# Register now to access 7 million high quality study materials (What's Course Hero?) Course Hero is the premier provider of high quality online educational resources. With millions of study documents, online tutors, digital flashcards and free courseware, Course Hero is helping students learn more efficiently and effectively. Whether you're interested in exploring new subjects or mastering key topics for your next exam, Course Hero has the tools you need to achieve your goals.

2 Pages

### multex_sol

Course: BINF 5035, Fall 2009
School: University of Medicine...
Rating:

Word Count: 800

#### Document Preview

of University York Department of Health Sciences Applied Biostatistics Suggested answers to exercise: Multiple regression Question 1 a) What is meant by `multiple regression analysis'? This is a statistical method used where we have a continuous outcome variable, here systolic blood pressure, and several possible predictors, here recovery index, age, race, area of residence, and ponderal index. The method...

Register Now

#### Unformatted Document Excerpt

Coursehero >> New Jersey >> University of Medicine and Dentistry of New Jersey >> BINF 5035

Course Hero has millions of student submitted documents similar to the one
below including study guides, practice problems, reference materials, practice exams, textbook help and tutor support.

Course Hero has millions of student submitted documents similar to the one below including study guides, practice problems, reference materials, practice exams, textbook help and tutor support.
of University York Department of Health Sciences Applied Biostatistics Suggested answers to exercise: Multiple regression Question 1 a) What is meant by `multiple regression analysis'? This is a statistical method used where we have a continuous outcome variable, here systolic blood pressure, and several possible predictors, here recovery index, age, race, area of residence, and ponderal index. The method estimates the relationship between the outcome and each predictor adjusting for all other predictors in the model. Here, the outcome or dependent variable is systolic blood pressure. The predictor, independent, or explanatory variables are recovery index, age, race, area of residence, and ponderal index. b) What is meant by the terms `b', `SE b' and `95% CI'? `b' is the coefficient of recovery index in a multiple regression equation. It means that for two groups of subjects whose recovery index differs by one unit, and who all have the same age, race, area and ponderal index, the difference in mean systolic blood pressure will be b units. It is found by the method of least squares. `SE b' is the standard error of the estimate of b. Different samples of the same size would give different estimates of b. SE b is the estimated standard deviation of the possible estimates of b. '95 % CI' is the 95 % confidence interval for b. For 95 % of possible samples, this range of values will include the value of b for the whole population. c) What assumptions about the variables are required for these analyses to be valid? The assumptions are that the differences between the observed systolic blood pressure and the systolic blood pressure predicted by the regression equation (residuals or deviations from the regression) follow a Normal distribution and that the variance of this distribution is uniform, i.e. unrelated to recovery index, age, race, area and ponderal index. The relationships should be linear. d) Why was the regression adjusted and what does this mean? Regression may be adjusted because the variable of interest, systolic blood pressure, is related to the adjusting variables, age, race, area, and ponderal index. We want to estimate the effect of recovery index on systolic pressure in children on the same age, race, area, and ponderal index. e) What would be the effect of adjusting for race if systolic blood pressure were related to race and recovery index were not? If recovery index is independent of adjusting variables, the adjustment will reduce the variability of deviations the and so make the estimate of b better, in that the confidence interval will be narrower, but the estimate will not be changed. What would be the effects of adjusting for ponderal index if blood pressure and recovery index were both related to ponderal index? If recovery index is related to the adjusting variables, the adjustment will reduce or remove the spurious relationship between recovery index and systolic blood pressure produced by both being independently related to something else. Both the coefficient and its standard error are likely to change. f) 1 Question 2 a) What is meant by `multiple logistic regression'? Multiple logistic regression or logistic regression is a multifactorial statistical method used when we have a dichotomous outcome, here reporting passive smoking as harmful or not. The method allows us to estimate the relationship between this outcome and several predictor variables, here affiliation with the tobacco industry and others. It allows us to estimate the odds ratios for each predictor adjusted for all others in the model. b) What is wrong with the interpretation of the odds ratio by the BMJ writer? `88 times more likely' suggests that the odds ratio has been interpreted as the increase in risk, whereas it actually represents the increase in odds. These are only similar if the condition of interest is rare. Also, the odds are 87 times greater or 88 times as great rather than 88 times more likely. This is not very important here, but w...

Find millions of documents on Course Hero - Study Guides, Lecture Notes, Reference Materials, Practice Exams and more. Course Hero has millions of course specific materials providing students with the best way to expand their education.

