WATCH FOR ANNOUNCEMENTS ABOUT : SCHEDULE CHANGES SAMPLE EXAM QUESTIONS FEEDBACK ETC.

COURSE  OVERVIEW

REQUIRED  MATERIALS

ASSIGNMENTS

WEB-ASSISTED  INFO

COURSE  TOPICS

 

MY OFFICE: 307K Stone Building  850-644-8778  OFFICE HOURS: Exceptions to be announced 1:00-3:00 P.M. Monday & Wednesday & by appointment slosh@garnet.acns.fsu.edu

FSU Stone Building  INSTRUCTOR: Professor Susan Carol Losh 126  Stone Building Monday & Wednesday 11:00-1:00 CLICK HERE  to find the Stone Building

My assistant for this course is Mr. Brandon Vaughn. He will assist you with assignments, assist me with grading, and will also be available prior to exams.
 

Brandon Vaughn OFFICE HOURS:

bkv03@garnet.acns.fsu.edu

PLEASE INFORM ME IMMEDIATELY IF YOU REQUIRE ANY ASSISTANCE WITH DISABILITIES!
 
 

I want to begin by tossing you a "curve ball" or a shock:

At this level, I DO NOT teach statistics.

I DO teach data analysis.

Although many of the topics covered are the same (e.g., hypothesis testing), the approach is very different. You will learn a lot about VARIABLES, what they are and what you can do with them. There will be some formulas but generally you won't have to memorize them (although you WILL need to memorize some symbols). This is a consumer-oriented approach to data. At the end of this course, I want you to be able to:

Do basic analysis on your own data, for example, for a Master's thesis, doctoral dissertation  or a conference paper.

Be able to read and understand basic data analysis in your field, for example, in a professional journal or conference paper.

Be able to understand basic data analysis, including charts, graphics and tables in regular media, such as a magazine or newspaper.

For many of you, I know that this is the only statistics course that you will ever take.

You come from an exceptionally  wide variety of major fields and schools or colleges at FSU.

Some of you wereDRAGGED here by your major professor or your program requirements, others have come joyously because this is the first of several quantitative courses that you anticipate electing--or the middle course of several you have taken and plan to take.

Understanding complex statistics really does require courses in calculus, linear algebra, and other college-level math courses to see "the big picture." And I think this kind of math background is probably necessary if you want to teach statistics.

But you don't have to be able to build a Digital Video Player to program a movie. And you do not have to be a mathematician to understand data analysis and apply it appropriately, or to understand whether someone has chosen the appropriate statistical tools and applied them correctly in a  conference presentation or an article.

You must, however, understand what the concepts MEAN.

I will have you analyze data via computer to illustrate and to recognize these constructs.

You will learn the Berkeley "Survey Documentation and Analysis" (SDA) system ONLINE, that is, on the Internet, to do so. The SDA is an award winning sytem developed at the University of California, Berkeley, and used by many federal government and university systems to access and analyze many sets of archival data so it can be generalized. It is eye-blinkingly rapid and simple to use. Because we realize this is a new experience for many of you, I and Brandon will be here to help you.

The important thing is not "can you program right" but can you meet:
 

Understand the kind of data that you have?

Definitions of nominal, ordinal, interval, and ratio data are easy to memorize. Discovering how these concepts correspond to the questionnaire items in your dissertation survey or the materials in your ethnography is typically difficult.

Understand the appropriate analytic tools to use?

I ALWAYS emphasize staying within your own understanding. Better to use a more simple technique that you understand thoroughly than a "fancy one" that you do not. Can you detect when the author of a conference paper used a statistical tool that made absolutely no sense?

Understand what your results mean?

For example, can you look at your results--or those in a journal article?--and comprehend whether they are an accident--a random and probable fluxuation from a sample finding--or whether they designate something that may be statistically real?

If your results are "real," how strong are they? When we study hundreds or thousands of cases, our results are typically stable, they won't vary much from sample to sample--but they could be trivial and substantively meaningless. How do you know if your results are at least moderately strong, or so weak that you would be embarrassed to see them published in the Tallahassee Democrat (or anywhere else)?

Understand where your results fit in the causal scheme of your own and others' research?

It is insufficient to simply report results, results are interpreted. Did your original substantive hypotheses receive any support? Were they unequivocally rejected? Did they make sense in your causal system?
 
 

ELEMENTARY CAUSAL EXAMPLE 101: Did you know?  Looking across months of the year, ice cream consumption and criminal assaults rise and fall together.  Students with lower grades tend to smoke more cigarettes. Does eating ice cream cause criminals to assault others? Does smoking cigarettes literally stupify you? Stay tuned. Statistics never, ever "prove causality." However, certain patterns of results will be more consistent with hypotheses than others. And, you will discover, certain numeric patterns of results can be the same for "real" or substantive findings--and for fake or "spurious" findings.

