Section outline

  • Collapse Expand

    Biostatistics II and Modeling

    Collapse all Expand all

    Instructors:
    • Dr Vedaste Ndahindwa

    Description of the course
    Biostatistics II will rely on information covered in Biostatistics I. The course provides a solid foundation in biostatistics including two sample hypothesis testing, non-parametric analysis, analysis of variance, odds ratios, linear regression and logistic regression. 

    Courses will alternate between class sessions and practice sessions. Each class session will be three hours. Students should bring computers to class with Stata installed on the computers.

    Learning objectives
    By the end of the course, students will have improved understanding and skills to:

    • Conduct one and two sample hypothesis testing for means
    • Conduct non-parametric hypothesis testing
    • Conduct the Analysis of Variance
    • Conduct and interpret correlation and simple linear regression
    • Conduct hypothesis testing for categorical data
    • Conduct and interpret binary logistic regression

    • Conduct and interpret survival analysis

    References
    • Bernard Rosner. Fundamentals of Biostatistics. 7th edition 2010. Boston: Brooks/Cole, Cengage Learning
    • Pagano and Gauvreau. Principles of Biostatistics. 2nd edition 2000. Pacific Grove, CA : Duxbury
    • Wayne W. Daniel. Biostatistics: A Foundation for Analysis in the Health Sciences. 9th edition 2009. Atlanta, Georgia : Wiley & Sons, Inc

    Assessment Modalities
    The grades will be based on the following:
    • Assignments (for a total of 50% of grade).
    • One in-class exam – 50% (CAT)
    • Final exam (External exam)

  • Collapse Expand

    Class 1 : Introduction to Hypothesis Testing

    This class covers hypothesis testing, the second of two general areas of statistical inference. Interval estimation and hypothesis testing are based on similar concepts. This session provides a format for conducting a hypothesis test.

    Learning objectives for this session:

    After completing this class the student will:

    • understand how to correctly state a null and alternative hypothesis
    • understand the concepts of type I error, type II error and the power of a test
    • be able to calculate and interpret z and t test statistics for making statistical inferences
    • understand the meaning of a significance level and a p-value
    • be able to conduct hypothesis test for a single mean
    • be able to compute hypothesis test for a single mean using Stata

    Lecture Topics:

    • Steps of hypothesis testing
    • Significance level, Type I, Type II error and statistical power
    • Hypothesis testing for one sample

    Readings:

    • Chapter 7: Bernard Rosner. Fundamentals of Biostatistics. 7th edition 2010. Boston: Brooks/Cole, Cengage Learning

  • Collapse Expand

    Class 2 [3h] : Hypothesis Testing: Two-Sample Inference

    This class covers hypothesis testing for the difference between two means. Independent and paired
    comparisons will be discussed in details.
    Learning objectives for this session
    After completing this class the student will:

    • be able to conduct hypothesis testing for the difference between two population means
    • be able to conduct hypothesis testing for paired comparisons
    • understand the comparison of means with unequal variances
    • be able to compute hypothesis test for two means using Stata

    Lecture Topics
    - Hypothesis testing: Comparison of Means from Two Paired Samples
    - Hypothesis testing: Two-Sample t Test for Independent Samples with Equal Variances
    - Hypothesis testing: Two-Sample t Test for Independent Samples with Unequal Variances
    Readings:
    • Chapter 8: Bernard Rosner. Fundamentals of Biostatistics. 7th edition 2010. Boston: Brooks/Cole,
    Cengage Learning

  • Collapse Expand

    Class 2 [3h] : Hypothesis Testing: K-Sample Inference

    During this class we discuss the testing of differences among means when there is interest in more than
    two populations or groups. the class covers the Analysis of variance (One way ANOVA) and the Kruskal
    Wallis Test.
    Learning objectives for this session
    After completing this class the student will:

    • be able to determine when analysis of variance is the appropriate
    • be able to discuss the general features of the Kruskal Wallis Test.
    • be able to compute One way ANOVA and Kruskal Wallis Test using Stata
    • be able to interpret the results

    Lecture Topics
    - Introduction
    - ANOVA and F-test
    - Kruskal Wallis Test
    Readings:
    • Chapter 12: Bernard Rosner. Fundamentals of Biostatistics. 7th edition 2010. Boston: Brooks/Cole,
    Cengage Learning