Below is a small sample set of documents:

University of Medicine and Dentistry of New Jersey - BINF - 5035
Health Sciences M.Sc. ProgrammeApplied BiostatisticsWeek 6: Proportions, risk ratios and odds ratiosRisk ratio or relative riskChi-squared tests are tests of significance, they do not provide estimates of the strength of relationships. There ar
University of Medicine and Dentistry of New Jersey - BINF - 5035
University of York Department of Health Sciences Applied BiostatisticsExercise: Odds ratio and relative riskQuestion 1 The following is the abstract of a paper (Illi et al., 2001): Objective: To investigate the association between early childhood
University of Medicine and Dentistry of New Jersey - BINF - 5035
University of York Department of Health Sciences Applied BiostatisticsSuggested answers to exercise: The analysis of cross-tabulationsQuestion 1 (a) What is meant by odds ratio 0.52 for runny nose and asthma and what does it tell us? The odds of a
University of Medicine and Dentistry of New Jersey - BINF - 5035
BINF5035Simple Descriptive Statistics Using SAS Procedures(commands=descriptives.sas)This handout covers the use of SAS procedures to get simple descriptive statistics and to carry out a few basic statistical tests, using the data set: the Flight
University of Medicine and Dentistry of New Jersey - BINF - 5035
2003-2008, The Trustees of Indiana UniversityComparing Group Means: 1Comparing Group Means: T-tests and One-way ANOVA Using Stata, SAS, and SPSSHun Myoung Park This document summarizes the methods of comparing group means and illustrates how to
University of Medicine and Dentistry of New Jersey - BINF - 5075
MICROSOFTINTERMEDIATE ACCESS MAINTAIN DATA INTEGRITYQUICK NOTESASSIGN APPROPRIATE DATA TYPE TO FIELDS.2 CREATE VALIDATION RULES IN TABLES.6 CREATE DATA CONTROL FIELDS IN TABLES ..9 CREATE VALIDATION RULES AND CONTROLS IN FORMS .11 USE EXPRESSION
University of Medicine and Dentistry of New Jersey - BINF - 5075
Clinical Trial Data Acquisition TechnologiesBINF5075Contents Clinical Trial Data Acquisition &amp; ManagementSoftware Clinical Trial Data Entry Technologies: Keyboard Barcoding Fax Direct data entry by participants Direct computer messaging:
University of Medicine and Dentistry of New Jersey - BINF - 5075
Database Management Systems 2BINF5075 Biomedical Informatics in Clinical Trials ManagementThe Relational Model The relational model is perhaps the simplest andmost intuitive data model ever developed. The entire model is based upon tables wit
University of Medicine and Dentistry of New Jersey - BINF - 5075
BINF5075 Database ExerciseDatabase operations will be covered in this module using Microsoft's Access software. This exercise assumes familiarity with MS-Excel so you should complete that one first if you haven't already done so. Why use a database
University of Medicine and Dentistry of New Jersey - BINF - 5075
Database Management Systems &amp; SQL -1BINF5075 Biomedical Informatics in Clinical Trials ManagementSQL Standard SQL-92 was developed by the INCITS Technical Committee H2 onDatabases. SQL-92 was designed to be a standard for relational database m
University of Medicine and Dentistry of New Jersey - BINF - 5075
Database Management Systems &amp; SQL-2BINF5075 Biomedical Informatics in Clinical Trials ManagementSQL ComponentsSQLDCL DBA Activities Create Users Delete Users Grant privileges Implement Access Security DDL RDBMS Structure Create/Delete DBs Create
University of Medicine and Dentistry of New Jersey - BINF - 5075
Data Cleaning Statistical ApproachBINF5075Statistical Approaches No explicit Data Quality methods Traditional statistical data collected from carefully designed experiments, often tied to analysis But, there are methods for finding anomalies
University of Medicine and Dentistry of New Jersey - BINF - 5075
Sample Size Planning and Randomization for Clinical TrialsBINF50751 Sample Size Planning1.1Introduction FundamentalPointsClinicaltrialsshouldhavesufficientstatistical powertodetectdifferencebetweengroups consideredtobeofclinicalinterest.The
University of Medicine and Dentistry of New Jersey - BINF - 5075
General Principles for Data Security in Clinical TrialsBINF5075Introduction In healthcare, data has broad public health significance; it is expected to be of the highest quality and integrity. This presentation provides guidance about compu