Previous experience with research methods and statistics may be helpful, but is definitely not essential.
 

Alan Agresti and Barbara Finlay, Statistical Methods for the Social Sciences (THIRD EDITION). Upper Saddle River, NJ: Prentice Hall, 1997. ISBN = 0-13-526526-6

Darrell Huff, How to Lie with Statistics. New York: W.W. Norton Company, new printing: 1993 (original printing 1954). ISBN = 0-393-31072-8

ALL MY COURSE LECTURES will be placed on the Internet and linked in with each course topic.

Course guides will be keyed to the readings. See the top of each Guide as it is posted.

Although I may not cover all the material in each one, you are responsible for ALL the material in each guide. That is why they are on the Internet.

I recommend that you read my online guides FIRST. They emphasize the portions of the material that I think are the most important for this course. I also think it may be easier for you to understand the text after you have read the associated guide.

Some of the material in the guides will be covered during class. However, class time will also be used for instruction related to each assignment, demonstrations, exam review, and assignment and exam feedback.

Below is information about  assignments, exams, due dates, and course weights.

There will be three equally weighted exams, each about one hour.Each exam counts 25 percent toward your final grade. While each exam will focus on the immediately prior units, be advised that much of the this material is cumulative in nature. In addition, if a concept or concepts appears to give considerable trouble in one exam, I will probably include questions addressing that concept on the next exam. Exams will be a mix of short answer, short essay and multiple choice and have a strong problem-solving orientation.

Assignments are designed and weighted so that if you make a mistake, it will not hurt your final grade to a large extent, and mistakes can then be corrected on the exams, which weight more heavily. I have had students "borrow" another student's homework. They receive an "A" on the homework, then flunk the exams. That is a very BAD strategy.

All five assignments put together will count a total of 25 percent toward your final grade.
 
 

Assignments have several primary foci:

To gain first-hand familiarity with several basic types of data analysis. While the most immediate use is for those analyzing data for a paper, thesis or dissertation, consumers will gain knowledge too. With some experience in data analysis, you will find that you will be a more knowledgeable data consumer.

To help develop your basic analysis and results interpretation skills. For example, nearly every assignment has you explain in words what your results mean.

To alert you to common problems that occur with different kinds of statistical analyses and ways to solve these problems.
 

OUR EXAMS WILL BE CLOSED-NOTE, CLOSED BOOK. Here are some of the things you can expect to see on exams:
 
 

Commonly used symbols, such as    or	Identifying the measurement level of a variable
Putting variables in causal order	Identifying the appropriate statistical test to use

Interpreting computer output, for example:
 

Identifying the correct measure of central tendency for your data	Using a confidence interval to see if your results are "statistically significant"
Selecting the appropriate correlation coefficient for your data	Assessing the strength of a correlation

If you don't understand the concepts in this material, a mountain of books and notes won't help you (although you may feel more secure). If you do understand them, it is unlikely you will need notes or books for the exams.
 
 

A NOTE ON ASSIGNMENT DUE DATES

 

CLICK HERE FOR GRADING CONSIDERATIONS

While each assignment focuses on unit readings and other course requirements, material on data analysis is cumulative by nature. For example, the level of measurement in your variables is considered throughout.

I use plus and minus grading, throughout and for final grades. Improvement over the course of the semester is considered in grading, and exams weight more heavily  toward your final grade than exercises.

If I think you are having trouble with the material, I will alert you immediately and I expect you will seek remedial help as quickly as possible. If you receive such an alert, please take it very seriously. Do not tell me that you "really understand the material" and fail to seek help. I issue such alerts because the work makes it obvious the student DOES NOT understand the material.

Our course is WEB assisted through the CourseInfo/Blackboard 6.0and WEB-MC  systems at FSU. You MUST be registered for edf5400-01 to access our Blackboard site. To access our course through Blackboard, here is what to do. Go online to:

(You will be forwarded to the new, more complicated url. The above works and is easy to remember.)
Enter your GARNET username (USERNAME ONLY!) and password to log in. For example, I would enter "slosh" ONLY and omit the "@garnet.acns.fsu.edu" part. Then click on “DES/INF STATSTCS APP” to enter our site.

If you DON'T have a garnet account, you need to get one NOW. Go to the Academic Computing and Network Services website (address below) and follow the links to register online for your garnet account at FSU.

Scroll down to the "Computer Accounts" link at acns to start an email account if you don't already have the garnet or mailer account that is required to log into BlackBoard.

Our course can also be accessed directly through the WEB-MC system. Go to:

(That's THIS WEB address.)

You can link to nearly all the course sites from this central location.
 
 

I will use WEB-assist for several course features:

• All lectures will be available online and linked with course topics. Objectives will be posted for each section of the course as the semester progresses.

