# Statistical Resources

Need statistical help? Utilize our statistical resources below.

### Biostatistics Consulting Service

The Medical College of Wisconsin Biostatistics Consulting Service provides statistical support to biomedical investigators.

## Resources

Opening documents:

Left-click to open documents.

If left-click does not work, try right-clicking and "save-as" or "open in new".

If you have any software questions or are having trouble downloading, then please email Dan Eastwood (eastwood@mcw.edu) with the name of the file you need and I will email it to you directly.

November 2013

BIV pack: Bayesian methods for IV regression

July 2011

Linear & Logistic Mixed Model Implementation

Manual (PDF)

Makefile

Normal.h

Normal.c

Normal-Uniform.h

Normal-Uniform.c

Logistic.h

Logistic.c

Logistic-Uniform.h

Logistic-Uniform.c

Onetime.h

Onetime.c

gls_cholmod.h

January 2011

SAS macros for estimation of direct adjusted cumulative incidence curves under proportional subdistribution hazards models

CIFCOX (TXT)

CIFSTRATA (TXT)

January 2009

Truncated normal sampler (TXT): For generating truncated normal random variates. A text file containing R functions for implementing, testing and comparing a new rejection sampler with the inverse CDF method

August 2008

**CHANGEPOINT** (TXT): For the implementation of the Cox-type regression on cumulative incidence function with a time change-point by Xiaolin Fan, PhD

CHANGEPOINT Readme (PDF): Quick reference guide

**
CIF**: (TXT)For the implementation of estimated cumulative incidence function without covariates under the competing risks setting by Xiaolin Fan, PhD.

CIF Readme: (PDF) Quick reference guide

CIFCOX (TXT): For the implementation of the Cox-type regression on cumulative incidence function under the competing risks settings by Xiaolin Fan, PhD

CIFOX Readme: (PDF): Quick reference guide

**(TXT): For the implementation of the two-level hierarchical for the Cox-type regression on cumulative incidence function under the competing risks setting by Xiaolin Fan, PhD**

TWOLEVEL

TWOLEVEL

TWOLEVEL Readme (PDF): Quick reference guide

March 2008

**STRUCTDPM**: (TXT) C code for implementing bayesian semiparametric modeling of genetic association studies of quantitative traits in the presence of population stratification

Instruction file for program: STRUCTDPM_readme (PDF)

See also: Tech Report 55 (PDF)

August 2007

SAS macro for adjusted survival curves: (TXT)

Instructions: A SAS Macro For Estimation Of Direct Adjusted Survival Curves Based On A Stratified Cox Regression Model (PDF): by Xu Zhang, Fausto R. Loberiza, John P. Klein, and Mei-Jie Zhang.

July 2007

SAS macros to find pseudo-values for censored data (TXT)

R functions to find pseudo-values for censored data (TXT)

Instructions for pseudo-value functions/macros:

SAS and R Functions to Compute Pseudo-values for Censored Data Regression (PDF) by John P Klein, Mette Harhoff, Per Kragh Andersen, and Sergey Tarima

SAS Macro for the Additive Hazards Model (TXT)

Quick Reference Guide To Additive Macro (TXT)

SAS Macro for the Semiparametric Gamma Frailty Model (TXT)

Quick Reference Guide To Gamma Frailty Macro (TXT)

SAS Macro for the Semiparametric Positive Stable Frailty Model (TXT)

Quick Reference Guide To Positive Stable Frailty Macro (TXT)

SAS Macro for Score Test of Homogeneity for Survival Data (TXT)

Quick Reference Guide to Score Test of Homogeneity for Survival Data (PDF)

SAS Macro For Cumulative Incidence Functions (TXT)

Quick Reference Guide To SAS Macro For Cumulative Incidence Functions (TXT)

**SAS Macro to Estimate Haplotype Frequencies under the Assumption of Hardy-Weinberg Proportions (HAPEM)**

Quick Reference Guide to the HAPEM macro (

**DOC**, TXT, PDF)

**Video Topics & Abstract Brochure**

Contains the entire listing of Biostatistics lecture videos and abstracts.

