class: center, middle, inverse, title-slide # Analyses from beginning to end ## Day 4 ### Jason Lerch --- <style> .small { font-size: 65%; } .medlarge { font-size: 95%; } .medium { font-size: 80%; } .footnote { font-size: 75%; color: gray; } .smallcode { } .smallcode .remark-code { font-size: 50% } .smallercode { } .smallercode .remark-code { font-size: 75% } </style> # Hello World Only a few slides today - most time will be taken up in interactive data analysis --- # The presentation First note: room change. Rather than the exam centre, we'll meet in PMH 7-605 (same as day 1) for the presentation. We can then either have the exam there too or move to the exam centre. No need to create a presentation - just make sure to have sent your html output from today's assignment. 2 minutes to present your core conclusions. 1-2 minutes of questions from me. --- # The assignment Take the "real" data, and (1) Analyze with the pre-registered plan from yesterday. (2) Reanalyze with any updated analyses you want to explore. (3) Describe your recommendation regarding whether the new therapeutic is worth adopting and why. Note: each group has different data this time; get your data here https://jasonlerch.github.io/MBP-stats-2019/last-assignment-data/Yates.csv (replacing "Yates" with your group name) --- # The exam 14 questions Very similar in style to what you've seen from the quizzes Includes interpreting of plots, interpreting of linear model outputs, true/false and multiple choice questions on p values, multiple comparisons, data splitting, statistical power, and the crisis of replication. No R coding required. No formula's need memorizing. Nothing new from today - today is revisiting what we've discussed the last three days Nothing from the papers except what was explicitly discussed in class.