University of Medicine and Dentistry of New Jersey - BINF - 5075
Dates and TimesSAS Date, Time and DateTime FormatsDate StorageSAS stores Dates, Times and Date-Time values differently. Datetime: seconds between January 1, 1960 and an hour/minute/second within a specified date Time: seconds since midnight of
University of Medicine and Dentistry of New Jersey - BINF - 5075
478NADKARNIET AL.,EAV/CR Storage for Scientific DataApplication of Information TechnologyOrganization of Heterogeneous Scientific Data Using the EAV/CR RepresentationPRAKASH M. NADKARNI, MD, LUIS MARENCO, MD, ROLAND CHEN, MD, EMMANOUIL SKO
University of Medicine and Dentistry of New Jersey - BINF - 5075
PROC IMPORT OUT= WORK.Products DATATABLE= &quot;Products&quot; DBMS=ACCESS2000 REPLACE; DATABASE=&quot;C:\DataWarehousing05f\SASDataQuality.mdb&quot;; RUN; Proc Contents Data= Products; run; *; * Cleaning the supplier name. *; *; *; * Standardizing entry values. *; *; P
University of Medicine and Dentistry of New Jersey - BINF - 5075
Downloaded from emj.bmj.com on 12 December 2006Simple nomograms to calculate sample size in diagnostic studiesS Carley, S Dosman, S R Jones and M Harrison Emerg. Med. J. 2005;22;180-181 doi:10.1136/emj.2003.011148Updated information and services
University of Medicine and Dentistry of New Jersey - BINF - 5075
Downloaded from emj.bmj.com on 2 March 2007An introduction to power and sample size estimationS R Jones, S Carley and M Harrison Emerg. Med. J. 2003;20;453-458 doi:10.1136/emj.20.5.453Updated information and services can be found at: http:/emj.b
University of Medicine and Dentistry of New Jersey - BINF - 5075
TABLE OF CONTENTS Click on a link below: Catching data entry errors with SAS.2 Removing duplicate observations from a dataset using SAS..2 SAS missing values.3 Mean substitution for missing values in SAS.4 Recoding variable values into missing values
University of Medicine and Dentistry of New Jersey - BINF - 5075
INTRODUCTION TO SAS Module 1 Dr. Al Schwarzkopf EXERCISE 1: Running a program with an internal dataset Step 1. Start the SAS program. Step 2. Copy the program below into the Edit window. Step 3. Run the program using the Run icon. DATA FITDATA; INPUT
University of Medicine and Dentistry of New Jersey - BINF - 5075
Data One; Input ID \$ X Y1 ; Cards; A 1 1 B 2 2 B 3 3 D 4 4 E 0 0 ; Data Two; Input ID \$ X A2 ; Cards; A 5 5 A 6 6 B 7 7 C 8 8 E 11 11 E 11 11 ; run; Data Three; Merge One Two (drop= x); By ID; Proc Print Data= Three; Title3 'Merge One Two'; run; Data
University of Medicine and Dentistry of New Jersey - BINF - 5075
Paper CC12Data Transfer from Microsoft Access to SAS Made EasyZaizai Lu, AstraZeneca Pharmaceutical David Shen, ClinForce Inc.ABSTRACTTo transfer data from Microsoft Access database to SAS has never been easy. Unlike Oracle database, neither SAS
University of Medicine and Dentistry of New Jersey - BINF - 5075
EBM: TRIALS ON TRIALEBM: TRIALS ON TRIALDetermining the sample size in a clinical trialAdrienne Kirby, Val Gebski and Anthony C KeechSAMPLE SIZE MUST BE PLANNED carefully to ensure that the research time, patient effort and support costs invest
University of Medicine and Dentistry of New Jersey - BINF - 5075
Some Practical Guidelines for Effective Sample-Size DeterminationRussell V. Lenth Department of Statistics University of Iowa March 1, 2001Abstract Sample-size determination is often an important step in planning a statistical study-and it is usua
University of Medicine and Dentistry of New Jersey - BINF - 5075
Page 1 of 4Sample Relational Data Models for Clinical ResearchLab exercise: Use Microsoft Access to implement a &quot;one to many&quot; model Access 2002 1. 2. 3. 4. 5. 6. Access20007. 8. 9. 10. 11. 12. 13. 14. 15. 16.Step 1: Design Tables Open Access 1
Kenyon - MATH - 106
University of Medicine and Dentistry of New Jersey - BINF - 5312
Chapter 12 Graphical User Interface Concepts: Part 1Outline 12.1 Introduction 12.2 Windows Forms 12.3 EventHandling Model 12.3.1 Basic Event Handling 12.4 Control Properties and Layout 12.5 Labels, TextBoxes and Buttons 12.6 GroupBoxe
University of Medicine and Dentistry of New Jersey - BINF - 5312
Chapter 13 Graphical User Interfaces Part 2Outline 13.1 13.2 13.3 13.4 Introduction Menus LinkLabels ListBoxes and CheckedListBoxes 13.4.1 ListBoxes 13.4.2 CheckedListBoxes 13.5 ComboBoxes 13.6 TreeViews 13.7 ListViews 13.8 Tab
University of Medicine and Dentistry of New Jersey - BINF - 5312