Preview Workflow

The CIM Courses system will be down temporarily undergoing routine maintenance.

### Last edit: Sun, 16 Aug 2015 16:40:22 GMT

Catalog Pages referencing this course
Programs referencing this course
Columbian College of Arts and Sciences
Forensic Science (FORS)
FORS
6225
Statistics for Forensic Scientists
Forensic Statistics
Fall 2015
3
Course Type
Lecture
None
No
No
Corequisites

25
Simone Gittelson
Frequency of Offering

Term(s) Offered

Are there Course Equivalents?
No

No
Fee Type

No

Statistics with a focus on forensic applications. Emphasis on the Bayesian approach. Logical, probabilistic statistical reasoning skills, and R software skills. Course content is the basis for an examination question on the comprehensive examination. Students must have taken an undergraduate statistics course before registering.
As a result of completing this course, students will be able to: 1. Apply the laws of probability to describe a set of events, understand the concept of odds and convert from probabilities to odds and vice-versa. 2. Describe the errors that occurred in historical cases (e.g., People v. Collins, Sally Clark) and the correct approach to interpreting the evidence in these cases. 3. Use R software to perform descriptive statistical analyses on data sets and plot common distributions (Binomial, Hypergeometric, Poisson, Beta, Normal, Student t). 4. Apply Fisher’s exact test and P-P plots to compare data sets from two different populations. 5. Derive and apply Bayes’ theorem. 6. Recognize and avoid logical fallacies (e.g., transposed conditional, defense attorney’s fallacy, ultimate issue error). 7. Distinguish between the different levels in the hierarchy of propositions (source, activity, offense). 8. Explain what a likelihood ratio is and assign a likelihood ratio for: a. DNA evidence in simple single source and paternity cases, b. evidence involving multiple stains/traces and multiple sources, c. database search results, d. activity level propositions for transfer evidence, e. continuous data (e.g., refractive index of glass). 9. Determine the optimal sample size in drug sampling. 10. Use R software to perform Bayesian statistical analyses for data following a common distribution.