84609 - METODI DI CAMPIONAMENTO

Learning outcomes

At the end of the course the student knows how to manage complex sampling plans. She/he will be able to plan complex surveys and to analyze data with advanced statistical tools, to assess and communicate the uncertainty on the obtained estimates.

Course contents

Sampling in finite populations. Population and sample. Sampling plans and the random variables that manage the selection.

Finite populations and descriptive inference. Analytical inference and finite populations.

Inference in complex units (cluster sampling). Role of the intraclass correlation coefficient in cluster sampling.

The role of auxiliary variables for leaving simple random sampling.

Inference for complex units selected with varying probability.

Ratio and regression adjustment in sampling complex units. Approximated properties of ratio and regression estimators seen with respect to residuals.

Multistage sampling.

Sequential sampling and hypothesis testing in finite populations.

The sequential test of probability ratio: hypothesis testing on the parameter of a Bernoulli; hypothesis testing on the mean of a normal.

Use of R software to implement and create the sampling designs examined in the course

 

Readings/Bibliography

Downloadable lecture notes: Daniela Cocchi "Principi e Metodi di Campionamento (corso intermedio)", 2023

Lecture notes (slides) in pdf. 

All teaching material is available on the "Virtual learning environment" platform (https://virtuale.unibo.it/).

Additional useful readings

• Yves TILLé, Maria Michela Dickson, Giuseppe Espa, ELEMENTI DI CAMPIONAMENTO E STIMA DA POPOLAZIONI FINITE, Pearson Italia, 2020.
• P.L. Conti, D. Marella, Campionamento da popolazioni finite. Il disegno campionario. Springer-Verlag Italia 2012.

Teaching methods

• Lectures and computer exercises with R

Although attending lessons is not mandatory, it is strongly recommended.

Assessment methods

The assessment aims to evaluate the achievement of the following learning objectives:

• knowledge of the fundamental aspects of sampling from finite populations and sequential sampling;

• ability to properly use the statistical tools for implementing sampling plans and analyze the results;

The exam is written and consists of exercises to be solved. The time for the written test is two hours.

During the exam it is allowed the use of a form (maximun a protocol sheet), while it is not allowed to use textbooks or notes. A pocket calulator is necessary.


In the written test you will not be asked to program in R, but to comment and explain the R code present in the text of the exercise. It is allowed to consult the manuals of the R packages examined in the lectures.

Teaching tools

Slides in pdf and R-code of the solved examples .

Links to further information

https://www.unibo.it/sitoweb/michele.scagliarini/

Office hours

See the website of Michele Scagliarini