Data Analysis and Statistical InferenceLaajuus (5 ECTS)

Objective

The student is able to apply basic rules of probability in simple applications. The student can list the most important discrete and continuous distributions and can apply them in problems of bio and food engineering. The student can explain the meaning of a confidence interval and can apply it in statistical reasoning. The student recognizes the most common statistical tests and can apply them in problems of bio and food engineering. The student is able to apply the principle of least squares in regression analysis, and he or she can interpret output of regression analysis software. The student can use R or Excel in statistical analyses.

Content

1. Different concepts of probability, and basic rules for calculating probabilities.
2. Combinatorics and factorial experimental designs.
3. Random variables and their most common distributions.
4. Laws of error propagation and estimation of measurement uncertainty.
5. Graphical representation of statistical data.
6. The idea of Monte Carlo simulation.
7. Confidence intervals and statistical reasoning using confidence intervals and the idea of statistical process control (SPC).
8. Statistical tests and their applications.
9. Regression analysis and its typical applications.
10. Introduction to analysis of variance and related experimental designs.
11. Using R and/or Excel in statistical analyses.

Qualifications

Fundamentals of Mathematics and Natural Sciences 1
Fundamentals of Mathematics and Natural Sciences 2

Assessment criteria, satisfactory (1)

1. The student can calculate probabilities for given simple events.
2. The student is able to construct factorial designs of experiments, and to calculate numbers of permutations and combinations.
3. The student recognizes binomial, Poisson and normal distributions, and he or she can apply the rules of thumb of the normal distribution in estimating normal probabilities.
4. The student can approximate the standard measurement uncertainty of simple expressions of measurement results.
5. The student can plot histograms and scatter plots of statistical data.
6. —
7. The student can calculate confidence intervals for expected values and for variances in typical applications in the field.
8. The student can make the correct conclusion of a statistical test at given level of significance when the null hypothesis and the p-value are given.
9. The student can apply linear regression of one variable in simple problems, e.g. calibration
10. —
11. The student can use R or Excel in elementary statistical analyses.

Assessment criteria, good (3)

1. The student can calculate simple conditional probabilities.
2. —
3. The student can apply binomial and Poisson distributions in simple applications in bio and food engineering.
4. The student can approximate the standard measurement uncertainty in typical calculations appearing in the field.
5. The student can use R or Excel for visualizing statistical data.
6. The student can use Monte Carlo simulation in uncertainty estimation.
7. The student can calculate confidence intervals for differences of expected values.
8. The student can form statistical hypotheses and apply t- and F-tests in simple applications of the field.
9. The student can transform simple nonlinear dependences into a linear regression form.
10. —
11. The student can use R or Excel statistical tests, and in regression analyses.

Assessment criteria, excellent (5)

1. —
2. —
3. The student can apply binomial, Poisson and normal distributions in typical applications in the field.
4. —
5. —
6. —
7. The student can calculate confidence intervals for linear combinations of expected values.
8. The student can apply t- and F-tests in bio, chemical, material and food engineering.
9. The student can interpret results given by multiple linear regression.
10. The student can apply one-way analysis of variance, and is able to recognize experimental designs in which the method can be applied.
11. The student can write can simple R-programs (scripts or functions).

Assessment criteria, approved/failed

1. The student can calculate probabilities for given simple events.
2. The student is able to construct factorial designs of experiments, and to calculate numbers of permutations and combinations.
3. The student recognizes binomial, Poisson and normal distributions, and he or she can apply the rules of thumb of the normal distribution in estimating normal probabilities.
4. The student can approximate the standard measurement uncertainty of simple expressions of measurement results.
5. The student can plot histograms and scatter plots of statistical data.
6. —
7. The student can calculate confidence intervals for expected values and for variances in typical applications in the field.
8. The student can make the correct conclusion of a statistical test at given level of significance when the null hypothesis and the p-value are given.
9. The student can apply linear regression of one variable in simple problems, e.g. calibration
10. —
11. The student can use R or Excel in elementary statistical analyses.