RANKINGS AND MULTI-CRITERIA EVALUATION OF ALTERNATIVES: USAGE OF OBJECTIVE DATA, SUBJECTIVE MEASUREMENTS AND EXPERT JUDGMENT

Size: px
Start display at page:

Download "RANKINGS AND MULTI-CRITERIA EVALUATION OF ALTERNATIVES: USAGE OF OBJECTIVE DATA, SUBJECTIVE MEASUREMENTS AND EXPERT JUDGMENT"

Transcription

1 RANKINGS AND MULTI-CRITERIA EVALUATION OF ALTERNATIVES: USAGE OF OBJECTIVE DATA, SUBJECTIVE MEASUREMENTS AND EXPERT JUDGMENT Pavel Brusilovskiy and Robert Hernandez Risk Management, Conrail Corporation Abstract There are many problems that require full utilization of all available and useful information in order to achieve a comprehensive and systemic evaluation of alternatives. These sources are objective data, subjective measurements (i.e. survey), and expert judgment. Each type of information is reflected in the ordinal scale as an individual ranking (or rating) of the alternatives. Two different cases are considered: a) all individual rankings are treated equally important; b) each individual ranking has its own ranked weights. In the latter case the weights reflect in corresponding ordinal scale of a decision maker s preferences (confidence, reliability and/or importance) of the different types of information obtained. The paper is dedicated to better management decisions through the aggregation of different types of information. Introduction Ranking within uni-criterion evaluation of alternatives is a frequently used approach to assess performance. Some common examples of this approach are to assess the best books to read through the use of the best selling books list or to evaluate salespeople s performance based on number of sales orders. The uni-criterion evaluation for these uncomplicated issues offers a fair performance representation. However, many evaluation problems are complex and require a multi-criteria evaluation approach instead of a uni-criterion technique. Complex issues necessitate the utilization of all available and useful sources and types of information. Generally, they are objective data, subjective measurements and expert judgment. Each type of information offers valuable insight to the issues under consideration, but independently none of them provide decision makers with complete information. The goal of this article is to present a simple and general approach to multi-criteria evaluation of alternatives for non-statisticians. This approach is valuable for integrating qualitative and quantitative information in diverse fields, and in particular related to quality performance, marketing and risk. For example: Quality Of Health Care Among Hospitals There are many sources of information to evaluate the quality of health care among hospitals. Objective data could be treatment success measures and corresponding cost related measures. Subjective measurements consist of special patient survey results. Expert judgment can be obtained from Quality Health Care professionals. Market Segmentation and Product Positioning There are many sources of information to evaluate existing products for each market segment. Objective data could be related to product attributes. Subjective measurements are consumers preferences, and expert judgment can be provided by professionals in appropriate field. A Risk Assessment and Risk Reduction example should clarify the importance of viewing the information at a comprehensive level. Risk Assessment and Risk Reduction Example Let s examine a risk management problem associated with the personal injury risk assessment in a large industrial company. Our major issue is to identify the safety districts with the highest degree of risk. An assessment procedure must take into account the two dimensions of risk. The first dimension reflects likelihood of occurrence of unfavorable event and the second dimension reflects consequences of this event [6]. Data and information sources for these two dimensions consist of three possible types which are objective data, subjective measurements and expert judgment. Each type of information offers valuable insight to a company s risk exposure, but independently none of these types of information can provide decision makers with a comprehensive risk exposure background. 1

2 Objective data Degree of risk can be characterized for each safety district in the company by several objective attributes: Personal injury rate reflects the probability of unfavorable event occurrence (first dimension of risk) Average settlement cost reflects medical and litigation expenses (one component associated with the second dimension of risk) Average amount of days disabled reflects lost manhours (another component associated with the second dimension of risk) Subjective measurements Important aspects of the personal injury process are safety training, work organization, behavioral features including inclination to risk and management-employee relations. Employee surveys can be used to evaluate the personal injury process. Subjective measurements as corresponding scores gauge important insight of personal injury process from employees point of view. This type of information represents local and subjective vision of the personal injury process, who are not experts in Risk Management. Expert Judgment Experts are individuals that have a special education, deep knowledge, and possess global vision of the personal injury process at a company level and within each safety district. They are able to take in account production or service technology, workers union affiliation structure, geographical location of a safety district, safety culture, management style and other latent conditions not found in objective data and subjective measurements. From this global perspective, the experts would rank safety districts according to the degree of personal injury risk. Each of these attributes or criteria are different and relatively independent components of the personal injury process. Separately, none of these criterion have the capability of providing decision makers with a comprehensive reflection to the degree of personal injury risk for each safety district. An adequate approach has to combine information from different sources. Our approach described in the following sections fulfills this requirement and is practical and non-consuming. Original Data Description The appropriate objective data, subjective measurements and expert judgment were collected for 14 safety districts within the company. Objective Data are presented by three interval-scaled variables INJ_RATE, SET_COST and DIS_DAYS. INJ_RATE measures number of injuries in a safety district for the last two years divided by total labor hours for the last two years. SET_COST measures average settlement cost among personal injuries in each safety district for the last two years. DIS_DAYS measures average number of days disabled in each safety district for the last two years. Subjective measurement data are depicted by one ordinally-scaled variable EMP_RATG. This variable measures average safety satisfaction for all employee responses in each safety district. The safety satisfaction is estimated on 100 points scale and the question is simply, How you would rate your satisfaction with safety where you work? The higher satisfaction rate a safety district has the less degree of risk associated with that district. Note: Ordinal scale means there is an ordering to levels, but distance between adjacent levels is not distinct. Expert judgment data are characterized by one ordinally scaled variable EXP_JUDG. This variable represents expert s safety district ranking. The higher rank a safety district has the greater degree of risk associated with that district. Raw Data We read the raw data into a SAS data set named PI_ASSES: libname risk c:\ INJURY ; options nodate linesize=76; data risk.pi_asses; input sftydist $ 25. inj_rate set_cost dis_days emp_ratg exp_judg; datalines; CAR SHOP LOCOMOTIVE SHOP LOCOMOTIVE ENGINEERS ; proc print data=risk.pi_asses; title Original Data For Risk Assessment ; These data and proc steps produced Output 1 on Page 3. 2

