Assignment 5: Archives & Online Databases

EDF 5481 READINGS
AND ASSIGNMENTS

ASSIGNMENT 5
WEB-BASED DATABASES

DUE BY 4 PM MONDAY DECEMBER 9

OVERVIEW

EDF 5481 METHODS OF EDUCATIONAL RESEARCH
INSTRUCTOR: DR. SUSAN CAROL LOSH
FALL 2002

TURN-IN LOGISTICS

PRELIMINARY INFO

THE ASSIGNMENT

POINTS TO CONSIDER

GUIDE 1: INTRODUCTION
GUIDE 2: VARIABLES AND HYPOTHESES
GUIDE 3: RELIABILITY, VALIDITY, CAUSALITY, AND EXPERIMENTS
GUIDE 4: EXPERIMENTS & QUASI-EXPERIMENTS
GUIDE 5: A SURVEY RESEARCH PRIMER
GUIDE 6: FOCUS GROUP BASICS
GUIDE 7: LESS STRUCTURED METHODS
GUIDE 8: ARCHIVES AND DATABASES

REFERENCE THE ONLINE DATABASES EXPOSITORY WEB SITE:

THAT GRADING THING
REVIEW HOW GRADES ARE CALCULATED HERE:

LOGISTICS

This assignment is due Monday, December 9, 2002 BY 4 PM.

HARD COPY please!

This entire assignment can be completed in approximately 3 pages.

Since this assignment is due finals week, NO LATE PAPERS ARE ALLOWED.

WHAT

For this assignment, you are to locate an online database (i.e., on the Internet). THE DATABASE YOU CHOOSE MUST BE ON THE WEB.

The database may either be:

(1) Files of data that can be accessed OR

(2) Sets of tables with accompanying text (see the tables in Science and Engineering Indicators 2002 link for an example) that could be used to construct a new datafile.

You will need to research your database to learn as much as possible about it.

For example, check links on the site, or on the sponsoring agency's site, to see whether a tutorial is available on how to use data, and how to use the tutorial if so. (The tutorial may be called other things such as a "User's Manual".)

See what kinds of analyses can be done with the data (e.g., frequency distributions or two-way crosstabulations; comparing one institution with another). The site should give you this kind of information if it can be done. Does the site have a data analysis package (such as the SDA system or some other simple analytic system) built into it so that users can analyze data online?

See whether data or tables can be downloaded into EXCEL, SAS, SPSS, or some other type of spreadsheet file.

Learn whether data may be obtained through more conventional sources (e.g., on CD-Rom for SESTAT or the General Social Survey).

Check alternative sources (e.g., The Digest of Educational Statistics, the FBI Uniform Crime Reports, the General Social Survey Codebook) to see whether variables have been defined or coded consistently over time.

Exploring the site should give you a lot of this information, such as whether data can be downloaded, tutorials, whether there is a charge for the data, whether the user needs any kind of license, types of online analysis available, alternative ways to access or buy the data, etc.

If you can't find out any of this information, you definitely want to note these omissions in your paper!

If the dataset is international, please be sure that information is also available in English, because the archive will become part of a resource for the entire department!

Find out as much as you can because you are going to tell the novice researcher (that's me, in this case) what you know about these data!

Consider exploring some of the sites on the course Online Database page for practice to see some of the kinds of information available about these online archives.

Examine the "hunting hints" in Guide Eight for where you can start looking. CLICK HERE

THE ASSIGNMENT

Now that you have located an online database and explored it, here's what you provide for me:

1. The name of the archive

2. The url or "web address" home page of the archive

3. An overall description of the archive including:

The unit of analysis(an individual, as in the SESTAT data? an organization, as in the Web CASPAR data? A time point in a country or state? Tables covering time points, variables or countries?)

The overall types of variables in the archive (give a few examples)

The time framecovered by the archive (average school FCAT scores for 1998-2001? The General Social Survey from 1972-2000?)

The geographic frame covered by the archive (state? local? United States? international?)

The sponsor(s) of the archive (e.g., NSF? NCES? United Faculty of Florida?)

How the archive came to be

The sources of the data (collected especially for the archive, such as IPEDS? compiled from other sources such as Web CASPAR?)

If any of this information is unavailable, let me know in your paper.

4. Any available sites/pages that describe the database (AND, it is perfectly OK to cut and paste from these sites to answer any of the points in question 3). These would include questionnaires or coding instructions or instruments (e.g., the 2001 survey questionnaire for the Public Attitudes toward Science study which is linked to Guide 5 on Survey Research).

5. The presence of any kind of tutorial link or page that informs the reader how to access OR use the database (OR both).

6. How are the data available? Ready for online analysis? Available for download into your computer? In .pdf format tables? Are there alternative ways to obtain the data (such as CD-Rom?)? If so, how can the data be obtained?

7. Given your best knowledge, what kinds of problems may occur when a novice tries to use the data? How do you find out this one? Do some basic analyses, such as frequency distributions and try it out if you can! For example, through using the data for Statistics in Spring 2002, I discovered the famous Census "Falling through the NET" dataset was riddled with mispunches (they interviewed three year olds; sizable data was missing on race and ethnicity, for example).

HELPFUL HINTS TO CONSIDER FOR #7

Were the data gathered over time by different agencies or principal investigators? If so, changes in variables, definitions, or coding may have occurred.

Was there a switch in methodologies? For example, did one part of the archive use telephone surveys and another part use in-person interviews?

How far back does the data series extend? The longer the series, the more likely you are to encounter strange alphabetic and non-alphanumeric codes, or inconsistencies in definitions or measures.

Were data compiled from different agencies into a single archive? Again, check for consistencies in definitions (even of the same variable!) across agencies.

Were there changes in definitions (e.g., "Failing Schools") over time? Can you incorporate these somehow when you study the archive?

See if the description of the archive notes any problems or missing information (Unfortunately, I wouldn't count on this one; it's embarassing to the agencies involved--or people may just not know.)

IMPORTANT!

Remember that any original problems when the data were first gathered will STILL be there when the data are archived. See what you can find out about issues with question format, sampling, coding categories, and other sources of bias and random error. Sometimes (the General Social Survey) there will be considerable information about entities such as response rate, sometimes there is not.

Always remember this classic cliché: do the best you can with what you got.

THE "IT'S NOT AN IDLE EXERCISE" DEPARTMENT

As you recall, our materials remain on the Internet, probably for a year, or more.

Even though you cannot access the Blackboard/CourseInfo system once you are no longer registered for EDF5481, virtually all the pages will remain on the WEB-MC server and thus, they can be pulled up in full-screen format all-year.

The online database Web site will be amended to include your databases this Spring.

EDF 5481 READINGS AND ASSIGNMENTS

OVERVIEW

ONLINE DATABASE MENU

November 24 2002.
This page was built with Netscape Composer.
It is best displayed in Netscape Navigator,
600 X 800 display resolution.
Susan Carol Losh