- Docente: Silvia Pacei
- Credits: 6
- SSD: SECS-S/03
- Language: Italian
- Teaching Mode: Traditional lectures
- Campus: Bologna
- Corso: Second cycle degree programme (LM) in Statistics, Economics and Business (cod. 8876)
Course contents
1. THE NON-SAMPLING ERROR
1.1. Sources of errors.
1.2. The “non-response” and its consequences.
1.3. Three types of non-response: a) errors in the list; b) total non-response; c) item non-response.
2. ERRORS IN THE LIST
2.1. Population, list and method of interview: main schemes for kind of list and method of interview.
2.2. Types of error in the lists: non-complete list; over-coverage in the list; double units in the list; list with grapes of units.
2.3. Methods to control for the errors in the list.
3. TOTAL NON-RESPONSE
3.1. Reasons for total non-response. Consequenses of total non-response.
3.2. How to prevent total non-responses or correct them during the survey.
3.3. Total non-response correct in the estimation phase: 1. Classes of adjustment for non-response; 2. Two-phase method; 3. Regression estimator; 4. Constrained-weighted estimator.
3.4. Non-response schemes and auxiliary variables selection.
4. ITEM NON-RESPONSE
4.1. Typologies of item non-response.
4.2. How to prevent the item non-responses.
4.3 Methods to deal with incomplete data: 1. Methods only based on respondents; 2. Weighting Methods; 3. Imputation Methods (Deductive Imputation; Imputation of the mean; Imputation from donator).
4.4. Imputation Methods for longitudinal surveys.
4.5. Comparative Analysis among imputation methods.
4.6. Multiple Imputation.
5. Examples of application in official surveys: Banca D’Italia sample survey on Italian households income; ISTAT sample survey on small and medium firms.
6. Introduction to the small area estimation problem.
SAS PROGRAMMING ON REAL OR SIMULATED DATASET.
Readings/Bibliography
Slides.
G. Nicolini; D. Marasini; G.E. Montanari; M. Pratesi; M.G. Ranalli; E. Rocco (2013). Metodi di stima in presenza di errori non campionari. Milano: Springer-Verlag Italia. Chapters 4, 5 and 6.
Teaching methods
Lectures and laboratory exercises using the SAS software.
As concerns the teaching methods of this course unit, all students must attend Module 1, 2 [https://www.unibo.it/en/services-and-opportunities/health-and-assistance/health-and-safety/online-course-on-health-and-safety-in-study-and-internship-areas] on Health and Safety online.
Assessment methods
Laboratory exam with eligibility, preparatory to the oral exam with a mark, to be taken in the same exam call.
The exam is aimed at verifying: the level of understanding and in-depth analysis of the topics, the ability to perform the relative logical-deductive connections, the knowledge of the basic vocabulary.
Office hours
See the website of Silvia Pacei