3 OUTPUT 1 Original Data For Risk Assessment OBS SFTYDIST INJ RATE SET COST DIS DAYS EMP RATG EXP JUDG 1 CAR SHOP LOCOMOTIVE SHOP MAINTENANCE OF WAY STORE ROOM MECHANICAL ENGINEERING INDUSTRIAL ENGINEERING CAR INSPECTORS LOCOMOTIVE INSPECTORS CIVIL ENGINEERING ROAD SIGNAL DATS GANG BRIDGE INSPECTORS TRACK GANG LOCOMOTIVE ENGINEERS Conversion to Rankings Most numeric variables in the risk.pi_asses data set will be converted to rank variables. The values of a rank variable are ranks, from 1 to n. To perform this conversion process, we need to exploit PROC RANK from the SAS Base software: /* Rank conversion for variables INJ_RATE, */ /* SET_COST, DIS_DAYS and EXP_JUDG */ /* is performed according to the rule: Original variable*/ /* values will be ranked from smallest to largest, */ /* assigning the rank 1 to the smallest value, 2 to the */ /* next smallest, and so on up to rank n */ /* *******************************************/ proc rank data =risk.pi_asses out=pi_rank1; ranks r_injury r_cost r_days r_judg; var INJ_RATE SET_COST DIS_DAYS EXP_JUDG; /* Rank Conversion for variable EMP_RATG is */ /* according to the rule: Original variable values will */ /* be from largest to smallest, assigning rank 1 to */ /* the largest value, 2 to next largest, and so on up to */ /* rank n */ proc rank data=risk.pi_asses out=pi_rank2 descending; ranks r_emp ; var EMP_RATG ; /* Merge pi_rank1 and pi_rank2 datasets into one */ /* dataset named risk.pi_ranks */ data risk.pi_ranks; title 'Personal Injury Rankings Data'; merge pi_rank1 pi_rank2; /* Prefix R indicates rank variable */ keep sftydist r_injury r_cost r_days r_emp r_judg; proc print data=risk.pi_ranks; These data and proc steps produced Output 2 on Page 4. 3

4 OUTPUT 2 Personal Injury Rankings Data OBS SFTYDIST R INJURY R COST R DAYS R JUDG R EMP 1 CAR SHOP LOCOMOTIVE SHOP MAINTENANCE OF WAY STORE ROOM MECHANICAL ENGINEERING INDUSTRIAL ENGINEERING CAR INSPECTORS LOCOMOTIVE INSPECTORS CIVIL ENGINEERING ROAD SIGNAL DATS GANG BRIDGE INSPECTORS TRACK GANG LOCOMOTIVE ENGINEERS Decision Making a) Aggregation of individual rankings: each criterion is equally weighted in importance Reviewing output 2, we can see that the Store Room safety district has the lowest degree of personal injury risk according to the injury rate (R_INJURY) and employee rate (R_EMP). But according to the criterion disabled days (R_DAYS), this district has a high level of personal injury risk compared to the other safety districts. The two other criteria R_COST and R_JUDG have lower ranks than R_DAYS, but higher ranks then R_INJURY and R_EMP. This is a common situation when a value for one criterion contradicts a value of another one. To overcome the contradiction problem, we need to employ one of the rankings aggregation method. A simple but rather useful method for this problem is the average ranking technique. The technique is a two step process when we are under the assumption that importance is equally weighted for each criterion. First step is to calculate average rank for each alternative (safety district) and then the second step is to construct their final multi-criteria rankings. data final1; set risk.pi_ranks; avgrank1=mean( r_injury, r_cost, r_days, r_emp, r_judg); keep sftydist avgrank1; 4 proc rank data=final1 out=risk.pifinal1; title Aggregation of Individual Ranking: Equal Weights of the Criteria ; ranks r_final1; var avgrank1; proc print data=risk.pifinal1; This data and proc steps produce the Output 3. OUTPUT 3 Aggregation Of Individual Ranking: Equal Weights Of The Criteria OBS SFTYDIST AVGRANK1 R FINAL1 1 CAR SHOP LOCOMOTIVE SHOP MAINTENANCE OF WAY STORE ROOM MECHANICAL ENGINEERING INDUSTRIAL ENGINEERING CAR INSPECTORS LOCOMOTIVE INSPECTORS CIVIL ENGINEERING ROAD SIGNAL DATS GANG BRIDGE INSPECTORS TRACK GANG LOCOMOTIVE ENGINEERS The final multi-criteria ranking in Output 3 shows that the Bridge Inspector safety district has lowest degree of risk and Industrial Engineering safety district has the highest degree of risk. There are also three safety districts, Locomotive Shop, Maintenance of Way and Track

5 Gangs, with the same degree of personal injury risk (tied ranks). The ranking approach is more than just recognizing who is the best and the worst. The intent of this approach is to provide decision makers with a comprehensive (multi-criteria) view to make better decisions. In output 3, the multi-criteria ranking information clearly illustrate that Industrial Engineering and Road Signal have the highest overall personal injury risk. For a substantial reduction in overall personal injury risk, management must at least have some action plans associated with the several safety districts holding the highest overall personal injury risk. b) Aggregation of individual rankings: each criterion has its own weight In the previous paragraph, we considered each criterion to be equally weighted in importance. Let us assume in the next example that each criterion holds different levels of importance or priority. Decision Maker may decide that operating cost has the highest priority within the company and prioritize the criteria accordingly. In our example, this operating cost initiative would mean that we would place higher priorities on settlement costs and disabled days. If technology is the number issue then we would place a higher priority on Expert Judgment. The information below is based on operating cost as the highest priority for the company and is provided by Decision Maker: Table 1. Decision Maker Priorities of Criteria Criterion Priority INJ_RATE 4 SET_COST 1 DIS_DAYS 2 EMP_RATG 3 EXP_JUDG 5 Note: Criteria with lower rank has a higher priority. This information can be converted to weights w(i) according to the rank-sum rule [1]: n+ 1 i 2*( n+ 1 i) wi () = = j n*( n+ 1) i=1,...,n For our example n=5, and DIS_DAYS has a priority of 2. Its calculated weight is the following: w( 2) = 2*( ) = *( 5+ 1) To calculate weights using formula (1), we need to submit the following code: data weights; title 'Criteria Weights'; do priority =1 to 5; w=2*(5+1-priority)/(5*6); output; end; proc print data=weights; The results are presented in Output 4. OUTPUT 4 Criteria Weights OBS PRIORITY W Now we need to calculate linear combinations of all rankings in Output 2 (Page 5) with the criteria weights in Output 4. The results are the weighted averages from the criteria rankings. The next step will encompass the conversion of the weighted averages from the individual criteria rankings to multi-criteria ranking. We will again use the RANK procedure to obtain the multi-criteria ranking. data risk.final2; set risk.pi_ranks; array weight(5) w1-w5; array r_criter(5) R_COST R_DAYS R_INJURY R_EMP R_JUDG; where n is the number of criteria, i is a priority of ith criterion. (1) (See the rest of code on the next page) 5