**Printable Video Topics & Abstract Brochure**(PDF)

**Video Topics, Abstracts, YouTube Links, PowerPoints**

Below you can find the full listing of video topics, abstracts, direct video links to YouTube, and each lecture's accompanying PowerPoint.

Analyzing Discrete Data: Describing discrete (categorical) data; graphical display; measure of association for binary outcomes; risk difference, relative risk, odds ratios; tests of association; Chi-square tests; Fisher’s exact test; introduction to logistic regression model PowerPoint Slides (PDF)

ANOVA: Comparing More Than Two Treatments: Techniques for comparing the mean responses of two or more treatment groups (one way ANOVA); comparison of two factors (two way ANOVA); multiple comparisons PowerPoint Slides (PDF)

Basic Concepts of Bayesian Statistics: What is Bayesian statistics; interpretation and assignment of probability; calibration of probability; conditional probability; Bayes Theorem; prior, posterior and predictive distributions; inference and prediction conditioned on full information; when Bayesian methods are particularly useful; individualized medicine; hierarchical and complex stochastic modeling; pooling of information; substantial extra-data information; adaptive clinical trials. PowerPoint Slides (PDF)

Biostatistics Questions & Database Basics: Resources available in the Biostatistics Consulting Service; basic questions when planning a study; basic concepts of how to create a research database; types of data; spreadsheet vs. database PowerPoint Slides (PDF)

Choosing Statistical Software: Introduction to some of the most commonly used statistical packages; comparison of the capabilities, availability, cost, and ease of use of the packages PowerPoint Slides (PDF)

Common Errors in Linear Regression: Linear regression components, use graphs to check linear regression assumptions, linearity, constant variance, normality, outliers, multicollinearity, remedies PowerPoint Slides (PDF)

Concepts on the Way from Data to Decisions: Hypothesis formulation; study-to-study variation; tests of hypothesis; type I and II errors; confidence intervals; planning a study PowerPoint Slides (PDF) | Applets (PDF)

Designing Clinical Trials: Dose-finding phase I designs; phase II designs; determination of sample size; the use of two stage designs PowerPoint Slides (PDF)

Getting Help for Your Biostatistics Questions & Database Basics: Resources available in the Biostatistics Consulting Service; basic questions when planning a study; basic concepts of how to create a research database; types of data; spreadsheet vs. database PowerPoint Slides (PDF)

Introduction to Survival Analysis: Censoring and truncation; Kaplan-Meier estimators; log rank tests; competing risks; cumulative incidence functions PowerPoint Slides (PDF)

Introduction to Survival Analysis (11.8.13): Survival analysis; time-to-event data; event of interest in studies (e.g. death, recurrence of disease, development of complications after treatment); methods for partial data; regression methods; methods used to analyze competing risks data PowerPoint Slides (PDF)

Logistical Regression: Simple logistic regression models for binary data; interpretation of regression coefficients in simple logistic regression; multiple logistic regression models; estimation and inference for logistic regression models; odds ratios; models for association; models for prediction/classification

PowerPoint Slides (PDF)

Logistic regression PowerPoint Slides (PDF)

Longitudinal Analysis: Longitudinal studies; design for longitudinal studies; analysis for longitudinal studies; correlation between measurements; statistical methods to address correlation; missing data mechanism PowerPoint Slides (PDF)

Matched Studies in Medical Research: The use of retrospective and prospective matching; Methods for comparison of treatment in matched studies with binary or continuous outcome; paired vs. unpaired t-tests; McNemar’s test Matched Studies in Medical Research (PDF)

Multiple Comparisons: Problem of multiple testing; familywise error rates; false discovery rates; multiple testing strategies; subgroup analysis; interim analysis PowerPoint Slides (PDF)

Paired Data Analysis: Paired t-test; Sign Test; Wilcoxon Sign rank test; McNemar’s test

PowerPoint Slides (PDF)

