A Review of Statistical Power Analysis Software

Total Page:16

File Type:pdf, Size:1020Kb

A Review of Statistical Power Analysis Software DEPARTMENTS Technological Tools Note: Dr. David Inouye is the edi­ use to researchers (see also Goldstein size, and higher a. level, and declines tor of the Technological Tools sec­ 1989). We do not deal with software with increasing sampling variance. tion. Anyone wishing to contribute for planning the precision of studies, Effect size is the difference between articles or reviews to this section although this is an important consid­ the null and alternative hypotheses, should contact him at the Department eration if the results are to be ana­ and can be measured either using raw of Zoology, University of Maryland, lyzed using confidence intervals or standardized values. Raw mea­ College Park, MD 20742, e-mail: rather than P values (Greenland 1988, sures, such as the slope in a regres­ di5 @umail.umd.edu. Krebs 1989). Because of software up­ sion analysis or difference between dates and new program releases, our means in a t test, are closer to the A REVIEW OF program evaluations will quickly be­ measurements that researchers take STATISTICAL POWER come out of date. Nevertheless, we and so are easier to visualize and in­ terpret. Standardized measures, such ANAL VSIS SOFTWARE highlight some important and time­ less issues to consider when evaluat­ as the correlation coefficient or d Although ecologists have become ing power software: scope, flexibil­ value (difference in means divided by increasingly sophisticated in applying ity, accuracy, ease of use, and ability the standard deviation), are dimen­ tests for statistical significance, few to deal with prospective and retro­ sionless and incorporate the sampling are aware of the power of these tests. spective analyses. variance implicitly, removing the Statistical power is the probability of Readers interested only in "the need to specify variance when calcu­ getting a statistically significant re­ bottom line" should skip straight to lating power. sult given that there is a biologically the Conclusions by way of the sum­ Power analysis is most useful real effect in the population being mary evaluation in Table 2. Those when planning a study. Such "pro­ studied. If a particular test is not sta­ less experienced with power analysis spective" power analyses are usually tistically significant, is it because will find the Background, Stand­ exploratory in nature, investigating there is no effect or because the study alone power and sample size soft­ the relationship between the range of design makes it unlikely that a bio­ ware, and Discussion sections of sample sizes that are deemed feasible, logically real effect would be de­ most use. Experienced power ana­ effect sizes thought to be biologically tected? Power analysis can distin­ lysts will be most interested in the important, levels of variance that guish between these alternatives, and section on Programming power could exist in the popUlation (usuillly is therefore a critical component of analysis using general purpose statis­ taken from the literature or from pilot designing experiments and testing re­ tical software and Table 4. data), and desired levels of a. and sta­ sults (Toft and Shea 1983, Roten­ tistical power. The result is a decision berry and Wiens 1985, Peterman Background about the sample size and a. level that 1990, Fairweather 1991, Taylor and The concepts of statistical power will be used in the study, and the tar­ Gerrodette 1993, Thomas and Juanes are covered in detail in a number of get effect size that will be "detect­ 1996). texts (Kraemer and Thiemann 1987, able" with the given level of statisti­ Discussions with colleagues sug­ Cohen 1988, Lipsey 1990; see also a cal power. gest that one major obstacle to the use particularly clear paper by Muller and After the study is completed and of power analysis is the perceived Benignus 1992). Briefly, the power of the results analyzed, a "retrospective" lack of computer software. Our paper a test is the probability of rejecting power analysis can also be useful if a is designed to remove this obstacle, the null hypothesis given that the al­ statistically nonsignificant result was by reviewing numerous packages that ternative hypothesis is true. Power obtained (e.g., Thomas and Juanes calculate power or sample size and depends on the type of test, increases 1996). Here the actual sample size determining which are likely to be of with increasing sample size, effect and a. level are known, and the vari- 126 Bulletin of the Ecological Society of America ance observed in the sample provides tables and graphs for inclusion in re­ that replied, all agreed to send review an estimate of the variance in the ports; (10) allow easy transfer of re­ copies, although SPSS Inc. (SPSS population. These values are used to sults to other applications; and (11) and SYSTAT DESIGN) failed to de­ calculate power at the minimum ef­ be well documented. liver anything. fect size thought to be of biological The third point, on