PCB 4454C - Biostatistics with Lab

College of Natural Sciences

Credit(s): 4
Contact Hours: 92
Effective Term Spring 2012 (450)

Requisites

Prerequisite STA 2023 or
Prerequisite MAC 2234 or
Permission of the Instructor

Course Description

This course is designed to provide the use of statistics in the analysis of biological data. Quality statistical analyses begin with quality data, so early topics cover the collection and processing of data as well as the calculation of descriptive summary statistics. Subsequent lectures will focus on the linkage between statistical analyses and the scientific method, especially in terms of developing and testing appropriate hypotheses. The remainder of the course involves a discussion of various routine techniques used to analyze biological data, including t-tests, analysis of variance (ANOVA), and linear regression. This course is a combined lecture and lab class, and the lab component involves hands-on analyses of real-world biological data using common statistical analysis software. At the completion of the course students will have sufficient understanding of basic statistical techniques to analyze data from their own undergraduate research studies.

Learning Outcomes and Objectives

  1. The student will organize the collection and summarization of biological data by:
    1. describing the difference between a population and a sample, as well as various approaches to obtaining a sample.
    2. explaining key differences between the various types of variables.
    3. describing the difference between accuracy and precision.
    4. condensing raw data through the construction of frequency distributions, stem-and-leaf plots, and histograms.
    5. calculating basic descriptive statistics, including statistics of location (e.g., mean, median and mode) and statistics of dispersion (e.g., range and standard deviation).
  2. The student will develop and test appropriate hypotheses related to probabilistic theory using critical thinking skills by:
    1. defining the sampling space and calculating the probability of a given sampling event.
    2. calculating expected frequencies of various sampling events following discrete frequency distributions (e.g., binomial, Poisson).
    3. describing the difference between a probability density function and a cumulative distribution function of continuous variables.
    4. describing key properties of the normal distribution.
    5. constructing confidence intervals around the mean.
    6. defining the difference between type I and type II error.
    7. constructing and testing both one-tail and two-tail hypothesis tests using the normal and t-distributions.
  3. The student will explain analysis of variance (ANOVA) by:
    1. describing how to partition sums of squares and degrees of freedom.
    2. describing differences between fixed and random effects.
    3. comparing means among groups based on a single classification (one-way ANOVA), hierarchical classification (nested ANOVA), and multiple classifications (two-way and three-way ANOVA).
    4. conducting a-priori and a-posteriori comparisons.
    5. deducing the appropriate sample size required and statistical power for ANOVA.
    6. testing various assumptions required for ANOVA, and determining appropriate transformations to the data.
  4. The student will explain linear regression by:
    1. differentiating between independent and dependent variables.
    2. defining the assumptions required to conduct linear regression analyses.
    3. comparing the relationship between one independent variable and one dependent variable (simple linear regression), multiple independent variables and one dependent variable (multiple linear regression), and one independent variable and one dependent variable where the relationship is not linear (curvilinear regression).
    4. constructing confidence limits around the predicted regression line.
    5. comparing regression lines among various groups using the analysis of covariance (ANCOVA).
    6. determining appropriate transformations through examination of patterns of unexplained variability in the residuals.
    7. describing the difference between regression and correlation.
  5. The student will use common statistical analysis software to conduct basic statistical analyses and interpret computer output by:
    1. importing, manipulating, and summarizing data.
    2. conducting one-sample and two-sample t-tests.
    3. conducting one-way ANOVA, two-way ANOVA, and multi-way ANOVA, including post-hoc tests and tests for ANOVA assumptions.
    4. conducting simple linear regression, multiple regression, and curvilinear regression analyses, including residual diagnostics and tests for regression assumptions.
    5. conducting an analysis of covariance (ANCOVA).
    6. conducting a Chi-squared goodness of fit test.
    7. preparing weekly lab reports that summarize and interpret the results obtained from computer output.

Criteria Performance Standard

Upon successful completion of the course the student will, with a minimum of 70% accuracy, demonstrate mastery of each of the above stated objectives through classroom measures developed by individual course instructors.

History of Changes

C&I Approval: 06/14/2011, BOT Approval: 10/20/2011, Effective Term: Spring 2012 (450)