Modern applied biostatistical methods using S-Plus /
Saved in:
| Online Access: |
Full text (MCPHS users only) |
|---|---|
| Main Author: | |
| Format: | Electronic eBook |
| Language: | English |
| Published: |
New York :
Oxford University Press,
1998
|
| Series: | Monographs in epidemiology and biostatistics ;
v. 28. |
| Subjects: | |
| Local Note: | ProQuest Ebook Central |
Table of Contents:
- Contents
- 1. S-language
- In the beginning
- Three data types�and some input conventions
- Reading values into SPLUS
- S-tools�a beginning set
- S-arithmetic
- More S-tools�intermediate set
- S-tools for statistics
- Statistical distributions in SPLUS
- Arrays and tables
- Matrix algebra tools
- Some additional S-tools
- Four S-code examples
- The .Data file
- Addendum: Built-in editors
- Problem set I
- 2. Descriptive Techniques
- Description of descriptive statistics
- Basic statistical measures
- Histogram smoothing�density estimationStem-and-leaf display
- Comparison of groups�t-test
- Comparison of groups�boxplots
- Comparison of data to a theoretical distribution�quantile plots
- Comparison of groups�qqplots
- xy-plot
- Three-dimensional plots�perspective plots
- Three-dimensional plots�contour plots
- Three-dimensional plots�rotation
- Smoothing
- Two-dimensional smoothing of spatial data
- Clusters as a description of data
- Additivity�sweeping an array
- Example�geographic calculations using S-functions
- Estimation of the center of a two-dimensional distributionAddendum: S-geometry
- Problem set II
- 3. Simulation: Random Values
- Random uniform values
- An example
- Sampling without and with replacement
- Random sample from a discrete probability distribution�acceptance/rejection sampling
- Random sample from a discrete probability distribution�inverse transform method
- Binomial probability distribution
- Hypergeometric probability distribution
- Poisson probability distribution
- Geometric probability distribution
- Random samples from a continuous distributionInverse transform method
- Simulating values from the normal distribution
- Four other statistical distributions
- Simulating minimum and maximum values
- Butler's method
- Random values over a complex region
- Multivariate normal variables
- Problem set III
- 4. General Linear Models
- Simplest case�univariate linear regression
- Multivariable case
- Multivariable linear model
- A closer look at residual values
- Predict�pointwise confidence intervals
- Formulas for glm()
- Polynomial regressionDiscriminant analysis
- Linear logistic model
- Categorical data�bivariate linear logistic model
- Multivariable data�linear logistic model
- Goodness-of-fit
- Poisson model
- Multivariable Poisson model
- Problem set IV
- 5. Estimation
- Estimation: Maximum Likelihood
- Estimator properties
- Maximum likelihood estimator
- Scoring to find maximum likelihood estimates
- Multiparameter estimation
- Generalized scoring
- Estimation: Bootstrap
- Background
- General outline
