# EXMD 634: Introduction to Quantitative Methods in Experimental Medicine

*Summer 2020*

# 1 Contents

- Course details

## 1.1 Lecture 1

- Precision vs. Bias
- Random Sampling and Randomization
- Introduction to R

## 1.2 Lecture 2

- Types of variables
- Introduction to probability
- Definition
- Probability rules
- Probability trees
- Bayes Theorem

- Two common probability distributions
- Binomial distribution
- Normal distribution

- Other probability distributions for categorical and continuous variables

## 1.3 Lecture 3

- Mean and standard deviation
- Central Limit Theorem
- Confidence intervals
- Inference for a single mean or difference in means
- Sample size calculation for a single mean or difference in means

## 1.4 Lecture 4

- Hypothesis testing
- Inference for a single mean or difference in means
- Sample size calculation for a single mean or difference in means

- Confidence intervals vs. hypothesis testing: Quantifying uncertainty vs. making decisions
- Extra Problems

## 1.5 Lecture 5

- Sample Size Calculation

## 1.6 Lecture 6

- Bayesian inference for a single mean and for the difference between means
- Hypothesis testing and the risk of wrong conclusions

## 1.7 Lecture 7

- Confidence intervals for
- a single proportion
- difference between two proportions

- Hypothesis testing for
- a single proportion
- difference between two proportions

- Sample size calculations for studies of one or two proportions

## 1.8 Lecture 8

- Odds ratio
- Risk ratio (or relative risk)
- Number needed to treat
- Chi-squared test
- Fisher’s exact test

## 1.9 Lecture 9

- Hypothesis tests
- Sign test
- Signed rank test
- Rank Sum test

- Bootstrap confidence intervals

## 1.10 Lecture 10

- One-way ANOVA
- Estimation and checking of assumptions

- Multiple comparisons
- ANOVA in R

## 1.11 Lecture 11

- Extension of one-way ANOVA
- Randomized block design (or Repeated Measures)
- Two-way ANOVA

- Correlation
- Correlation vs. Causation
- Inference for the correlation coefficient

## 1.12 Lecture 12

- Simple and Multiple Linear Regression