Fundamentals of Statistics and Data Analysis - R Programming Assessment Answers

Topic: R Programming Assignment

• Which country did you choose? What is ESS?
  • Country chosen is France
• Choose two variables and create a research question, e.g. 
  • Does ethnicity impact the level of trust in the police in America?
• Create one or two hypothesis. e.g. African American individuals report lower levels of trust in the police. Write one or two sentences why you believe this is a reasonable hypothesis. Best way to do this: Look at previous research that discovered lower levels of trust in the police among African Americans and their explanations for it.  
• What is your independent, dependent variable and unit of analysis in your research question?
• What level of measurements are your variables? Describe these two variables in 2-3 sentences. e.g. Level of trust in the police is measured in (...). For a continuous variable, report the minimum and maximum value and mean (average). For a categorical variable, report the various categories. (How many categories does the variable have?, rank-ordered?, Which category has the highest observation?)

• Use the same dataset from last homework and delete all missing values, including "Don't Know" and "Refusals "

• If you have not done it so far, create a smaller dataset from your chosen country and include the following variables:

1.     gndr (gender)
2.     agea (age)
3.     blgetmg (belonging to a minority ethnic group)
4.     your chosen dependent variable
5.     your chosen independent variable

• In homework #1 you were expected to describe your variables. This week, we also learned about mean, median and mode. Report these measures to all your variables (depending whether your variable is continuous or categorical).

• Create percentage tables for each variable in your dataset and describe it with 2-3 sentences. (except continuous variable)

• Choose two variables in your dataset and create a contingency table. (Ideally, use your independent and dependent variable. Those who have a categorical variable with more than 5 categories, please use two other variables in your dataset).

• Please attach your codes to the document as an appendix (just copy and paste your command from R studio to the document).

1. Try to fix all mistakes from previous homeworks and combine the tasks from all homeworks into one word document (I might not be able to return homework #3 on time, so this is fine.)
2. Conduct a chi-square test on two categorical variables in your data. Write all the steps and logistics behind conducting a chi-square test. This includes showing understanding of:

• Null and alternative hypothesis

• alpha level, p-value

• critical value: How and where do you find it?

• Chi-square statistic

• degrees of freedom