CJ 605 Spring 04 Advanced Statistics in Criminal Justice:
Sequence of Topics and Readings
DATE OF LAST UPDATE: 1/24/04
Sequence
The sequence of topics and readings, as best as I can
predict them at this point, appear below. All of this is subject to
change depending upon numerous factors, including el Nino. The
readings and assignments are for the week they are DUE.
You will see that next to each reading are some codes.
CD = on a CD that will be distributed. These are usually PDf or htm
files.
W = available as a linked file directly off the
website. Click and it will ask you to download. Then fire up Adobe
Acrobat Reader
For the main texts:
R&B = Raudenbush and Bryk
RBCC=Raudenbush, Bryk, Cheong and Congdon
For the recommended texts:
K&DL = Kreft and deLeeuw
S&B = Snijders and Bosker
|
Class Date |
Topics / Readings DUE on this week |
|
1/26 |
Current issues in neighborhood effects; neighborhood
effects and health effects; how to create an aggregate file in SPSS and
conduct your own contextual analysis; audit functions in secondary data
analysis; READ BEFORE THE FIRST CLASS MEETING and try to answer some of the questions:
QUESTIONS to consider while
you read |
|
2/2 |
Review of aggregation procedure and results;
understanding the aggregation problem; theoretical and statistical
implications; statistical power questions READ
QUESTIONS to consider while
you read |
|
2/09 |
HLM SUBMODEL 1: One-way ANOVA with random effects ROUND 2: intraclass correlation; the statistical test; t hinking about local sentiment READ:
RECOMMENDED:
QUESTIONS to consider while
you read |
|
2/16 |
HLM SUBMODEL 2: One-way ANCOVA with random effects; more thoughts about collective efficacy and reactions to crime and local commitment READ
RECOMMENDED: K&DL, 30-32 QUESTIONS to consider while you
read |
|
2/23 |
HLM SUBMODEL 2: One-way ANCOVA with random effects: ROUND
2 READ:
QUESTIONS to consider while you
read |
|
3/1 |
HLM SUBMODEL 3: Random coefficients regression model |
| 3/8 |
Daytona Beach Spring Break
There IS an assignment for next week! - BUT see memo of 3/12/04 |
|
3/15 |
HLM SUBMODEL 4: Means as outcomes regression: adding only
L2 predictors
RECOMMENDED: Duncan and Raudenbush (1999) (CD)
QUESTIONS to consider while you
read |
|
3/22 |
SOME ISSUES: Centering at Level 1 & 2; Intraclass correlation HLM FULL MODEL: Intercepts and Slopes as Outcomes (IASAO); what does it mean to predict varying slopes? READ:
QUESTIONS to consider while you
read |
|
3/29 |
The general probability model: Binary and count outcomes READ:
QUESTIONS to consider while you
read |
|
4/5 |
More on the full model: Conceptual and empirical questions: Varying slopes at LI; predicting LI slopes with LII variables. What does this mean? READ:
QUESTIONS to consider while you
read |
|
4/12 |
Residuals: Doing Diagnostics; Variables in the file; Plots you want to generate; Read:
QUESTIONS to consider while you
read |
|
4/19 |
Changes over time; implications for evaluation READ:
Recommended: Osgood W, Smith G (1995) Applying hierarchical linear modeling to extended longitudinal evaluations: The Boys Town follow-up study. Evaluation Review 19:3-28; Raudenbush (2001) Annual Review of Psychology (CD) |
|
4/26 |
If we get time: A host of last minute items: meta analysis via HLM; weighting; multiparameter tests PRESENTATIONS OF PAPERS |
|
5/3 |
PRESENTATIONS OF PAPERS; REVIEW LAST DAY OF REGULARLY SCHEDULED CLASSES: 5/3 |
|
5/10 |
5/10 Final, in-class exam; final papers due Final Examination Period: ; final version of paper due |