E0410 Fundamentals of Statistics for Scientific Data Using R by Daria Sapunova, PhD student, RECETOX daria.sapunova@recetox.muni.cz Bohunice, D29, room 123 Theoretical part Mentimeter.com We are approaching the end of the course Date Content 25/04 Correlation 02/05 Linear regression 09/05 Linear + multiple regression 16/05 Dean’s holiday 23/05 Wrap up or linear regression if we didn’t cover it up, questions Final assignment Working on a dataset provided by a student or the teacher. The results should be presented as a pdf file consisting of: Context Words a title - a short introduction regarding the topic with references approx. 200 words data description approx. 100 words statistical method description approx. 200 words results with data visualization and interpretation of the results approx. 200 words a short conclusion approx. 100 words Appendix with the R script - Final assignment üThe examination period is from 27.05.24 to 04.07.24 üPlease, upload pdf files with your assignment till 01.07.24 included üThe instruction with the example will be uploaded 18.05.-19.05.24, prepare your questions by 23.05. if you will have any üThe generated data will be sent 18.05.-19.05.24 Who needs data? üTill 03.05.24 included fill up the table Study materials -> Learning materials -> Final Assignment -> data_generate.xlsx Check list Deadline Action 03/05 Fill up data_generate.xlsx 18/05-19/05 The instruction with the example and the generated data will be uploaded by the teacher 23/05 Questions regarding the instruction and data 01/07 Upload the final assignment If you have questions - daria.sapunova@recetox.muni.cz Repetition Mentimeter.com Parametric and non-parametric: association between two numerical variables We have: two numerical continuous variables Height Weight Salary Productivity Employment Inflation Teenage girl measures height standing near marks on wall wanting to become tall Man paying online and receiving cashback to wallet Losing weight. Female nutritionist cartoon character. Slimming, weightloss, dieting. Counting calories. Overweight man with hamburger. Vacancy concept illustration Finance illustration concept is a measure of the strength of the linear association, and it indicates the direction of the linear association. Correlation Height (cm) üStrength correlation coefficient (r/ρ) from -1 to 1 üDirection Positive or negative ü üStrength (r) from -1 to 1 üDirection Positive or negative ü Correlation üStrength (r) from -1 to 1 üDirection Positive or negative ü https://sphweb.bumc.bu.edu/otlt/MPH-Modules/PH717-QuantCore/PH717-Module9-Correlation-Regression/PH 717-Module9-Correlation-Regression4.html Correlation üStrength (r) from -1 to 1 üDirection Positive or negative ü Perfect positive Perfect negative Very strong positive Very strong negative Moderate positive Moderate negative No correlation Correlation https://www.simplypsychology.org/correlation.html A graph of a function Description automatically generated Correlation is a measure of the strength of the linear association https://www.coursera.org/learn/linear-regression-r-public-health Parametric and non-parametric: association between two numerical variables We have: two numerical continuous variables Nonparametric Parametric üPearson correlation üSpearman correlation Nonparametric Parametric The observations within each group must be independent of each other. Assumptions: Normal distribution üPearson correlation üSpearman correlation Linearity Monotonic relationship between the two variables A graph of a person and person Description automatically generated https://www.coursera.org/learn/linear-regression-r-public-health Monotonicity means that as the value of one variable increases, the value of the other variable either consistently increases or consistently decreases (but not necessarily at a constant rate). This assumption means that the relationship between the variables doesn't have to be strictly linear. A graph of a function Description automatically generated Monotonic relationship between the two variables Task! Portrait of an excited young girl with laptop computer and celebrating success A scatter plot shows a moderate negative correlation between the levels... | Download Scientific Diagram Moderate positive correlation between pre-and post-tests, for paired... | Download Scientific Diagram Scatter plot demonstrating weak positive insignificant correlation... | Download Scientific Diagram Practical part