STAT40x3 :: Assignments

Below are links to assignments for the course. If data is associated with the assignment, it will be linked here. When you download anything except for the actual assignment, browsers and operating systems handle the downloads differently. The basic process is the right-click and select “Save Target as...” or “Save Link as...”. On the window that pops up, change 'Save as Type' to 'All Files' and make sure the file has the appropriate extension (suffix).

Assignments

No.	Due Date	Description
1	January 18, 2011	This assignment reveiws some important items from the first semester and introduces you to writing your homework for this course. Follow the directions carefully and attach your code to the end of the assignment. The solutions are posted The `R` script is posted.
2	January 25, 2011	This assignment also reviews (and builds upon) some previous items covered. Follow the directions carefully and attach your code to the end of the assignment. There are three datasets required for this assignment. football1.csv This dataset is real (compiled from Wikipedia). I merely reduced the number of variables in it to make it easier to use. gdpcap.csv This dataset was compiled from two data sources. The `hig` variable is a measure of the level of honesty in the government, according to Transparency International. The source of the gdp per capita numbers was the CIA World Factbook. fraternity.csv This dataset is fabricated. The solutions are posted The `R` script is posted.
3	February 1, 2011 February 8, 2011	This assignment is the first assignment that looks at properly comparing means from more than two groups. Follow the directions carefully and attach your code to the end of the assignment. There is one external dataset required for this assignment. The other two datasets are internal datasets. gdpcap.csv This dataset was compiled from two data sources. The `hig` variable is a measure of the level of honesty in the government, according to Transparency International. The source of the gdp per capita numbers was the CIA World Factbook. OPEC membership was determined from the OPEC website. The solutions are posted The `R` script is posted.
4	February 8, 2011	This assignment continues examining how to test multiple means. It also beings having you think about the source of the data and what effect the source has on the conclusions you can make. As always, follow the directions carefully and attach your code to the end of the assignment. There are two external datasets required for this assignment: wheat2.csvI have included the script that I used to create the `wheat2` dataset. You may find it interesting to look through to see how datasets are created to test the statistical tests we use. biome2.csvThis dataset is fabricated. The solutions are posted The `R` script is posted.
5	February 15, 2011	This assignment continues examining how to test multiple means and multiple variables. There is but one question, but it is a comprehensive question. As always, follow the directions carefully and attach your code to the end of the assignment. There is one dataset required for this assignment: wheat3.csvI have included the script that I used to create the `wheat3` dataset. You may find it interesting to look through to see how datasets are created to test the statistical tests we use. The `R` script is posted.
6	February 22, 2011	Revised, 17 February 2011: This assignment continues examining how to test hypotheses. It does test categorical vs. categorical, but it also gives you an interesting problem with a few ways of determining the answer and has you determine which way is best. As always, follow the directions carefully and attach your code to the end of the assignment. There is one external dataset required for this assignment: sri2010pres.csvThis is the official results from the 2010 Sri Lankan presidential election. The source of this data is the Sri Lankan Department of Elections. The solutions are posted The `R` script is posted.
MEX1	March 1, 2011	Here is the First Midterm Examination. Read the examination thoroughly before you begin. If you have questions, please contact me. There are two external datasets required for this examination: sri2010pres.csvThis is the official results from the 2010 Sri Lankan presidential election. The source of this data is the Sri Lankan Department of Elections. beer1.csvThere are the (pseudo) results from a beer-tasting experiment I performed with the entire faculty of this university. The five beers tasted were Coors Light, Bud Light, Guinness, Olympia, and Widmer IPA. The faculty taster scored his or her beer on a scale of 1 to 5, with 5 indicating ambrosia and 1 indicating dog water. The solutions are posted to the in-class examination.
8	March 8, 2011	This assignment gives a few quick problems that will become important in the future. As always, follow the directions carefully and attach your code to the end of the assignment as an appendix. There is one external dataset required for this assignment: sri2010pres.csvThis is the official results from the 2010 Sri Lankan presidential election. The source of this data is the Sri Lankan Department of Elections.
9	March 22, 2011	This assignment gives a few quick problems that will become important in the future. As always, follow the directions carefully and attach your code to the end of the assignment as an appendix. There is one external dataset required for this assignment: ssm.csvthis dataset consists of state-level measurements for 34 ballot measure elections which limited single sex marriage rights. It was compiled from Wikipedia. The `R` script is posted.
10	March 29, 2011	This assignment gives a single, extensive problem dealing with some of the things we have been dealing with these past three weeks. Graphs need to be appropriate. Include the script as an appendix. There is one external dataset required for this assignment: afg2009pres.csv I am also providing the start of your script to help you get the data in the computer.
10x	March 31, 2011	Remember, this assignment is optional and replaces Assignment 10. Again, this assignment gives a single, extensive problem dealing with some of the things we have been dealing with these past three weeks. Graphs need to be appropriate. Include the script as an appendix. The pdf does actually link to a new description of the assignment, so you may wish to look at that. There is one external dataset required for this assignment: egy2011referendum.csvAdditional information about this data can be found on the Center for Electoral Forensics website. The `R` script is posted.
MEX2	April 5, 2011	Here is the Second Midterm Examination. Read the examination thoroughly before you begin. If you have questions, please contact me. There are three necessary datasets required for this examination: gdpcap.csvThis dataset was compiled from two data sources. The `hig` variable is a measure of the level of honesty in the government, according to Transparency International. The source of the gdp per capita numbers was the CIA World Factbook. crime.csvThis data file contains several variables measured in 1990 and 2000 on each US state and the District of Columbia. The sources for the variables you will need are the Federal Bureau of Investigation and the Bureau of the Census. xsd2011referendum.csvThis data file contains the vote counts for each county in South Sudan. The referendum question was “Shall we become independent of Sudan?” The source of this data is the official electoral entity in charge of this referendum in South Sudan, the Southern Sudan Referendum Commission. More information can be had on the Center for Electoral Forensics website. The solutions are posted to the in-class examination. The solutions are posted to the take-home examination. The `R` script is posted.
12	April 14, 2011	Here is the first assignment of the third section of the course. Please read the directions carefully. You have already had all of the necessary exposure to `R` commands to complete the assignment. For a refresher, review the analysis of variance scripts (and assignments). There is no external dataset required for this assignment. The data tables are provided in the assignment itself.
13	April 21, 2011	Here is an assignment that encourages (forces?) you to thin about experimental design. There is no computer work here. However, you will want to review your t-tests. There is no external dataset required for this assignment. Actually, there are no data for the assignment.
14	April 26, 2011	Here is the last assignment of the course — and it is optional. Please read the directions carefully. You have already had all of the necessary exposure to `R` commands to complete the assignment. For a refresher, review the scripts from this past couple weeks. There are four external datasets required for this assignment. None are new. All can be found on the datasets page. The `R` script is posted.
FEX	May 5, 2011 By 10:00 am	Here is the Final Examination. Read the examination thoroughly before you begin. If you have questions, please contact me. There are two datasets required for this examination: cdi2010pres2.csvThis data file contains the vote counts for each electoral division (Localite) for the two candidates (Gbagbo and Ouattara), along with totals and the number of votes rejected. The source of the data is the CEI for the Côte d'Ivoire. earmarks.csvThis file contains (for each university and year in the study) the amount of peer-reviewed funding and the amount of earmarks the university received. The data is from the Chronicle of Higher Education and the National Science Foundation. My comments on the final examination are posted. The `R` script I used is posted.