6 (continued from previous page) /* The order of the R_variables in the array statement */ /* array r_criter(5) has to correspond to the ranks of the*/ /* criteria in Table 1. */ avgrank2=0; do priority=1 to 5; weight(priority)=2*(5+1-priority)/(5*6); avgrank2= weight(priority)*r_criter(priority) + avgrank2; end; keep sftydist avgrank2; proc rank data=risk.final2 out=risk.pifinal2; ranks r_final2; var avgrank2; proc print data=risk.pifinal2; title 'Aggregation of Individual Rankings: Nonequal Weights of the Criteria'; OUTPUT 5 Aggregation Of Individual Rankings: Nonequal Weights Of The Criteria OBS SFTYDIST AVG_RANK2 R_FINAL2 1 CAR SHOP LOCOMOTIVE SHOP MAINTENANCE OF WAY STORE ROOM MECHANICAL ENGINEERING INDUSTRIAL ENGINEERING CAR INSPECTORS LOCOMOTIVE INSPECTORS CIVIL ENGINEERING ROAD SIGNAL DATS GANG BRIDGE INSPECTORS TRACK GANG LOCOMOTIVE ENGINEERS Naturally, the final ranking from R_FINAL2 depends on the decision maker s priorities. We can determine the correlation between equally weighted and non-equally weighted rankings. R_FINAL2 strongly correlates with R_FINAL1 on Output 2 (Page 6). The Spearman s correlation coefficient between these two variables is Below is the SAS coding to check the correlation between the two final ranking variables. In our example, multi-criteria rankings have basically the same rank order. However, other priorities may have multi-criteria rankings that do not strongly correlate with one another. If this is the case then priority information from the decision maker can be essential for multi-criteria ranking. Comparing equally weighted and non-equally weighted rankings improve the decision maker s understanding of the complex issues in terms of priority and ranking data allfinal; merge risk.pifinal1 risk.pifinal2; keep r_final1 r_final2; proc corr data=allfinal spearman; var r_final1; with r_final2; Discussion In this section we will discuss advantages and disadvantages of the approach described, some generalization and related literature. Advantages The approach works well also in the present of rank ties. Rank ties are interpreted as the same level of importance for decision maker priorities and/or criteria preferences for alternatives under consideration. There might be a requirement to add more information from several experts and/or subjective attributes. This approach easily can take in account this modification. A more sophisticated approach like path analysis can be applied to objective analysis of subjective measurements. Several path coefficients could be included in the multi-criteria ranking process of the alternatives. See [3] for more details on path analysis. Disadvantage Our general concern with the conversion process is the lost of some useful information through ranking. In the example, all variables except for EXP_JUDG variable can be less informative after the conversion process. The EXP_JUDG variable is measured in rank scale and there is no loss of information at all. Loss of information during the conversion process mainly depends on the degree of accuracy and objectivity of the measured variable in its primary scale. In our case, interval scaled variable INJ_RATE is measured without any random error and therefore is considered to be 100 percent accurate. The high accuracy level may lead to some shrinkage of useful information during the conversion process. Interval scaled variables SET_COST and DIS_DAYS have a subjective component related to 6

7 plaintiff compensation practices in local jurisdictions. This subjective component in these variables lower the objectivity level. Conversion of these variables will probably have no deterioration of information due to the low degree of measurement objectivity. Overall, we intentionally sacrifice some information but in return gain more simplicity to work with multi-criteria issues. Optimal properties of multi-criteria ranking The multi-criteria ranking possesses the following two properties: The mean value of Spearman correlation coefficients between each criterion ranking in Output 2 and final ranking (R_FINAL1) in Output 3 is maximum. The multi-criteria ranking is also optimal as a least square estimator. See footnote [5] for more details Other approaches to multi-criteria ranking There are several different approaches to multi-criteria ranking. Another popular approach of multi-criteria evaluation in ranking scale is the so called axiomatic one. It is based on the concept of Kemeny median. Difference between the approach described in this paper and the axiomatic approach is approximately the same as the difference between mean and median in the location parameter estimation problem. See [4] for more details. Weights and Priorities Several different methods are developed to take criteria priorities into account. To calculate weights w(i), we have used one of the simplest formula. See [1] for comparison of different weighting methods. Criteria rankings concordance In order to test a concordance among separate criteria rankings, it is necessary to use Kendall's W coefficient of concordance. The SAS system does not provide this test but it can be easily performed within the SAS system independently See [6] for more detail on Kendall s W coefficient of concordance. Objective data and expert judgment References 1. Barrett Bruce E.and F.H. Barron, "Decision Quality Using Ranked AttributeWeights," Management Science, November 1996, pp Brusilovskiy Pavel.M. and Tilman Leo.M., "Incorporating Expert Judgement into Multivariate Polynomial Modeling," Decision Support Systems, Vol. 18 (1996), pp Hatcher, Larry. A Step-by-step Approach to Using the SAS System for Factor Analysis and Structural Equation Modeling. Cary, NC: SAS Institute Inc., Kemeny J.G. and Snell J.L. Mathematical Models in the Social Sciences. New York: Blaisdell Publishing Company. 5. Kendall,Maurice.G. Rank Correlation Methods. Griffin London, Moore, Peter G. The Business of Risk. Great Britian: Cambridge University Press, SAS Institute Inc., SAS Procedures Guide, Version 6, Third Edition, Cary, NC: SAS Institute Inc., 1990, pp 750. Author Contacts Pavel Brusilovskiy Conrail Corporation 2001 Market Street 6-D P.O. Box Phildelphia, PA (215) pbrusilovs@aol.com Robert Hernandez Conrail Corporation 2001 Market Street 14-C P.O. Box Philadelphia, PA (215) RHer1@aol.com See [2] for a more sophisticated usage of objective data and expert judgment. 7

Selection of Best Web Site by Applying COPRAS-G method Bindu Madhuri.Ch #1, Anand Chandulal.J #2, Padmaja.M #3

Selection of Best Web Site by Applying COPRAS-G method Bindu Madhuri.Ch #1, Anand Chandulal.J #2, Padmaja.M #3 Selection of Best Web Site by Applying COPRAS-G method Bindu Madhuri.Ch #1, Anand Chandulal.J #2, Padmaja.M #3 Department of Computer Science & Engineering, Gitam University, INDIA 1. binducheekati@gmail.com,

More information

Advanced Search Techniques for Large Scale Data Analytics Pavel Zezula and Jan Sedmidubsky Masaryk University

Advanced Search Techniques for Large Scale Data Analytics Pavel Zezula and Jan Sedmidubsky Masaryk University Advanced Search Techniques for Large Scale Data Analytics Pavel Zezula and Jan Sedmidubsky Masaryk University http://disa.fi.muni.cz The Cranfield Paradigm Retrieval Performance Evaluation Evaluation Using

More information

Week 7 Picturing Network. Vahe and Bethany

Week 7 Picturing Network. Vahe and Bethany Week 7 Picturing Network Vahe and Bethany Freeman (2005) - Graphic Techniques for Exploring Social Network Data The two main goals of analyzing social network data are identification of cohesive groups

More information

Organizing Your Data. Jenny Holcombe, PhD UT College of Medicine Nuts & Bolts Conference August 16, 3013

Organizing Your Data. Jenny Holcombe, PhD UT College of Medicine Nuts & Bolts Conference August 16, 3013 Organizing Your Data Jenny Holcombe, PhD UT College of Medicine Nuts & Bolts Conference August 16, 3013 Learning Objectives Identify Different Types of Variables Appropriately Naming Variables Constructing

More information

Slide Copyright 2005 Pearson Education, Inc. SEVENTH EDITION and EXPANDED SEVENTH EDITION. Chapter 13. Statistics Sampling Techniques