accuracy, re­ We reviewed three aspects of each significance, or alternatively the ef­ quires further explanation. For some program: scope (points 1-3 above), fect size detectable with the minimum tests, such as z tests and those based ease of use (4-10), and ease of learn­ desired level of power. Note that it is on discrete distributions like the bino­ ing (11; also the intuitiveness of the rarely useful to calculate power using mial, both the P value and statistical program layout, and the clarity and the effect size observed in the power are calculated using the same infonnation content of the on-line sample: such analyses tell us nothing distribution function. Algorithms for help). For scope, we compiled a list about the ability of the test to, detect computing these functions are well of the test situations explicitly men­ biologically important results (Tho­ known, which means that accurate tioned in the program documentation mas 1997). power calculations are easy to per­ or on screen. We also recorded Power calculations can be done form using a computer. Most t, F, and whether the program uses exact or ap­ using the tables or charts provided in c2 tests, however, require calculation proximate methods to calculate many articles and texts (e.g., Kraemer of a different distribution function for power. We summarized ease of use and Thiemann 1987, Cohen 1988, power than for significance tests, and ease of learning on a subjective Lipsey 1990, Zar 1996). However, called a "noncentral" distribution scale from excellent through very these often require some hand calcu­ function. Efficient algorithms for good, good, fair, and poor. Note that lations before they can be used, in­ computing noncentral distribution ease of use is more important than cluding interpolation between tabled functions have been developed only ease of learning for most users, be­ values, and can give inaccurate re­ recently, and it was previously com­ cause all the programs can be learned sults in some situations (e.g., see Bra­ mon to calculate power using ap­ in a day or two. dley et al. 1996 regarding the accu­ proximate methods. Some programs After our initial review, we se­ racy of Cohen's ANOVA tables). still use approximations, a topic we lected the four most promising pack­ Computer software has the potential will return to in the Discussion. ages and asked a class of 19 graduate to make power analysis more accu­ students to evaluate them as part of a rate, interactive, and easy to perform. Methods 2-week "power module" (lectures and Ideally, power analysis should be We compiled a list of software ca­ seminars) in an advanced ecology integrated within the general purpose pable of performing power or sample class. Students in the class had a wide statistical software researchers use size calculations by searching the range of statistical expertise, but none for their regular analyses. This means published literature and the Internet, had prior practical experience of having a comprehensive "study plan­ word of mouth, and requests to power analysis. During the module, ning" module for prospective power Internet news groups. From this pre­ students were asked to complete six analysis, and options to produce esti­ liminary list, we excluded a few spe­ power analysis problems using each mates of retrospective power or de­ cialized programs with limited scope of the four programs, and then to try a tectable effect size for each test per­ that we considered unlikely to be of problem from their own research. The formed. Failing this, researchers use to ecologists (CRCSIZ, EpiiNFO, six questions covered a t test, two­ could use stand-alone software de­ ECHIP, HYPERSTAT, SSIZE, R2; more way ANOV A with contrasts, trend signed solely for power analysis. In information about these programs is analysis (regression), comparison of either case an ideal program should: available at our World Wide Web site proportions, nonparametric test (Wil­ (1) cover the test situations most http://www.interchg.ubc.ca/cacb/ coxon), and survival analysis. Some commonly encountered by research­ power/). We also excluded general were framed in tenns of study design, ers; (2) be flexible enough to deal purpose statistical software where others as retrospective analyses. As with new or unusual situations; (3) power capabilities are not built in but part of their report, students indepen­ produce accurate results; (4) calculate can be programmed, although we dently completed an evaluation form power, sample size, and detectable ef­ briefly discuss these programs later in and ranked the packages on the basis fect size; (5) allow easy exploration the paper. For all remaining software, of which they would recommend to of multiple values of input param­ we contacted the vendors asking for a their colleagues. eters; (6) take a wide variety of effect review copy, or downloaded the soft­ We sent a draft of this paper to the size measures as input, both raw and ware if it was available over the vendors or authors of the program standardized; (7) allow estimation of Internet.
