(in Polish) Podstawy informatyki i chemometrii 0600-S1-CTZ-PIiC

Lecture topics:
1. Introductory lecture.
2. Introduction to statistical analysis of experimental data, significant digits (figures), statistical analysis of random error, the uncertainty of measurement, type B evaluation of uncertainty.
3. Propagation of uncertainty, type A evaluation of uncertainty, combined standard uncertainty.
4. Linear regression – least square method, weighted linear regression, analysis of residuals, linearizing transformations.
5. Linear regression – least square method, weighted linear regression, analysis of residuals, linearizing transformations.
6. Nonlinear regression – polynomial equation fitting, multiple linear regression analysis, regression coefficients, selecting variables – stepwise procedures.
7. Numerical integration, integral and geometric interpretation, rectangle method, trapezoidal method, Simpson’s rule method, Gauss–Legendre method.
8. Fundamentals of numerical solving of differential equations, Euler method, Runge–Kutta method, Milne method (predictor-corrector)
9. Methods for solving algebraic equations, bisection method, secant method (regula falsi), tangent method (Newton-Raphson).
10. Methods for solving systems of linear equations, Matrix calculus – fundamentals, Cramer method, Gauss-Seidel method, Gauss-Jordan elimination method, Newton-Raphson method for nonlinear algebraic equations.
11. Introduction to chemometrics (definition, range of applications, basic issues: measurement planning, data collection, data control and processing, visual analysis, factor analysis, model regression , classification, similarity analysis).
12. Design of experiments (optimality of the plan, principles of creating a regression model, factorial designs).
13. Principal component analysis (PCA) and partial least squares (PLS) methods. Determination of the number of significant components, analysis of the object and variable space, examples.
14. Optimization methods, method of changing a single parameter, random walk method, simplex method, variable-size simplex, expansion, contraction, optimization criteria.
15. Monte Carlo methods - integration and simulation, pseudorandom number generators, Monte Carlo integration, Monte Carlo simulation.

Laboratory:
Exercises with the use of appropriate computer programs (MS Excel, IBM SPSS) are concerned with the following issues:
Exercise no. 1. Statistical analysis of experimental data, the mean, standard deviation, dispersion measures - practical, classic problem-solving.
Exercise no. 2. Regression analysis, application of the linear regression to calculate the calibration curve - practical, classic problem-solving.
Exercise no. 3. Multiple linear regression - practical, classic problem-solving.
Exercise no. 4. Design of experiments - full factorial designs.

Total student workload

Contact hours with teacher: - participation in lectures – 15 hrs - participation in laboratory classes – 15 hrs Self-study hours: - preparation for laboratory classes – 10 hrs - preparation for test/ examination - 8 hrs - consultations with an academic teacher – 2 hrs Altogether: 50 hrs (2 ECTS)

Learning outcomes - knowledge

W1: Knows and understands selected numerical methods used for chemical calculations K_W04 W2: Knows and understands the methods used for the analysis and interpretation of statistical data K_W05

Learning outcomes - skills

U1: Uses MS Excel and IBM SPSS in chemical and statistical calculations as well as for creating charts K_U05 U2: Applies selected statistical methods to the analysis of experimental data K_U05 U3: Uses selected numerical methods to solve problems in the field of exact sciences K_U04

Learning outcomes - social competencies

K1: Is aware of the need to conscientiously and accurately perform each task K_K03 K2: Is aware of the level of his knowledge and skills, the need for continuous training and personal development K_K05

Teaching methods

Lecture: Expository teaching methods: informative (conventional) lecture) Laboratory: Exploratory teaching methods: Practical, classic problem-solving

Expository teaching methods

- discussion
- informative (conventional) lecture

Exploratory teaching methods

- practical

Type of course

compulsory course

Prerequisites

Basic knowledge of MS Excel application, high school course in math.

Course coordinators

Piotr Szczepański

Assessment criteria

Assessment methods:
lecture - K_W04, K_W05, K_U04, K_U05
exercises - K_W04, K_W05, K_U04, K_U05

Assessment criteria:
Lecture: written exam in the form of a test; required threshold for a satisfactory grade - 50%, 61% - sufficient plus, 66% - good, 76% - good plus, 81% - very good.
Classes: graded credit on the basis of laboratory exercises and one test; required threshold for a satisfactory grade - 50%, 61% - sufficient plus, 66% - good, 76% - good plus, 81% - very good.

Exam problems:
1. Introduction to statistical analysis of experimental data, significant digits (figures), statistical analysis of random error, the uncertainty of measurement, type B evaluation of uncertainty, propagation of uncertainty, type A evaluation of uncertainty, combined standard uncertainty
2. Linear regression – least square method, weighted linear regression, analysis of residuals, linearizing transformations
3. Nonlinear regression – polynomial equation fitting, multiple linear regression analysis, regression coefficients, selecting variables – stepwise procedures
4. Numerical integration, integral and geometric interpretation, rectangle method, trapezoidal method, Simpson’s rule method, Gauss–Legendre method.
5. Fundamentals of numerical solving of differential equations, Euler method, Runge–Kutta method.
6. Methods for solving algebraic equations, bisection method, secant method (regula falsi), tangent method (Newton-Raphson)
7. Optimization methods, method of changing a single parameter, random walk method, grid search method (factorial design), rules for creating a regression model, experimental design, the simplex method, variable-size simplex, expansion, contraction, optimization criteria
8. Monte Carlo methods - integration and simulation, pseudorandom number generators, Monte Carlo integration, Monte Carlo simulation.

Bibliography

1. P. Szczepański, Chemistry IT, Toruń 2012.
2. M. Otto, Chemometrics. Statistics and computer application In analytical chemistry, WILEY-VCH, 2016.
3. Guide to the Expression of Uncertainty in Measurement, ISO, Switzerland 1995.
4. D.W. Rogers, Computational chemistry using the PC, John Wiley & Sons. Inc., 2003.
5. P. Gemperline, Practical guide to chemometrics, CRC Press, 2006
6. J. N. Miller, J. C. Miller, Statistics and chemometrics for analytical chemistry, Pearson Education Limited, 2018.

Additional information

Additional information (registration calendar, class conductors, localization and schedules of classes), might be available in the USOSweb system:

Description of 0600-S1-CTZ-PIiC in USOSweb