Slide Copyright 2005 Pearson Education, Inc. SEVENTH EDITION and EXPANDED SEVENTH EDITION. Chapter 13. Statistics Sampling Techniques SEVENTH EDITION and EXPANDED SEVENTH EDITION Slide - Chapter Statistics. Sampling Techniques Statistics Statistics is the art and science of gathering, analyzing, and making inferences from numerical information

More information

Data analysis using Microsoft Excel

Data analysis using Microsoft Excel Introduction to Statistics Statistics may be defined as the science of collection, organization presentation analysis and interpretation of numerical data from the logical analysis. 1.Collection of Data

More information

Chapter X Security Performance Metrics

Chapter X Security Performance Metrics Chapter X Security Performance Metrics Page 1 of 10 Chapter X Security Performance Metrics Background For many years now, NERC and the electricity industry have taken actions to address cyber and physical

More information

CHAPTER 4 MAINTENANCE STRATEGY SELECTION USING TOPSIS AND FUZZY TOPSIS

CHAPTER 4 MAINTENANCE STRATEGY SELECTION USING TOPSIS AND FUZZY TOPSIS 59 CHAPTER 4 MAINTENANCE STRATEGY SELECTION USING TOPSIS AND FUZZY TOPSIS 4.1 INTRODUCTION The development of FAHP-TOPSIS and fuzzy TOPSIS for selection of maintenance strategy is elaborated in this chapter.

More information

Mean Tests & X 2 Parametric vs Nonparametric Errors Selection of a Statistical Test SW242

Mean Tests & X 2 Parametric vs Nonparametric Errors Selection of a Statistical Test SW242 Mean Tests & X 2 Parametric vs Nonparametric Errors Selection of a Statistical Test SW242 Creation & Description of a Data Set * 4 Levels of Measurement * Nominal, ordinal, interval, ratio * Variable Types

More information

USING PRINCIPAL COMPONENTS ANALYSIS FOR AGGREGATING JUDGMENTS IN THE ANALYTIC HIERARCHY PROCESS

USING PRINCIPAL COMPONENTS ANALYSIS FOR AGGREGATING JUDGMENTS IN THE ANALYTIC HIERARCHY PROCESS Analytic Hierarchy To Be Submitted to the the Analytic Hierarchy 2014, Washington D.C., U.S.A. USING PRINCIPAL COMPONENTS ANALYSIS FOR AGGREGATING JUDGMENTS IN THE ANALYTIC HIERARCHY PROCESS Natalie M.

More information

Graph Theory for Modelling a Survey Questionnaire Pierpaolo Massoli, ISTAT via Adolfo Ravà 150, Roma, Italy

Graph Theory for Modelling a Survey Questionnaire Pierpaolo Massoli, ISTAT via Adolfo Ravà 150, Roma, Italy Graph Theory for Modelling a Survey Questionnaire Pierpaolo Massoli, ISTAT via Adolfo Ravà 150, 00142 Roma, Italy e-mail: pimassol@istat.it 1. Introduction Questions can be usually asked following specific

More information

DISCUSSION PAPER. Board of Certification Oral Examination Consistency

DISCUSSION PAPER. Board of Certification Oral Examination Consistency DISCUSSION PAPER Issue : Prepared for: Board of Certification Oral Examination istency CIPHI - Board of Certification Date: June 20, 2003 BACKGROUND The Certificate in Public Health Inspection (Canada),

More information

This PDF was generated from the Evaluate section of

This PDF was generated from the Evaluate section of Toolkit home What is inclusive design? Why do inclusive design? How to design inclusively Overview Map of key activities Manage This PDF was generated from the Evaluate section of www.inclusivedesigntoolkit.com

More information

B.2 Measures of Central Tendency and Dispersion

B.2 Measures of Central Tendency and Dispersion Appendix B. Measures of Central Tendency and Dispersion B B. Measures of Central Tendency and Dispersion What you should learn Find and interpret the mean, median, and mode of a set of data. Determine

More information

Data Analysis and Solver Plugins for KSpread USER S MANUAL. Tomasz Maliszewski

Data Analysis and Solver Plugins for KSpread USER S MANUAL. Tomasz Maliszewski Data Analysis and Solver Plugins for KSpread USER S MANUAL Tomasz Maliszewski tmaliszewski@wp.pl Table of Content CHAPTER 1: INTRODUCTION... 3 1.1. ABOUT DATA ANALYSIS PLUGIN... 3 1.3. ABOUT SOLVER PLUGIN...

More information

Multi-Criteria Decision Making 1-AHP

Multi-Criteria Decision Making 1-AHP Multi-Criteria Decision Making 1-AHP Introduction In our complex world system, we are forced to cope with more problems than we have the resources to handle We a framework that enable us to think of complex

More information

Statistics, Data Analysis & Econometrics

Statistics, Data Analysis & Econometrics ST009 PROC MI as the Basis for a Macro for the Study of Patterns of Missing Data Carl E. Pierchala, National Highway Traffic Safety Administration, Washington ABSTRACT The study of missing data patterns

More information

Department of Management Services REQUEST FOR INFORMATION

Department of Management Services REQUEST FOR INFORMATION RESPONSE TO Department of Management Services REQUEST FOR INFORMATION Cyber-Security Assessment, Remediation, and Identity Protection, Monitoring, and Restoration Services September 3, 2015 250 South President

More information

Nuts and Bolts Research Methods Symposium

Nuts and Bolts Research Methods Symposium Organizing Your Data Jenny Holcombe, PhD UT College of Medicine Nuts & Bolts Conference August 16, 3013 Topics to Discuss: Types of Variables Constructing a Variable Code Book Developing Excel Spreadsheets

More information

All-Hazards Approach to Water Sector Security & Preparedness ANSI-HSSP Arlington, VA November 9, 2011

All-Hazards Approach to Water Sector Security & Preparedness ANSI-HSSP Arlington, VA November 9, 2011 All-Hazards Approach to Water Sector Security & Preparedness ANSI-HSSP Arlington, VA November 9, 2011 Copyright 2009 American Water Works Association Copyright 2011 American Water Works Association Security

More information

CHAPTER THREE INFORMATION RETRIEVAL SYSTEM

CHAPTER THREE INFORMATION RETRIEVAL SYSTEM CHAPTER THREE INFORMATION RETRIEVAL SYSTEM 3.1 INTRODUCTION Search engine is one of the most effective and prominent method to find information online. It has become an essential part of life for almost

More information

Information Retrieval Rank aggregation. Luca Bondi

Information Retrieval Rank aggregation. Luca Bondi Rank aggregation Luca Bondi Motivations 2 Metasearch For a given query, combine the results from different search engines Combining ranking functions Text, links, anchor text, page title, etc. Comparing

More information

IBM SPSS Categories. Predict outcomes and reveal relationships in categorical data. Highlights. With IBM SPSS Categories you can:

