Topic outline

  • General

    • Certificate issue 修了証発行
      Restricted Not available unless:
      • The activity questionnaire_01 is marked complete
      • The activity questionnaire_02 is marked complete
      • The activity questionnaire_03 is marked complete
      • The activity questionnaire_04 is marked complete
      • The activity questionnaire_05 is marked complete
      • The activity questionnaire_06 is marked complete
      • The activity questionnaire_07 is marked complete
      • The activity questionnaire_08 is marked complete

  • Describing Data

    When summarizing continuous data such as age or laboratory results, do you think that you should provide the median and range? Can you explain why it's not the average?

    This lecture will explain the basics, such as interpreting data using histograms and scatter plots, and choosing analysis methods.

    This lecture will also explain data cleaning and preliminary analysis that should be performed before conducting tests or estimations.


  • Hypothesis Testing 1

    This lecture will explain the basics of statistical hypothesis testing.

    You might always see p-values ​​in papers and academic presentations, but do you accurately understand the definition and concept of p-value?

    Take this lecture and become able to explain it yourself.


  • Hypothesis Testing 2

    This lecture focuses on cases where the outcome is continuous or categorical variables.

    Don't you easily assume that "Wilcoxon's log rank test is used for datasets with small N and continuous variable" or "Fisher's exact test is used for those with small N and categorical variable"?

    This lecture will explain appropriate understandings of the testing.


  • Survival Analysis

    This lecture will explain survival analysis, which is a particularly important analytical method in clinical cancer research.

    This method is required when the outcome is survival. Why is it inappropriate to use analytical methods for continuous or categorical variables? This lecture will provide you the basic concepts of survival analysis.


  • Randomization and Confounding

    In the previous lectures, we focused on explaining methods of data analysis according to the type of outcome.

    However, being able to analyze data does not necessarily mean that you will be able to correctly interpret the results.

    The purpose of this lecture is to understand "confounding," one of the most important concepts to understand in clinical research, and why randomized clinical trials are necessary.


  • Multivariate Analysis 1

    This lecture will explain multivariate analysis, which is used to rule out confounding.

    A brief explanation of the structure of statistical models and how hazard ratios and odds ratios are estimated from statistical models will also be provided.


  • Multivariate Analysis 2

    Multivariate analysis can be used for purposes other than confounding adjustment, such as predicting recurrence and prognosis, predicting the occurrence of adverse events such as complications, and predicting the efficacy of medicinal products.

    This lecture will focus on the points to be aware of when performing multivariate analysis for prediction purposes.


  • Sample Size Calculation

    This lecture explains how to calculate sample size, which is necessary in the planning stage of clinical research.

    Specifically, how to set alpha, beta, and treatment effects is explained using a randomized controlled trial of cancer as an example.