Advanced data analysis in analytical chemistry

Source: https://www.su.se/english/education/course-catalogue/kz/kz7106?semester=VT2026&eventcode=57026 Parent: https://www.su.se/english/education/course-catalogue?q=&internationalStudents=%5B%22true%22%5D&forcedReasonCode=%5B%220%22%5D

The course will cover theoretical, practical, and investigative aspects of data analysis for chemical analysis. For this purpose, we cover data visualization and characterization of collected data, basic statistics for hypothesis testing, quantification and method validation.

In order for the experiment to be valid, a group of two to three students need to work together when tasting (sampling) and then plotting the data to find the optimal combination.

The course will cover from the fundamentals of statistical tests to application in analytical method validation and modeling. The gained knowledge is applied throughout the course in miniprojects. Additionally, the course content serves as bases for data analysis in the following courses in the Master Program in Analytical Chemistry.

How to make the tastiest lemonade?

Course structure

The course features lectures, workshops, computer lab work, oral and written presentation of scientific work within the following subjects:

Data presentation, characterization, distributions:

different statistics for average and spread, plotting data (scatter plot, histogram, box-plot, etc.), distributions (uniform distribution, normal distribution, t-distribution, etc.), central limit theorem.

Hypothesis testing:

type I and II error, p-value, t-test, and F-test, analysis of variance.\ Regression analysis for quantification and modeling: residuals, significance testing, slope and interpretation, calculating the concentration, lack-of-fit, goodness-of-fit, multilinear regression, robust regression.

Method validation:

precision, trueness, accuracy, uncertainty, different validation guidelines, quality control, and accreditation.

Teaching Format

Lectures, seminars, exercises and labs.

Expected learning outcomes

Define the hypothesis for testing statistical significance depending on the scientific question. Apply the statistical significance test and interpret the results. Evaluate the suitability of different statistical tests for given data and suggest a hypothesis testing method depending on the research question.
Explain the assumptions, limitations, and advantages of the calibration graph method, standard addition method, and internal standard method. Calculate the analysis result for different quantification methods. Evaluate the linear range of a calibration graph and evaluate the statistical significance of a regression line (residual analysis, Lack-of-Fit, significance of the intercept, etc.). Design a suitable calibration method depending on the instrumental method, available materials, and requirements for the analysis. Assess the suitability of the calibration approach for a given quantification approach.
Name method performance characteristics. Calculate the method characteristics and evaluate if they fulfill the method requirements. Evaluate the need for estimating different method performance characteristics depending on the research question. Design a plan for method validation depending on the method under development. \

Assessment

Written lab reports and written exam.

Examiner

Anneli Kruve\ Mianneli.kruve@su.se

Schedule

The schedule will be available no later than one month before the start of the course. We do not recommend print-outs as changes can occur. At the start of the course, your department will advise where you can find your schedule during the course.

Schema KZ7106 VT 2026 Dagtid pdf, 67.1 kB.