Chemometrics
A.Y. 2026/2027
Learning objectives
This Chemometrics course aims to give students the skills to design chemical experiments that effectively collect useful data. It also aims to introduce them to statistical and modeling techniques for data analysis using the R software. A key objective is to provide students with the skills needed to design and analyze experiments to evaluate the effect of factors on a response variable, highlighting the importance of randomization, replication, and blocking.
Expected learning outcomes
At the end of the Chemometrics course, the student will be able to:
Knowledge and Understanding: Demonstrate a solid understanding of the statistical principles underlying statistical analysis techniques (with particular emphasis on significance tests and the regression model) and experimental design.
Application: Design experiments using the principles of randomization, blocking, and replication. Correctly apply the appropriate statistical tests to evaluate the effect of two or more factors on a response variable, and regression models. Analyze and interpret the results of statistical analyses.
Communication: Communicate the results of statistical analyses effectively, both in written and oral form, using appropriate language and supported by clear graphs and tables.
IT Skills: Use the R software for data analysis, implementing the learned techniques and interpreting the outputs.
Knowledge and Understanding: Demonstrate a solid understanding of the statistical principles underlying statistical analysis techniques (with particular emphasis on significance tests and the regression model) and experimental design.
Application: Design experiments using the principles of randomization, blocking, and replication. Correctly apply the appropriate statistical tests to evaluate the effect of two or more factors on a response variable, and regression models. Analyze and interpret the results of statistical analyses.
Communication: Communicate the results of statistical analyses effectively, both in written and oral form, using appropriate language and supported by clear graphs and tables.
IT Skills: Use the R software for data analysis, implementing the learned techniques and interpreting the outputs.
Lesson period: Second semester
Assessment methods: Esame
Assessment result: voto verbalizzato in trentesimi
Single course
This course can be attended as a single course.
Course syllabus and organization
Single session
Responsible
Lesson period
Second semester
Course syllabus
1) Review of probability and statistics: random variables; Gaussian distribution; point estimation of the parameters of a probability distribution; the linear regression model and the least squares method for estimating parameters; the principal component analysis.
2) Reference distribution, the concepts of blocking and randomization. Hypothesis testing and confidence intervals.
3) The ANOVA technique for comparing k different treatments in a completely randomized design and in a randomized block design (complete and incomplete).
4) Two-way ANOVA and interaction between the factors
5) The 2-level factorial design
6) The fractional factorial design (if we have time enough)
7) The split-plot design (if we have time enough)
2) Reference distribution, the concepts of blocking and randomization. Hypothesis testing and confidence intervals.
3) The ANOVA technique for comparing k different treatments in a completely randomized design and in a randomized block design (complete and incomplete).
4) Two-way ANOVA and interaction between the factors
5) The 2-level factorial design
6) The fractional factorial design (if we have time enough)
7) The split-plot design (if we have time enough)
Prerequisites for admission
Basic knowldge in mathematics and linear algebra is required. It is desirable to have acquired the notions of probability and random variables, but not strictly necessary because they will be briefly recalled during the lectures.
Teaching methods
Theoretical concepts will be presented during lectures using a combination of whiteboard explanations and presentation slides. Furthermore, every lecture will include practical examples of statistical analysis, which will be demonstrated using the open-source statistical software, R.
Students are highly encouraged to participate and ask questions to clarify any doubts.
Additionally, to make the classes more interactive and effective, the instructor will occasionally propose questions and practical exercises to be solved in the classroom.
Students are highly encouraged to participate and ask questions to clarify any doubts.
Additionally, to make the classes more interactive and effective, the instructor will occasionally propose questions and practical exercises to be solved in the classroom.
Teaching Resources
Statistics for Experimenters: An Introduction to Design, Data Analysis and Model Building. By Box, George E. P; Hunter, William Gordon; Hunter, J. Stuart. New York : Wiley.
Notes on principal component analysis, written by the professor and available on the platform Myariel
Slides of the Course
Notes on principal component analysis, written by the professor and available on the platform Myariel
Slides of the Course
Assessment methods and Criteria
The assessment methods are designed to effectively verify both the theoretical knowledge and the practical data analysis competencies acquired by the students during the course.
* The standard exam consists of a 1.5-hour computer-based written test (paper will not be used). It includes 5 theoretical multiple-choice questions and 2 data analysis exercises to be completed using R software. The exam is open-book; students are permitted to consult their notes and course handouts.
* Alternative Assessment for Attending Students (First Exam Session Only)
Attending students have the option to be evaluated through a project-based continuous assessment. This option is available only during the first exam session and consists of the following steps:
1) Group Formation: During the first month of the course, students must form groups of 3 to 5 members.
2) Assignments and Reports: Throughout the course, each group must solve the exercises provided in the slides and perform the data analysis described in the "paper for project" (available on myAriel in the linear models folder).
The solutions must be compiled into PDF reports. Each exercise report must include the problem statement, the applied solution, and a detailed discussion with comments and interpretations.
Reports must be uploaded to myAriel according to the deadlines posted on the course forum.
Only one report per group needs to be submitted. Every report must clearly state the name, surname, and student ID number of all contributing authors.
3) Final Oral Presentation: During the first exam session, these students will give an oral presentation based on their submitted assignments. Two weeks before the exam, the professor will communicate which specific assignment each group will present. On the day of the exam, the instructor will ask each student in the group to present and discuss a specific part of the exercise or analysis (students may project the report itself or prepare slides for this purpose).
* The standard exam consists of a 1.5-hour computer-based written test (paper will not be used). It includes 5 theoretical multiple-choice questions and 2 data analysis exercises to be completed using R software. The exam is open-book; students are permitted to consult their notes and course handouts.
* Alternative Assessment for Attending Students (First Exam Session Only)
Attending students have the option to be evaluated through a project-based continuous assessment. This option is available only during the first exam session and consists of the following steps:
1) Group Formation: During the first month of the course, students must form groups of 3 to 5 members.
2) Assignments and Reports: Throughout the course, each group must solve the exercises provided in the slides and perform the data analysis described in the "paper for project" (available on myAriel in the linear models folder).
The solutions must be compiled into PDF reports. Each exercise report must include the problem statement, the applied solution, and a detailed discussion with comments and interpretations.
Reports must be uploaded to myAriel according to the deadlines posted on the course forum.
Only one report per group needs to be submitted. Every report must clearly state the name, surname, and student ID number of all contributing authors.
3) Final Oral Presentation: During the first exam session, these students will give an oral presentation based on their submitted assignments. Two weeks before the exam, the professor will communicate which specific assignment each group will present. On the day of the exam, the instructor will ask each student in the group to present and discuss a specific part of the exercise or analysis (students may project the report itself or prepare slides for this purpose).
Professor(s)
Reception:
Wednesday from 9:00 to 12:00
Via Conservatorio, III floor, Room n. 35