A Primer in Biological Data Analysis and Visualization Using R

Erscheinungsjahr 2014
ISBN: 978-0-231-16698-0
Verlag: COLUMBIA UNIV PR

Buch, Englisch, 248 Seiten, Format (B × H): 183 mm x 254 mm, Gewicht: 612 g

R is the most widely used open-source statistical and programming environment for the analysis and visualization of biological data. Drawing on Gregg Hartvigsen's extensive experience teaching biostatistics and modeling biological systems, this text is an engaging, practical, and lab-oriented introduction to R for students in the life sciences.

Underscoring the importance of R and RStudio in organizing, computing, and visualizing biological statistics and data, Hartvigsen guides readers through the processes of entering data into R, working with data in R, and using R to visualize data using histograms, boxplots, barplots, scatterplots, and other common graph types. He covers testing data for normality, defining and identifying outliers, and working with non-normal data. Students are introduced to common one- and two-sample tests as well as one- and two-way analysis of variance (ANOVA), correlation, and linear and nonlinear regression analyses. This volume also includes a section on advanced procedures and a chapter introducing algorithms and the art of programming using R.

Autoren/Hrsg.

Hartvigsen, Gregg

Fachgebiete

• Mathematik | Informatik EDV | Informatik Angewandte Informatik Bioinformatik
• Naturwissenschaften Biowissenschaften Angewandte Biologie Bioinformatik
• Mathematik | Informatik EDV | Informatik Business Application Mathematische & Statistische Software

Inhaltsverzeichnis

Introduction1. Introducing Our Software Team1.1. Solving Problems with Excel and R1.2. Install R and RStudio1.3. Getting Help with R1.4. R as a Graphing Calculator1.5. Using Script Files1.6. Extensibility1.7. Problems2. Getting Data Into R2.1. Using C( ) for Small Datasets2.2. Reading Data from an Excel Spreadsheet2.3. Reading Data from a Website2.4. Problems3. Working with Your Data3.1. Accuracy and Precision of Our Data3.2. Collecting Data Into Dataframes3.3. Stacking Data3.4. Subsetting Data3.5. Sampling Data3.6. Sorting an Array of Data3.7. Ordering Data3.8. Sorting a Dataframe3.9. Saving a Dataframe to a File3.10. Problems4. Tell Me About My Data4.1. What Are Data?4.2. Where's the Middle?4.3. Dispersion About the Middle4.4. Testing for Normality4.5. Outliers4.6. Dealing with Non-normal Data4.7. Problems5. Visualizing Your Data5.1. Overview5.2. Histograms5.3. Boxplots5.4. Barplots5.5. Scatterplots5.6. Bump Charts (Before and After Line Plots)5.7. Pie Charts5.8. Multiple Graphs (Using Par and Pairs)5.9. Problems6. The Interpretation of Hypothesis Tests6.1. What Do We Mean by "Statistics"?6.2. How to Ask and Answer Scientific Questions6.3. The Difference Between "Hypothesis" and "Theory"6.4. A Few Experimental Design Principles6.5. How to Set Up a Simple Random Sample for an Experiment6.6. Interpreting Results: What is the "P-value"?6.7. Type I and Type II Errors6.8. Problems7. Hypothesis Tests: One- and Two-sample Comparisons7.1. Tests with One Value and One Sample7.2. Tests with Paired Samples (Not Independent)7.3. Tests with Two Independent Samples7.4. Problems8. Testing Differences Among Multiple Samples8.1. Samples Are Normally Distributed8.2. One-way Test for Non-parametric Data8.3. Two-way Analysis of Variance8.4. Problems9. Hypothesis Tests: Linear Relationships9.1. Correlation9.2. Linear Regression9.3. Problems10. Hypothesis Tests: Observed and Expected Values10.1. The X2 Test10.2. The Fisher Exact Test10.3. Problems11. A Few More Advanced Procedures11.1. Writing Your Own Function11.2. Adding 95% Confidence Intervals to Barplots11.3. Adding Letters to Barplots11.4. Adding 95% Confidence Interval Lines for Linear Regression11.5. Non-linear Regression11.6. An Introduction to Mathematical Modeling11.7. Problems12. An Introduction to Computer Programming12.1. What Is a "Computer Program"?12.2. Introducing Algorithms12.3. Combining Programming and Computer Output12.4. Problems13. Final Thoughts13.1. Where Do I Go from Here?AcknowledgmentsSolutions to Odd-numbered ProblemsBibliographyIndex

Über Autor(innen)

Gregg Hartvigsen is a professor in the Department of Biology at the State University of New York at Geneseo. He taught a workshop on network analysis using R at the National Institute for Mathematical and Biological Synthesis at the University of Tennessee, Knoxville, and was a visiting scientist and site reviewer for the Mathematical Biosciences Institute at Ohio State University. He also served as co-PI on a National Science Foundation training grant for undergraduate biology and mathematics.