IBM SPSS Categories. Predict outcomes and reveal relationships in categorical data. Highlights. With IBM SPSS Categories you can: IBM Software IBM SPSS Statistics 19 IBM SPSS Categories Predict outcomes and reveal relationships in categorical data Highlights With IBM SPSS Categories you can: Visualize and explore complex categorical

More information

Buros Center for Testing. Standards for Accreditation of Testing Programs

Buros Center for Testing. Standards for Accreditation of Testing Programs Buros Center for Testing Standards for Accreditation of Testing Programs Improving the Science and Practice of Testing www.buros.org Copyright 2017 The Board of Regents of the University of Nebraska and

More information

Want to Do a Better Job? - Select Appropriate Statistical Analysis in Healthcare Research

Want to Do a Better Job? - Select Appropriate Statistical Analysis in Healthcare Research Want to Do a Better Job? - Select Appropriate Statistical Analysis in Healthcare Research Liping Huang, Center for Home Care Policy and Research, Visiting Nurse Service of New York, NY, NY ABSTRACT The

More information

An Introduction to Analysis (and Repository) Databases (ARDs)

An Introduction to Analysis (and Repository) Databases (ARDs) An Introduction to Analysis (and Repository) TM Databases (ARDs) Russell W. Helms, Ph.D. Rho, Inc. Chapel Hill, NC RHelms@RhoWorld.com www.rhoworld.com Presented to DIA-CDM: Philadelphia, PA, 1 April 2003

More information

Predict Outcomes and Reveal Relationships in Categorical Data

Predict Outcomes and Reveal Relationships in Categorical Data PASW Categories 18 Specifications Predict Outcomes and Reveal Relationships in Categorical Data Unleash the full potential of your data through predictive analysis, statistical learning, perceptual mapping,

More information

TOPSIS Modification with Interval Type-2 Fuzzy Numbers

TOPSIS Modification with Interval Type-2 Fuzzy Numbers BULGARIAN ACADEMY OF SCIENCES CYBERNETICS AND INFORMATION TECHNOLOGIES Volume 6, No 2 Sofia 26 Print ISSN: 3-972; Online ISSN: 34-48 DOI:.55/cait-26-2 TOPSIS Modification with Interval Type-2 Fuzzy Numbers

More information

Six Sigma in the datacenter drives a zero-defects culture

Six Sigma in the datacenter drives a zero-defects culture Six Sigma in the datacenter drives a zero-defects culture Situation Like many IT organizations, Microsoft IT wants to keep its global infrastructure available at all times. Scope, scale, and an environment

More information

The NESTED Procedure (Chapter)

The NESTED Procedure (Chapter) SAS/STAT 9.3 User s Guide The NESTED Procedure (Chapter) SAS Documentation This document is an individual chapter from SAS/STAT 9.3 User s Guide. The correct bibliographic citation for the complete manual

More information

A new international standard for data validation and processing

A new international standard for data validation and processing A new international standard for data validation and processing Marco Pellegrino (marco.pellegrino@ec.europa.eu) 1 Keywords: Data validation, transformation, open standards, SDMX, GSIM 1. INTRODUCTION

More information

In the recent past, the World Wide Web has been witnessing an. explosive growth. All the leading web search engines, namely, Google,

In the recent past, the World Wide Web has been witnessing an. explosive growth. All the leading web search engines, namely, Google, 1 1.1 Introduction In the recent past, the World Wide Web has been witnessing an explosive growth. All the leading web search engines, namely, Google, Yahoo, Askjeeves, etc. are vying with each other to

More information

Usability Evaluation of Software Testing Based on Analytic Hierarchy Process Dandan HE1, a, Can WANG2

Usability Evaluation of Software Testing Based on Analytic Hierarchy Process Dandan HE1, a, Can WANG2 4th International Conference on Machinery, Materials and Computing Technology (ICMMCT 2016) Usability Evaluation of Software Testing Based on Analytic Hierarchy Process Dandan HE1, a, Can WANG2 1,2 Department

More information

CREATION OF THE RATING OF STOCK MARKET ANALYTICAL SYSTEMS ON THE BASE OF EXPERT QUALITATIVE ESTIMATIONS

CREATION OF THE RATING OF STOCK MARKET ANALYTICAL SYSTEMS ON THE BASE OF EXPERT QUALITATIVE ESTIMATIONS CREATION OF THE RATIN OF STOCK MARKET ANALYTICAL SYSTEMS ON THE BASE OF EXPERT QUALITATIVE ESTIMATIONS Olga A. Siniavsaya, Boris A. Zhelezo, Roman V. Karpovich* Belorussian State Economic University 220672

More information

Choosing the Right Procedure

Choosing the Right Procedure 3 CHAPTER 1 Choosing the Right Procedure Functional Categories of Base SAS Procedures 3 Report Writing 3 Statistics 3 Utilities 4 Report-Writing Procedures 4 Statistical Procedures 5 Efficiency Issues

More information

SAS/STAT 13.1 User s Guide. The NESTED Procedure

SAS/STAT 13.1 User s Guide. The NESTED Procedure SAS/STAT 13.1 User s Guide The NESTED Procedure This document is an individual chapter from SAS/STAT 13.1 User s Guide. The correct bibliographic citation for the complete manual is as follows: SAS Institute

More information

Operationalizing Cybersecurity in Healthcare IT Security & Risk Management Study Quantitative and Qualitative Research Program Results

Operationalizing Cybersecurity in Healthcare IT Security & Risk Management Study Quantitative and Qualitative Research Program Results Operationalizing Cybersecurity in Healthcare - - 2017 IT Security & Risk Management Study Quantitative and Qualitative Research Program Results David S. Finn, CISA, CISM, CRISC Health IT Officer, Symantec

More information

THE EFFECT OF JOIN SELECTIVITIES ON OPTIMAL NESTING ORDER

THE EFFECT OF JOIN SELECTIVITIES ON OPTIMAL NESTING ORDER THE EFFECT OF JOIN SELECTIVITIES ON OPTIMAL NESTING ORDER Akhil Kumar and Michael Stonebraker EECS Department University of California Berkeley, Ca., 94720 Abstract A heuristic query optimizer must choose

More information

Engagement Portal. Physician Engagement User Guide Press Ganey Associates, Inc.