• We have a communications section in Blackboard which allows course members to post questions and initiate discussion. This can be particularly useful immediately prior to exams.

• Assignments will be posted to our course site.

• Exam coverage and sample questions will be posted prior to exams.

• Generic feedback on assignments and exams will be posted. Please read this feedback before you ask questions about your personal written work because these sites may answer many of your questions.

• I DO NOT ANSWER QUESTIONS ABOUT PERSONAL ASSIGNMENTS OR EXAMS DURING CLASS. PLEASE DO NOT EVEN ASK. I don't answer questions about personal assignments or your exam during class break either. There is not enough time for me to thoroughly read over and ask you questions about your answers. This is not fair to you, to me, or to your classmates. However, I will be glad to make an appointment to discuss your assignment or exam with you AFTER you have read the feedback sites.

• Announcements on the main Blackboard page will alert you to any changes in the nature of assignments or to the schedule for the syllabus, course deadlines, or class meetings. Also watch the top of the sites for such announcements.

• On line databases will be linked with our site. We will concentrate on several online archives. We will examine the year 2002 General Social Survey the most. The General Social Survey is an enormous set of data on individual characteristics, from intelligence tests to traumatic personal events to opinions on many topics, collected using in-person interviews with a representative cross-section of the American general public. Although it begins in 1972, we will use the year 2002 data.We will also use some National Science Foundation data on computer and Internet use.

DATES	TOPICS TO BE COVERED	ISSUES AND OBJECTIVES
May 10-17	Conceptual and operational variables. Independent, intervening and dependent variables Discrete and continuous variables Levels of Measurement	Navigating our course WEB sites What are the characteristics of a variable? Causality 101 What are nominal, ordinal, interval and ratio variables?
May 26	ASSIGNMENT 1 DUE	Basic univariate frequencies, recoding data, and  percentage table construction
MAY 31	MEMORIAL DAY HOLIDAY	UNIVERSITY CLOSED
May 19-June 7	Everything you wanted to know about a single variable Tabular arrays Basic presentations of data Measures of central location & variation Normal curve 101 Confidence intervals Graphic displays	How to construct a univariate table Basics of the SDA online system Percents, rates, change over time, ratios Measures of central location & variation Charts, graphs, icons
June 7	ASSIGNMENT 2 DUE	Central tendency and variation
June 14	EXAM ONE REVIEW	Univariate basic statistics
June 16	EXAM 1	COVERS MATERIAL THROUGH GUIDE 3
June 9-23	Constructing Bivariate Tables Is an apparent relationship "Real" or "Accidental"? Classical Hypothesis Testing Substantive Significance Selecting Measures of Association Differences across groups	Learning the "pieces" of a Table Bivariate Crosstabulations Introduction to classical hypothesis testing Chi-Square Correlation coefficients:,, and  "PRE" issues T-tests for independent groups
	EXAM ONE FEEDBACK
June 30	ASSIGNMENT 3 DUE	Bivariate Tables Zero Order (Bivariate) Correlations T-test Practice Hypothesis Testing
June 28-July 14	Measures of Association and Tabular Control  Multivariate Tables  The Concept of Statistical Interaction  Causal Issues in Non-experimental Data	Three-way Crosstabulation Tables What's the Role of "Control Variables"? Extraneous,Spurious, Intervening Relationships Recognizing Interaction in Tables
JULY 5	FOURTH OF JULY OBSERVED HOLIDAY	UNIVERSITY CLOSED
July 7	EXAM TWO REVIEW	Basic bivariate statistics
July 12	EXAM TWO We can do a short review before also	COVERS MATERIAL THROUGH GUIDE 5
July 14-26	Basics in Multiple Regression and Correlation	What happens with at least two independent variables? Multiple R Partial Correlations & Regression Coefficients Metric and Standardized Coefficients Confidence Intervals and Statistical Significance Interpreting Regression Analysis
July 19	ASSIGNMENT 4 DUE	Three-Way Crosstabulation Tables With a Control Variable Causality Issues in Non-Experimental Data
	EXAM TWO FEEDBACK
July 28	ASSIGNMENT 5 DUE	Working with multiple regression
July 28-August 2	Sampling and Probability	Probability and Non Probability Samples Issues with Sample Weights
August 2	EXAM THREE REVIEW	Very basic multivariate statistics
August 4	EXAM THREE	COVERS MATERIAL THROUGH GUIDE 9

A LECTURE (AND ASSOCIATED MATERIALS) WILL BE LINKED WITH EACH TOPIC AS THE SEMESTER PROGRESSES.
 
 

EDF 5400 READINGS AND ASSIGNMENTS

This page created with Netscape Composer
and is best viewed with Netscape Navigator
600 X 800 display resolution.
There may be some minor changes as the semester progresses.
Your patience is appreciated.
Susan Carol Losh
May 5, 2004