  • Collapse Expand

    Class 3 [3h] : Hypothesis Testing: Nonparametric Analysis

    This class covers techniques that are useful when the underlying assumptions of traditional hypothesis
    tests are violated or one wishes to perform a test without making assumptions about the sampled
    population.
    Learning objectives for this session
    After completing this class the student will:

    • understand the rank transformation and how nonparametric procedures can be used
    • be able to discuss and interpret a wide variety of nonparametric tests commonly used in practice
    • understand which nonparametric tests may be used in place of traditional parametric statistical
    • tests
    • understand the general advantages and disadvantages of nonparametric methods.
    • be able to compute nonparametric tests using Stata

    Lecture Topics
    - Testing normality
    - Data transformation
    - Sign Test
    - Wilcoxon Signed-Rank Test
    - Wilcoxon Rank-Sum Test
    Readings:
    • Chapter 9: Bernard Rosner. Fundamentals of Biostatistics. 7th edition 2010. Boston: Brooks/Cole,
    Cengage Learning

  • Collapse Expand

    Class 4 : Hypothesis Testing: Categorical Data

    This class explores techniques that are to test association between two categorical variables. Uses of
    the chi-square distribution are discussed and illustrated. Fisher’s Exact test will also covered.
    Learning objectives for this session
    After completing this class the student will:

    • be able to construct and use contingency tables to test independence
    • understand when it is appropriate to use a chi-square statistic
    • be able to compute and interpret Chi-squared test
    • be able to apply Fisher’s exact test for 2 x 2 tables

    Lecture Topics
    - Contingency tables
    - Observed and expected frequencies
    - Chi-squared test Interpretation
    - R × C Contingency Tables
    - Fisher exact test
    Readings:
    • Chapter 10: Bernard Rosner. Fundamentals of Biostatistics. 7th edition 2010. Boston: Brooks/Cole,
    Cengage Learning

  • Collapse Expand

    Class 5 [3h] : Correlation and Regression

    This class provides an introduction and overview of two common techniques for exploring the strength of
    the relationship between two quantitative variables. The first technique, linear regression, will help us find
    an objective way to predict or estimate the value of one variable given a value of another variable. The
    second technique, correlation, will help us find an objective measure of the strength of the relationship
    between two variables.
    Learning objectives for this session
    After completing this class the student will:

    • be able to obtain a simple linear regression model and use it to make predictions.
    • be able to calculate the coefficient of determination and to interpret tests of regression coefficients
    • be able to calculate correlations among variables.
    • understand how regression and correlation differ and when the use of each is appropriate.
    • be able to compute and interpret regression and correlation using Stata

    Lecture Topics
    - Correlation
    - Simple linear regression
    - Least Squares estimation
    - R-squared
    - Coefficients
    - Hypothesis testing for Coefficients
    Readings:
    • Chapter 11: Bernard Rosner. Fundamentals of Biostatistics. 7th edition 2010. Boston: Brooks/Cole,
    Cengage Learning

  • Collapse Expand

    Class 6 [3h] : Logistic Regression

    This class covers an introduction of the regression when the dependent variable is binary. Concepts and
    assumptions will be discussed.
    Learning objectives for this session
    After completing this class the student will:
    • understand the circumstances in which you would use logistic regression
    • be able to perform logistic regression for dichotomous dependent variables.
    • be able to fit a binary logistic regression model to data using Stata
    • Interpret the output of a binary logistic regression model
    Lecture Topics
    - Logistic Regression model
    - Analysis and interpretation
    Readings:
    • Chapter 11: Wayne W. Daniel. Biostatistics: A Foundation for Analysis in the Health Sciences.
    9th edition 2009. Atlanta, Georgia : Wiley & Sons, Inc

  • Collapse Expand

    Class 7 [3h] : Survival Analysis

    Lecture Topics
    - Introduction to survival analysis and censoring
    - Kaplan Meier survival estimate
    - Cox proportional hazards regression models


    Readings:
    • John P. Klein, Melvin L. Moeschberger. Survival Analysis: Techniques for Censored and Truncated
    Data. 2nd edition 2005. New York: Springer.

  • Collapse Expand

    Biostatistics II CAT

Accessibility
Reset All

Background Colour Background Colour

Font Face Font Face

Font Kerning Font Kerning

Font Size Font Size

1

Image Visibility Image Visibility

Letter Spacing Letter Spacing

0

Line Height Line Height

1.2

Link Highlight Link Highlight

Text Alignment Text Alignment

Text Colour Text Colour