Engagement Portal. Physician Engagement User Guide Press Ganey Associates, Inc. Engagement Portal Physician Engagement User Guide 2015 Press Ganey Associates, Inc. Contents Logging In... 3 Summary Dashboard... 4 Results For... 5 Filters... 6 Summary Page Engagement Tile... 7 Summary

More information

Chapter Two: Descriptive Methods 1/50

Chapter Two: Descriptive Methods 1/50 Chapter Two: Descriptive Methods 1/50 2.1 Introduction 2/50 2.1 Introduction We previously said that descriptive statistics is made up of various techniques used to summarize the information contained

More information

Choosing the Right Procedure

Choosing the Right Procedure 3 CHAPTER 1 Choosing the Right Procedure Functional Categories of Base SAS Procedures 3 Report Writing 3 Statistics 3 Utilities 4 Report-Writing Procedures 4 Statistical Procedures 6 Available Statistical

More information

Applied Statistics for the Behavioral Sciences

Applied Statistics for the Behavioral Sciences Applied Statistics for the Behavioral Sciences Chapter 2 Frequency Distributions and Graphs Chapter 2 Outline Organization of Data Simple Frequency Distributions Grouped Frequency Distributions Graphs

More information

Advanced IT Risk, Security management and Cybercrime Prevention

Advanced IT Risk, Security management and Cybercrime Prevention Advanced IT Risk, Security management and Cybercrime Prevention Course Goal and Objectives Information technology has created a new category of criminality, as cybercrime offers hackers and other tech-savvy

More information

Computer Aided Draughting and Design: Graded Unit 1

Computer Aided Draughting and Design: Graded Unit 1 Higher National Graded Unit Specification General Information for Centres This Graded Unit has been validated as part of the HNC Computer Aided Draughting and Design (CADD) award. Centres are required

More information

SOC 2 examinations and SOC for Cybersecurity examinations: Understanding the key distinctions

SOC 2 examinations and SOC for Cybersecurity examinations: Understanding the key distinctions SOC 2 examinations and SOC for Cybersecurity examinations: Understanding the key distinctions DISCLAIMER: The contents of this publication do not necessarily reflect the position or opinion of the American

More information

A Graph Theoretic Approach to Image Database Retrieval

A Graph Theoretic Approach to Image Database Retrieval A Graph Theoretic Approach to Image Database Retrieval Selim Aksoy and Robert M. Haralick Intelligent Systems Laboratory Department of Electrical Engineering University of Washington, Seattle, WA 98195-2500

More information

CLUSTER ANALYSIS. V. K. Bhatia I.A.S.R.I., Library Avenue, New Delhi

CLUSTER ANALYSIS. V. K. Bhatia I.A.S.R.I., Library Avenue, New Delhi CLUSTER ANALYSIS V. K. Bhatia I.A.S.R.I., Library Avenue, New Delhi-110 012 In multivariate situation, the primary interest of the experimenter is to examine and understand the relationship amongst the

More information

CS513-Data Mining. Lecture 2: Understanding the Data. Waheed Noor

CS513-Data Mining. Lecture 2: Understanding the Data. Waheed Noor CS513-Data Mining Lecture 2: Understanding the Data Waheed Noor Computer Science and Information Technology, University of Balochistan, Quetta, Pakistan Waheed Noor (CS&IT, UoB, Quetta) CS513-Data Mining

More information

The J100 RAMCAP Method

The J100 RAMCAP Method The J100 RAMCAP Method 2012 ORWARN Conference Kevin M. Morley, PhD Security & Preparedness Program Manager AWWA--Washington, DC Water is Key to Daily Life Potable drinking water Sanitation Public Health

More information

Chapter X Security Performance Metrics

Chapter X Security Performance Metrics Chapter X Security Performance Metrics Page 1 of 9 Chapter X Security Performance Metrics Background For the past two years, the State of Reliability report has included a chapter for security performance

More information

CHAPTER 3 A FAST K-MODES CLUSTERING ALGORITHM TO WAREHOUSE VERY LARGE HETEROGENEOUS MEDICAL DATABASES

CHAPTER 3 A FAST K-MODES CLUSTERING ALGORITHM TO WAREHOUSE VERY LARGE HETEROGENEOUS MEDICAL DATABASES 70 CHAPTER 3 A FAST K-MODES CLUSTERING ALGORITHM TO WAREHOUSE VERY LARGE HETEROGENEOUS MEDICAL DATABASES 3.1 INTRODUCTION In medical science, effective tools are essential to categorize and systematically

More information

Mobile Cloud Multimedia Services Using Enhance Blind Online Scheduling Algorithm

Mobile Cloud Multimedia Services Using Enhance Blind Online Scheduling Algorithm Mobile Cloud Multimedia Services Using Enhance Blind Online Scheduling Algorithm Saiyad Sharik Kaji Prof.M.B.Chandak WCOEM, Nagpur RBCOE. Nagpur Department of Computer Science, Nagpur University, Nagpur-441111

More information

Information Criteria Methods in SAS for Multiple Linear Regression Models

Information Criteria Methods in SAS for Multiple Linear Regression Models Paper SA5 Information Criteria Methods in SAS for Multiple Linear Regression Models Dennis J. Beal, Science Applications International Corporation, Oak Ridge, TN ABSTRACT SAS 9.1 calculates Akaike s Information

More information

JMASM35: A Percentile-Based Power Method: Simulating Multivariate Non-normal Continuous Distributions (SAS)

JMASM35: A Percentile-Based Power Method: Simulating Multivariate Non-normal Continuous Distributions (SAS) Journal of Modern Applied Statistical Methods Volume 15 Issue 1 Article 42 5-1-2016 JMASM35: A Percentile-Based Power Method: Simulating Multivariate Non-normal Continuous Distributions (SAS) Jennifer

More information

Jessica J. Schuler Department of Resource Analysis, Saint Mary s University of Minnesota, Minneapolis, MN 55404

Jessica J. Schuler Department of Resource Analysis, Saint Mary s University of Minnesota, Minneapolis, MN 55404 Metadata Management: Visualization of Data Relationships Jessica J. Schuler Department of Resource Analysis, Saint Mary s University of Minnesota, Minneapolis, MN 55404 Keywords: Geographic Information

More information

Introduction Entity Match Service. Step-by-Step Description

Introduction Entity Match Service. Step-by-Step Description Introduction Entity Match Service In order to incorporate as much institutional data into our central alumni and donor database (hereafter referred to as CADS ), we ve developed a comprehensive suite of

More information

INDEPENDENT SCHOOL DISTRICT 196 Rosemount, Minnesota Educating our students to reach their full potential

INDEPENDENT SCHOOL DISTRICT 196 Rosemount, Minnesota Educating our students to reach their full potential INDEPENDENT SCHOOL DISTRICT 196 Rosemount, Minnesota Educating our students to reach their full potential MINNESOTA MATHEMATICS STANDARDS Grades 9, 10, 11 I. MATHEMATICAL REASONING Apply skills of mathematical

More information

Error Analysis, Statistics and Graphing

Error Analysis, Statistics and Graphing Error Analysis, Statistics and Graphing This semester, most of labs we require us to calculate a numerical answer based on the data we obtain. A hard question to answer in most cases is how good is your

More information

EXAM PREPARATION GUIDE

EXAM PREPARATION GUIDE EXAM PREPARATION GUIDE PECB Certified ISO 39001 Lead Auditor The objective of the PECB Certified ISO 39001 Lead Auditor examination is to ensure that the candidate has the knowledge and skills to plan

More information

MAT 110 WORKSHOP. Updated Fall 2018

MAT 110 WORKSHOP. Updated Fall 2018 MAT 110 WORKSHOP Updated Fall 2018 UNIT 3: STATISTICS Introduction Choosing a Sample Simple Random Sample: a set of individuals from the population chosen in a way that every individual has an equal chance

More information

CIM Level 3 Foundation Certificate in Marketing

CIM Level 3 Foundation Certificate in Marketing Qualification Specification: CIM Level 3 Foundation Certificate in Marketing About CIM CIM (The Chartered Institute of Marketing) has been representing its members and the industry for over 100 years.

