This is the home page for Basic Data Analysis for the Master Programs in Management and Policy Planning.
Please, please, please let me know at the help address (not at "data-hw at turnbull") if there are any problems with any materials or links posted here.
Older news has been moved to Previous updates.
Wed Jun 26 18:48:00 2013
Mon Jun 24 16:32:12 2013
Past examinations available:
Final examinations are comprehensive, that is, 30-50% of the final examination is related to the first part of the course.
Thu Jun 20 11:42:55 2013
Thu Jun 20 11:09:02 2013
Thu Jun 6 19:45:26 2013
Thu May 30 11:12:00 2013
Thu May 23 15:04:46 2013
Thu May 23 03:19:07 2013
Thu May 9 17:54:53 2013
Past examinations available:
Final examinations are comprehensive, that is, 30-50% of the final examination is related to the first part of the course. The questions that might be relevant to this midterm are not identified, however.
Thu May 2 11:46:44 2013
Thu Apr 25 03:53:45 2013
Thu Apr 18 16:23:05 2013
Thu Apr 18 15:28:28 2013
Thu Apr 18 13:45:49 2013
Thu Apr 18 04:00:00 2013
Thu Apr 11 16:06:05 2013
Thu Apr 11 13:40:18 2013
Thu Apr 11 03:59:29 2013
This is a first course in data analysis for master's students in management and policy studies. This is not a technical course in statistics; for that, take (e.g.) Professor Kanazawa's course. The focus is on (1) understanding the relationship between behavior of decision-makers and the statistics we collect about their behavior, and (2) using those statistics to make inferences about motivation and predictions of future behavior.
Students passing this course are expected to be able to collect data, generate distributions of data values, and compute certain simple statistics from that data. For more complex computations, computers will be used for the analysis, including regression analysis and hypothesis testing. Interpretation of the results is emphasized, not their calculation.
See Links to Lecture Notes and Links to Homework Assignments for schedule information.
| Stephen Turnbull, Associate Professor | ||
|---|---|---|
| Graduate School of Systems and Information Engineering | ||
| Room | Phone | |
| Office | 3F1234 | 53-5091 |
| Lab | 3E401 | 53-5175 |
| turnbull@sk.tsukuba.ac.jp | ||
| Home Page | http://turnbull.sk.tsukuba.ac.jp/ | |
| Schedule | Office hours: Th 5th period at 3E401, or by appt. Graduate students are welcome to drop in any time, but I reserve the right to say "not now" outside of scheduled office hours. See my schedule page for more information about where to find me when. |
|
| 経営政策プログラム ／ Business Administration and Public Policy | |
|---|---|
| データ解析基礎 ／ Basic Data Analysis | |
| Catalog No. | 01CD103 |
| Day/Time | Thursday, 3rd & 4th (12:15--15:00) |
| Room | 8A108 |
| Home Page | http://turnbull.sk.tsukuba.ac.jp/Teach/DataAnalysis/ |
| mailto:data-help@turnbull.sk.tsukuba.ac.jp | |
| Recommended texts | Freedman, Pisani & Purves, Statistics (4th ed.), New York: W. W. Norton, 2007. Hardback, special order, at Maruzen, near University Hall. (Maruzen won't stock foreign books any more.) Hardback, new, at Amazon Japan. Paperback, new, at Amazon Japan. Hardback, new, at Amazon (US) (about shipping). Paperback, new, at Amazon (US) (about shipping). Used copies also available from Amazon. 4th edition is preferred because exercises change a lot, but 3rd edition probably is similar. |
Kline, Principles and Practice of Structural Equation Modeling, New York: Guilford Press, 2011. Amazon links will be posted later. |
|
Maddala and Lahiri, Introduction to Econometrics (4th ed.), New York: Wiley, 2009. Amazon links will be posted later. |
|
Amemiya, Introduction to Statistics and Econometrics, Cambridge, MA: Harvard U. Press, 1994. Amazon links will be posted later. |
|
Note: The dates in the table below are inaccurate.
