Final project

Deadlines

  • Compulsory draft due: 2020-11-25, 11:59pm
  • Presentation slides due: 2020-12-02, 11:59pm
  • Final version due: 2020-12-13, 11:59pm
  • A draft report must be submitted before the presentations.
  • You may submit a revised report until the final deadline; if no revision is submitted, the preliminary version will be considered final.

Co-operation and feedback

  • You may submit project drafts to the instructor for comments.
  • Co-operation is permitted, with proper citation.

Report format

  • The report should be a ZIP archive in the form FirstnameLastnameProject.zip. The archive when unzipped should have a directory called FirstnameLastnameProject. Inside it, the code and data should be in separate subdirectories. This is essentially how you did your homeworks.
  • The code generating the report may be in either in RMD/HTML or IPYNB format.
  • Any data files (text format) should be submitted with the source code in a separate data directory.
  • The report and script to generate it should be in a separate directory called code or src.
  • Use only relative paths for data files, or secondary scripts you might be using.
  • The code must run and generate the report when executed without any modification.
  • Code should be commented; they should outline the logic and purpose of the computer instructions.

Report organization

Report should be organized roughly as follows. It should emphasize the statistical analysis. You may find helpful guidelines in the Equator network website.

  • Title: Provide an accurate and concise a description of the content of the report.
  • Specific aims/goals: Succintly describe the goals of your project; clearly describe the primary and any secondary objectives of the study, or specific hypotheses being tested. (a paragraph plus 1-3 list items).
  • Background: Describe scientific background (including relevant references to previous work) to understand the motivation and context for the study, and explain the experimental approach (1-2 pages).
  • Study design and data: Describe the data/study that you will be using for your project. State how it is organized (one file or multiple files, or database). Briefly outline any relevant experimental or study protocols (about 1 page).

  • Statistical analysis: This should be the bulk of the report.

    • Provide details of the statistical methods used for each analysis.
    • Specify the unit of analysis for each dataset (e.g. single animal, group of animals, single neuron).
    • Describe any methods used to assess whether the data met the assumptions of the statistical approach.
    • Use descriptive summaries (figures, tables, summary statistics) to get a feel for the data. Make sure you identify any missing values, unusual values or outliers, and state how you handle them.
    • Report the results for each analysis (addressing each specific aim) carried out, with a measure of precision (e.g. standard error or confidence interval).

  • Conclusion: Briefly summarize the main findings (half page to one page).

    • Interpret the results, taking into account the study objectives and hypotheses, current theory and other relevant studies in the literature.
    • Comment on the study limitations including any potential sources of bias, any limitations of your model, and the imprecision associated with the results

Report grading:

We will start with the default grade of 23, and add or subtract points based on fidelity to guidelines above.

Positives: Clear writing, clean commented code, use of advanced and appropriate statistical methods, clever algorithms good tables or figures, identification of limitations in approach, use of appropriate guidelines for study.

Negatives: Inappropriate use of statistical methods, incorrect interpretation of statistical procedures, inappropriate study design, cluttered presentation (eg. too many decimal points; incorrectly labeled graphs; too much or irrelevant computer output), not including code, uncommented code.

Presentation format

  • Presentations should be in PDF only, no more than 12 slides.
  • Slides should be submitted in advance of the actual presentation so that we can stick to the time.
  • Plan on speaking for 10 minutes. Each person will have 15 minutes max.

Presentation grading:

By default you will get 7 points, with points added or subtracted based on the following:

  • Clarity of presentation
  • Respecting time limits
  • Aesthetics
  • Clearly labeled graphs, tables, and figures
  • Ability to answer questions
  • Submission of compulsory draft