More information

Ranking Between the Lines

Ranking Between the Lines Ranking Between the Lines A %MACRO for Interpolated Medians By Joe Lorenz SAS and all other SAS Institute Inc. product or service names are registered trademarks or trademarks of SAS Institute Inc. in

More information

Statistical Package for the Social Sciences INTRODUCTION TO SPSS SPSS for Windows Version 16.0: Its first version in 1968 In 1975.

Statistical Package for the Social Sciences INTRODUCTION TO SPSS SPSS for Windows Version 16.0: Its first version in 1968 In 1975. Statistical Package for the Social Sciences INTRODUCTION TO SPSS SPSS for Windows Version 16.0: Its first version in 1968 In 1975. SPSS Statistics were designed INTRODUCTION TO SPSS Objective About the

More information

The Piecewise Regression Model as a Response Modeling Tool

The Piecewise Regression Model as a Response Modeling Tool NESUG 7 The Piecewise Regression Model as a Response Modeling Tool Eugene Brusilovskiy University of Pennsylvania Philadelphia, PA Abstract The general problem in response modeling is to identify a response

More information

CHAPTER 3 MAINTENANCE STRATEGY SELECTION USING AHP AND FAHP

CHAPTER 3 MAINTENANCE STRATEGY SELECTION USING AHP AND FAHP 31 CHAPTER 3 MAINTENANCE STRATEGY SELECTION USING AHP AND FAHP 3.1 INTRODUCTION Evaluation of maintenance strategies is a complex task. The typical factors that influence the selection of maintenance strategy

More information

Monitoring and Improving Quality of Data Handling

Monitoring and Improving Quality of Data Handling Monitoring and Improving Quality of Data Handling The purpose of this document is to: (a) (b) (c) Maximise the quality of the research process once the question has been formulated and the study designed.

More information

Integration of Fuzzy Shannon s Entropy with fuzzy TOPSIS for industrial robotic system selection

Integration of Fuzzy Shannon s Entropy with fuzzy TOPSIS for industrial robotic system selection JIEM, 2012 5(1):102-114 Online ISSN: 2013-0953 Print ISSN: 2013-8423 http://dx.doi.org/10.3926/jiem.397 Integration of Fuzzy Shannon s Entropy with fuzzy TOPSIS for industrial robotic system selection

More information

Basic Statistical Terms and Definitions

Basic Statistical Terms and Definitions I. Basics Basic Statistical Terms and Definitions Statistics is a collection of methods for planning experiments, and obtaining data. The data is then organized and summarized so that professionals can

More information

Purna Prasad Mutyala et al, / (IJCSIT) International Journal of Computer Science and Information Technologies, Vol. 2 (5), 2011,

Purna Prasad Mutyala et al, / (IJCSIT) International Journal of Computer Science and Information Technologies, Vol. 2 (5), 2011, Weighted Association Rule Mining Without Pre-assigned Weights PURNA PRASAD MUTYALA, KUMAR VASANTHA Department of CSE, Avanthi Institute of Engg & Tech, Tamaram, Visakhapatnam, A.P., India. Abstract Association

More information

Fingerprint Authentication for SIS-based Healthcare Systems

Fingerprint Authentication for SIS-based Healthcare Systems Fingerprint Authentication for SIS-based Healthcare Systems Project Report Introduction In many applications there is need for access control on certain sensitive data. This is especially true when it

More information

An Improved KNN Classification Algorithm based on Sampling

An Improved KNN Classification Algorithm based on Sampling International Conference on Advances in Materials, Machinery, Electrical Engineering (AMMEE 017) An Improved KNN Classification Algorithm based on Sampling Zhiwei Cheng1, a, Caisen Chen1, b, Xuehuan Qiu1,

More information

Implementation of a High-Performance Distributed Web Crawler and Big Data Applications with Husky

Implementation of a High-Performance Distributed Web Crawler and Big Data Applications with Husky Implementation of a High-Performance Distributed Web Crawler and Big Data Applications with Husky The Chinese University of Hong Kong Abstract Husky is a distributed computing system, achieving outstanding

More information

Frequency Distributions

Frequency Distributions Displaying Data Frequency Distributions After collecting data, the first task for a researcher is to organize and summarize the data so that it is possible to get a general overview of the results. Remember,

More information

HIPAA RISK ADVISOR SAMPLE REPORT

HIPAA RISK ADVISOR SAMPLE REPORT HIPAA RISK ADVISOR SAMPLE REPORT HIPAA Security Analysis Report The most tangible part of any annual security risk assessment is the final report of findings and recommendations. It s important to have

More information

Cut Out The Cut And Paste: SAS Macros For Presenting Statistical Output ABSTRACT INTRODUCTION

Cut Out The Cut And Paste: SAS Macros For Presenting Statistical Output ABSTRACT INTRODUCTION Cut Out The Cut And Paste: SAS Macros For Presenting Statistical Output Myungshin Oh, UCLA Department of Biostatistics Mel Widawski, UCLA School of Nursing ABSTRACT We, as statisticians, often spend more

More information

CHAPTER 3 RESEARCH METHODOLOGY OF THE STUDY

CHAPTER 3 RESEARCH METHODOLOGY OF THE STUDY CHAPTER 3 RESEARCH METHODOLOGY OF THE STUDY 3.1 Introduction: In this chapter, an endeavor is made to portray the various aspects of the research methodology adopted for this study purpose. The aim of

More information

ATLAS.ti 8 THE NEXT LEVEL.

ATLAS.ti 8 THE NEXT LEVEL. ATLAS.ti 8 THE NEXT LEVEL. SOPHISTICATED DATA ANALYSIS. EASY TO USE LIKE NEVER BEFORE. FREE! BETA www.cloud.atlasti.com www.atlasti.com ATLAS.ti 8 AND ATLAS.ti DATA ANALYSIS WITH ATLAS.ti IS EASIER, FASTER

More information

8: Statistics. Populations and Samples. Histograms and Frequency Polygons. Page 1 of 10

8: Statistics. Populations and Samples. Histograms and Frequency Polygons. Page 1 of 10 8: Statistics Statistics: Method of collecting, organizing, analyzing, and interpreting data, as well as drawing conclusions based on the data. Methodology is divided into two main areas. Descriptive Statistics:

More information

STATISTICS (STAT) Statistics (STAT) 1

STATISTICS (STAT) Statistics (STAT) 1 Statistics (STAT) 1 STATISTICS (STAT) STAT 2013 Elementary Statistics (A) Prerequisites: MATH 1483 or MATH 1513, each with a grade of "C" or better; or an acceptable placement score (see placement.okstate.edu).