Propensity Scores: Definition of propensity score; the background and motivation of developing propensity score method; propensity score estimation method; propensity score matching; estimating treatment effect using propensity including matched pair analysis and regression adjustment and stratification

PowerPoint Slides (PDF)

Reading Medical Literature: The main parts of a statistical paper; review of basic statistical concepts; reading the statistical methods and results section

**PowerPoint Slides**(PDF)

Methods for Equivalence and Non‐Inferiority Testing: Equivalence tests: tests designed to show two treatments have the same mean outcome; non-inferiority tests: tests to show a new treatment performs no worse than an existing test; confidence interval based tests

**PowerPoint Slides**(PDF)

Simple Statistics & Graphics in Excel: Data entry; descriptive statistics (mean, median, etc.); statistical inference (t-test, ANOVA, regression); how to create and enhance graphs (line, pie, bar) in Excel

PowerPoint Slides (PDF)

Simple Statistics in Excel: Entering and managing data in Excel; descriptive statistics; statistical inference in Excel including t-test, simple regression models; data analysis add-in PowerPoint Slides (PDF)

Statistical Consideration in Grant Writing:

Specific aims and hypotheses; specifying the study population; selecting a study design; defining outcome measures; sample size calculations; data analysis plan PowerPoint Slides (PDF)

Statistical Graphics in Excel: Types of graphs in Excel: pie charts, bar charts, histograms, line graphs, scatter diagrams; properties of a good graph; modifying default graphs

**PowerPoint Slides**(PDF)

Statistics, Probability & Diagnostic Medicine: Sensitivity; specificity, positive and negative predictive value; the likelihood ratio; the ROC curve PowerPoint Slides (PDF)

Simple Linear Regression: Simple linear regression; fitting a line to data; interpretation and prediction; confidence intervals and hypothesis testing; measuring the strength of association; model checking; binary predictions PowerPoint Slides (PDF)

Uses and Abuses of Non‐parametric Statistics: The sign and sign rank test for paired data; the Mann-Whitney Wilcoxon test for unpaired data PowerPoint Slides (PDF)

Web-Based Sample Size Calculation: Statistics hypotheses, significance level and statistical power; free online website for sample size and power calculations PowerPoint Slides (PDF)

Writing a Protocol: Protocol rational for prospective and retrospective studies; elements of a protocol PowerPoint Slides (PDF)

YouTube channel: Watch all past videos on our Biostatistics MCW YouTube channel by clicking on the title of the presentation.

MCW Biostatistic YouTube Videos

Preface (PDF)

**SAS Macros**

Errors (PDF) (First Edition)

Ordering Information

**Data Sets (txt files):
**

- Data from section 1.2

- Data from section 1.3

- Data from section 1.4

- Data from section 1.5

- Data from section 1.6

- Data from section 1.7

- Data from section 1.8

- Data from section 1.9

- Data from section 1.10

- Data from section 1.11

- Data from section 1.12

- Data from section 1.13

- Data from section 1.14

- Data from section 1.15

- Data from section 1.16

- Data from section 1.18

- Data from section 1.19

- Data from problem 4.7.4 (p.120)

- Data from problem 4.7.7 (p.122)

- Data from problem 5.5.6 (p.146)

- Data from problem 5.5.8 (p.147)

- Data from problem 7.8.6 (p.222)

- Data from problem 7.8.7 (p.223)

- Data from problem 7.8.13 (p.225)

- Data from problem 7.8.14 (p.226)

- Data from problem 13.5.1 (p.418)

- Data from problem 13.5.2 (p.419)

Biostatistics Linux FAQ (PDF)

Cheese Cluster User Guide (PDF)

Cluster (PDF)

Use the command:

**dos2unix**

Also: Use UNIX2DOS for converting UNIX to DOS file

Biostatistics Basic UNIX commands (PDF):

Printing in UNIX.

Using a USB drive from a SunRay terminal.

Changing the priority of a process.

Terminating processes using "kill".

Cleaning up SAS files and backup files.