Note: I have updated the schedule of topics, but this is not yet final. Also, the lecture notes are more less in order, but the topics treated in the notes may correspond to an earlier or later date than described here.
| No | Date | Link |
|---|---|---|
| 1 | April 11 | Introductory remarks. |
| 2 | April 18 | Distributions, histograms, and location. |
| 3 | April 25 | More statistics: dispersion, skewness, kurtosis. |
| 4 | May 1 | The normal distribution. |
| _ | May 3 | Golden Week holiday |
| 5 | May 10 | Probability and probability distributions. |
| 6 | May 17 | Statistical inference. Confidence intervals and hypothesis testing. |
| 7 | May 24 | Midterm examination. |
| 8 | May 31 | Correlation. |
| 9 | June 7 | Regression analysis. |
| 10 | June 14 | Regression analysis. |
| 11 | June 21 | Special models. |
| _ | June 28 | Final examination. |
The homeworks have not been updated and refer to earlier years. You may wish to download them to get an advance look at them, but be aware that you should make sure you have this year's edition before submitting homework!
| Homework | Link |
|---|---|
| _ | These links are untested and may not work! |
| 1 | Homework 1: Variable Types |
| 2 | Measurement 1: Creating a Data Set |
| 2 | Homework 2: Working with Distributions |
| 3 | Homework 3: Averages and Probabilities |
Please check this space for updates about studying for the final.
Latest update: Sat Jun 23 03:29:53 2012
Fri Jun 22 23:28:08 2012
Fri Jun 22 02:43:10 2012
Thu Jun 21 10:24:10 2012
Thu Jun 14 11:46:01 2012
Thu Jun 7 11:47:18 2012
Thu May 24 13:40:21 2012
Wed May 23 04:30:36 2012
Thu May 17 11:06:28 2012
Thu May 17 03:25:33 2012
Thu May 10 01:53:16 2012
Tue May 1 18:24:56 2012
Tue May 1 13:39:39 2012
Tue May 1 01:50:59 2012
Thu Apr 26 04:21:49 2012
Thu Apr 19 15:27:49 2012
Thu Apr 12 11:27:05 2012
Last update: Mon Jun 27 22:52:49 2011
Mon Jun 27 18:06:59 2011
Mon Jun 27 18:04:32 2011
- Past examinations (I will try to update these with answers):
- 2009 Final Exam (no answers).
- 2010 Final Exam (no answers).
- 2009 Midterm Exam (no answers).
- 2011 Midterm Exam (no answers).
- Errors in the 2011 midterm (full of mojibake, and removed).
- Comments on a midterm (not relevant, and removed).
- Information about review session (for 2010 final exam).
Mon Jun 27 00:30:12 2011
Updated my schedule page.
Homework 8 and Homework 9 posted as separate documents. The CSV files needed are Section1All_csv.csv and US-GDP-1947.1-2010.1.csv.
Note: I thought that it was confusing without numbers, so I've numbered the questions in each homework. If you have not yet submitted your reports, please download these and refer to the question numbers in your reports. If you have already submitted your report, you do not need to resubmit.
This renumbering will affect the Lecture 10 notes. I also corrected a few typos in that lecture. You may wish to download the notes again.
tables2.csv is a set of tables in CSV format (comma-separated, Shift-JIS coding) that may be of some use in homework.
Fri Jun 24 22:31:36 2011
Thu Jun 23 03:19:23 2011
Tue Jun 21 11:15:50 2011
Thu Jun 16 10:14:31 2011
Thu Jun 9 16:59:08 2011
Thu Jun 9 09:46:44 2011
Thu Jun 2 23:04:38 2011
Thu Jun 2 15:19:10 2011
WARNING: There is an error in several recent homework assignments. The address homework@turnbull.sk.tsukuba.ac.jp is given, but this address is a cut-and-paste error. Do not use this address; you will get an error. Use the address data-hw@turnbull.sk.tsukuba.ac.jp.
There is a less important error, the word "random" is missing in Problem 1 of Homework 6. These errors will be fixed this evening, and the homework reposted.
Thu Jun 2 10:33:25 2011
Thu May 26 15:05:36 2011
Thu May 26 11:40:25 2011
Thu May 26 11:23:45 2011
Tue May 24 23:39:38 2011
Tue May 24 21:13:47 2011
Tue May 24 20:34:21 2011
Tue May 24 12:44:14 2011
Thu May 12 02:55:20 2011
Tue May 3 01:25:44 2011
Thu Apr 28 02:27:01 2011
Thu Apr 21 03:19:20 2011