Context of the Research Question
V. Summary of Findings and Comment