These are writing assignments for a graduate-level applied research methods statistics 1 class. Must be knowledgable in the system software stata. Please find attached.
Writing Assignment 6:
Adding Confidence Intervals to your Descriptions of Public Opinion
Due date: Friday, February 26, 6:00 a.m.
Purpose: This assignment reinforces concepts and coding skills that you will use repeatedly in the remainder of this class and in 8131. It also prepares you for the first paper assignment.
Knowledge: This exercise
Reinforces your understanding of confidence intervals
Tests your ability to analyze subsets of your data
Skills: This exercise also
Using Stata to create variables and run analyses by group
Develops your ability to write about statistics
Task: Your supervisor for your internship at the campaign of a candidate for Congress wants you to generalize your findings on public opinion to the U.S. population. She asks you to examine the 2018 GSS again, but she wants you to choose a different issue, summarize public opinion on that issue by group, and discuss to what extent you can draw conclusions about the U.S. population based on this sample.
Choose a different topic (see previous writing assignments for possible choices)
Examine whether opinion on this issue varies with two variables of your choice by using subsetting if statements.
Obvious choices include sex, race, age, education (educ), religion (use relig), religious attendance (attend), party identification (partyid), and liberalism-conservatism (polviews).
Use GSS Data Explorer (https://gssdataexplorer.norc.org/ ) to check the question wording for your public variable.
Click on SEARCH VARIABLES
Put a variable name (e.g., cappun) or search term (e.g., death penalty) in the Keyword box.
Click on variable name to find exact question wording. Include at least part of the question wording when you explain how you coded your dependent variable.
Use codebook varname or tab varname, nolabel to make sure that you understand how each variable is coded.
Create a new dummy variable version of your dependent variable and recode it either 0-1 or 0-100.
If your dependent variable has more than two values, you may want to do a frequency distribution or a crosstab with your independent variables to decide where to dichotomize it (that is, to decide which values to make No and which values to make Yes).
Do not make any non-missing values into missing values.
You want to discuss patterns for the full population, not just for those who have strong opinions.
If you are using one of the spending variables (nat*), do not drop those who think we are spending about the right amount.
If you decide to focus on who wants to increase spending, code both the people who say we are spending about the right amount and those who say we are spending too much as 0’s.
If you decide to focus on who wants to cut spending, code both the people who say we are spending about the right amount and those who say we are spending too little as 0’s.
If you are looking at attitudes toward sex outside of marriage, decide whether to include the people who say “almost always wrong” or “wrong only sometimes” with those who say “always wrong” or with those who say “not wrong at all.”
Remember to code your dummy variable 0 for No and either 1 for Yes (in which case you should use proportion) or 100 for Yes (in which case you should use mean).
Even if you use proportion on a 0-1 dummy variable, you should translate the proportions into percentages because your reader will understand percentages better.
Using subsetting if statements, see whether public opinion is different in different subsets of the data (e.g., calculate separate percentages for men and women; for Democrats, independents, and Republicans; or for liberals, moderates, and conservatives).
We covered subsetting if’s in sub-module 2G.
Note that bysort does not work with mean or proportion.
If a variable has more than three values, you probably want to simplify the if statement to include multiple values to make patterns clearer (e.g., you might use if age<40 and if age>=40 & age<. to look at age differences).
Similarly, you might want to calculate percentages separately for Democrats, independents, and Republicans or for liberals, moderates, and conservatives, instead of using the more detailed categories in the GSS.
Write approximately one page (double-spaced, 12-point font, in Word) describing your findings.
In the first paragraph, briefly state what you are going to do (e.g., I am examining public opinion on X in the U.S. population and seeing how it varies with values of these two independent variables).
You might want to explain why this topic is worth investigating.
You might want to briefly present your expectations about differences across groups (e.g., I hypothesize that men will be more likely than women to …).
Present the percentage of the GSS who say Yes (the value you coded 1 or 100) and generalize to the population as a whole. (That is, give us both the sample percentage and the 95% confidence interval.)
Describe how the percentage varies across the values of your two independent variables.
For ordinal-level independent variables, does the percentage steadily increase or decrease as the independent variable increases?
Use 95% confidence intervals to generalize to the populations of your sub-groups (e.g., what can we say about the percentage of all men or all women or all Democrats who say Yes?).
See whether the confidence intervals for your groups overlap. If they do not, you can conclude that opinion on your topic differs between your groups in the population.
Briefly mention whether your hypotheses/expectations were correct.
Include your mean or proportion tables after your text but before your appendix.
Criteria: This is a low-stakes exercise, worth 2% of your final grade, so it is primarily an opportunity to practice your understanding of this module. Writing assignments are worth 10 points. To get the full 10 points,
Correctly code your dependent variable.
Correctly interpret the sample percentage and 95% confidence interval for the group as a whole.
Use subsetting if’s correctly.
Correctly interpret the sample percentages and 95% confidence intervals for each of your sub-groups.
Include all necessary tables.
Provide an appropriate appendix.
I will also provide feedback on your writing. Try to make this as easy and pleasant as possible for your supervisor (and me) to read. Use some logical order in your presentation. Use simple, active-voice language. Be grammatically correct.