More information

Mapping Distance and Density

Mapping Distance and Density Mapping Distance and Density Distance functions allow you to determine the nearest location of something or the least-cost path to a particular destination. Density functions, on the other hand, allow

More information

Test designs for evaluating the effectiveness of mail packs Received: 30th November, 2001

Test designs for evaluating the effectiveness of mail packs Received: 30th November, 2001 Test designs for evaluating the effectiveness of mail packs Received: 30th November, 2001 Leonard Paas previously worked as a senior consultant at the Database Marketing Centre of Postbank. He worked on

More information

A SAS and Java Application for Reporting Clinical Trial Data. Kevin Kane MSc Infoworks (Data Handling) Limited

A SAS and Java Application for Reporting Clinical Trial Data. Kevin Kane MSc Infoworks (Data Handling) Limited A SAS and Java Application for Reporting Clinical Trial Data Kevin Kane MSc Infoworks (Data Handling) Limited Reporting Clinical Trials Is Resource Intensive! Reporting a clinical trial program for a new

More information

FIRE CODE ADMINISTRATOR PROGRAM

FIRE CODE ADMINISTRATOR PROGRAM DEPARTMENT OF FINANCIAL SERVICES Division of State Fire Marshal Bureau of Fire Standards & Training Release Date: December 2012 Revised Date: May 2017 FIRE CODE ADMINISTROR PROGRAM I. Program Overview

More information

ESG Lab Review RingCentral Mobile Voice Quality Assurance

ESG Lab Review RingCentral Mobile Voice Quality Assurance ESG Lab Review RingCentral Mobile Voice Quality Assurance Abstract This ESG Lab Review documents hands-on testing of RingCentral Office to verify its ability to assure high quality of service (QoS) for

More information

An introduction to SPSS

An introduction to SPSS An introduction to SPSS To open the SPSS software using U of Iowa Virtual Desktop... Go to https://virtualdesktop.uiowa.edu and choose SPSS 24. Contents NOTE: Save data files in a drive that is accessible

More information

The City of St. Petersburg (City) initiated

The City of St. Petersburg (City) initiated FWRJ Remote Facility Condition Inspections and Subsequent Integration into the City of St. Petersburg s Asset Management Program Laura Baumberger, Robert Labrie, and Rebecca Overacre The City of St. Petersburg

More information

EXAM PREPARATION GUIDE

EXAM PREPARATION GUIDE When Recognition Matters EXAM PREPARATION GUIDE PECB Certified ISO/IEC 20000 Lead Auditor www.pecb.com The objective of the Certified ISO/IEC 20000 Lead Auditor examination is to ensure that the candidate

More information

MULTI-FINGER PENETRATION RATE AND ROC VARIABILITY FOR AUTOMATIC FINGERPRINT IDENTIFICATION SYSTEMS

MULTI-FINGER PENETRATION RATE AND ROC VARIABILITY FOR AUTOMATIC FINGERPRINT IDENTIFICATION SYSTEMS MULTI-FINGER PENETRATION RATE AND ROC VARIABILITY FOR AUTOMATIC FINGERPRINT IDENTIFICATION SYSTEMS I. Introduction James L. Wayman, Director U.S. National Biometric Test Center College of Engineering San

More information

Machine Learning Techniques for Data Mining

Machine Learning Techniques for Data Mining Machine Learning Techniques for Data Mining Eibe Frank University of Waikato New Zealand 10/25/2000 1 PART VII Moving on: Engineering the input and output 10/25/2000 2 Applying a learner is not all Already

More information

ECLT 5810 Clustering

ECLT 5810 Clustering ECLT 5810 Clustering What is Cluster Analysis? Cluster: a collection of data objects Similar to one another within the same cluster Dissimilar to the objects in other clusters Cluster analysis Grouping

More information

GLEIF Global LEI Data Quality Report Dictionary

GLEIF Global LEI Data Quality Report Dictionary GLEIF Global LEI Data Quality Report Dictionary Global LEI Data Quality Report Dictionary 2 19 Contents Data Quality Report Glossary... 3 1. Chapter 1: Preface... 4 1.1. Purpose of the Data Quality Report...

More information

Missing Data Techniques

Missing Data Techniques Missing Data Techniques Paul Philippe Pare Department of Sociology, UWO Centre for Population, Aging, and Health, UWO London Criminometrics (www.crimino.biz) 1 Introduction Missing data is a common problem

More information

Slides for Data Mining by I. H. Witten and E. Frank

Slides for Data Mining by I. H. Witten and E. Frank Slides for Data Mining by I. H. Witten and E. Frank 7 Engineering the input and output Attribute selection Scheme-independent, scheme-specific Attribute discretization Unsupervised, supervised, error-

More information

COMPUTER NETWORK PERFORMANCE. Gaia Maselli Room: 319

COMPUTER NETWORK PERFORMANCE. Gaia Maselli Room: 319 COMPUTER NETWORK PERFORMANCE Gaia Maselli maselli@di.uniroma1.it Room: 319 Computer Networks Performance 2 Overview of first class Practical Info (schedule, exam, readings) Goal of this course Contents

More information

From ODM to SDTM: An End-to-End Approach Applied to Phase I Clinical Trials

From ODM to SDTM: An End-to-End Approach Applied to Phase I Clinical Trials PhUSE 2014 Paper PP05 From ODM to SDTM: An End-to-End Approach Applied to Phase I Clinical Trials Alexandre Mathis, Department of Clinical Pharmacology, Actelion Pharmaceuticals Ltd., Allschwil, Switzerland

More information

PMA Companies Welcome Kit

PMA Companies Welcome Kit PMA Companies Welcome Kit Welcome to PMA Companies: We want to thank you for the opportunity to be one of your business partners. We look forward to servicing your organization s insurance and risk management

More information

Data can be in the form of numbers, words, measurements, observations or even just descriptions of things.

Data can be in the form of numbers, words, measurements, observations or even just descriptions of things. + What is Data? Data is a collection of facts. Data can be in the form of numbers, words, measurements, observations or even just descriptions of things. In most cases, data needs to be interpreted and

More information

INTRODUCTION TO INTEGRATION STYLES

INTRODUCTION TO INTEGRATION STYLES INTRODUCTION TO INTEGRATION STYLES Enterprise integration is the task of making separate applications work together to produce a unified set of functionality. Some applications may be custom developed

More information

International Journal of Advance Foundation and Research in Science & Engineering (IJAFRSE) Volume 1, Issue 2, July 2014.

International Journal of Advance Foundation and Research in Science & Engineering (IJAFRSE) Volume 1, Issue 2, July 2014. A B S T R A C T International Journal of Advance Foundation and Research in Science & Engineering (IJAFRSE) Information Retrieval Models and Searching Methodologies: Survey Balwinder Saini*,Vikram Singh,Satish

More information

Forestry Applied Multivariate Statistics. Cluster Analysis

Forestry Applied Multivariate Statistics. Cluster Analysis 1 Forestry 531 -- Applied Multivariate Statistics Cluster Analysis Purpose: To group similar entities together based on their attributes. Entities can be variables or observations. [illustration in Class]

More information