Recommended publications
  • Estimating Complex Production Functions: the Importance of Starting Values
    Version: January 26 Estimating complex production functions: The importance of starting values Mark Neal Presented at the 51st Australian Agricultural and Resource Economics Society Conference, Queenstown, New Zealand, 14-16 February, 2007. Postdoctoral Research Fellow Risk and Sustainable Management Group University of Queensland Room 519, School of Economics, Colin Clark Building (39) University of Queensland, St Lucia, QLD, 4072 Email: [email protected] Ph: +61 (0) 7 3365 6601 Fax: +61 (0) 7 3365 7299 http://www.uq.edu.au/rsmg Acknowledgements Chris O’Donnell helpfully provided access to Gauss code that he had written for estimation of latent class models so it could be translated into Shazam. Leighton Brough (UQ), Ariel Liebman (UQ) and Tom Pechey (UMelb) helped by organising a workshop with Nimrod/enFuzion at UQ in June 2006. enFuzion (via Rok Sosic) provided a limited license for use in the project. Leighton Brough, tools coordinator for the ARC Centre for Complex Systems (ACCS), assisted greatly in setting up an enFuzion grid and collating the large volume of results. Son Nghiem provided assistance in collating and analysing data as well as in creating some of the figures. Page 1 of 30 Version: January 26 ABSTRACT Production functions that take into account uncertainty can be empirically estimated by taking a state contingent view of the world. Where there is no a priori information to allocate data amongst a small number of states, the estimation may be carried out with finite mixtures model. The complexity of the estimation almost guarantees a large number of local maxima for the likelihood function.
    [Show full text]
  • Apple / Shazam Merger Procedure Regulation (Ec)
    EUROPEAN COMMISSION DG Competition CASE M.8788 – APPLE / SHAZAM (Only the English text is authentic) MERGER PROCEDURE REGULATION (EC) 139/2004 Article 8(1) Regulation (EC) 139/2004 Date: 06/09/2018 This text is made available for information purposes only. A summary of this decision is published in all EU languages in the Official Journal of the European Union. Parts of this text have been edited to ensure that confidential information is not disclosed; those parts are enclosed in square brackets. EUROPEAN COMMISSION Brussels, 6.9.2018 C(2018) 5748 final COMMISSION DECISION of 6.9.2018 declaring a concentration to be compatible with the internal market and the EEA Agreement (Case M.8788 – Apple/Shazam) (Only the English version is authentic) TABLE OF CONTENTS 1. Introduction .................................................................................................................. 6 2. The Parties and the Transaction ................................................................................... 6 3. Jurisdiction of the Commission .................................................................................... 7 4. The procedure ............................................................................................................... 8 5. The investigation .......................................................................................................... 8 6. Overview of the digital music industry ........................................................................ 9 6.1. The digital music distribution value
    [Show full text]
  • Statistics and GIS Assistance Help with Statistics
    Statistics and GIS assistance An arrangement for help and advice with regard to statistics and GIS is now in operation, principally for Master’s students. How do you seek advice? 1. The users, i.e. students at INA, make direct contact with the person whom they think can help and arrange a time for consultation. Remember to be well prepared! 2. Doctoral students and postdocs register the time used in Agresso (if you have questions about this contact Gunnar Jensen). Help with statistics Research scientist Even Bergseng Discipline: Forest economy, forest policies, forest models Statistical expertise: Regression analysis, models with random and fixed effects, controlled/truncated data, some time series modelling, parametric and non-parametric effectiveness analyses Software: Stata, Excel Postdoc. Ole Martin Bollandsås Discipline: Forest production, forest inventory Statistics expertise: Regression analysis, sampling Software: SAS, R Associate Professor Sjur Baardsen Discipline: Econometric analysis of markets in the forest sector Statistical expertise: General, although somewhat “rusty”, expertise in many econometric topics (all-rounder) Software: Shazam, Frontier Associate Professor Terje Gobakken Discipline: GIS og long-term predictions Statistical expertise: Regression analysis, ANOVA and PLS regression Software: SAS, R Ph.D. Student Espen Halvorsen Discipline: Forest economy, forest management planning Statistical expertise: OLS, GLS, hypothesis testing, autocorrelation, ANOVA, categorical data, GLM, ANOVA Software: (partly) Shazam, Minitab og JMP Ph.D. Student Jan Vidar Haukeland Discipline: Nature based tourism Statistical expertise: Regression and factor analysis Software: SPSS Associate Professor Olav Høibø Discipline: Wood technology Statistical expertise: Planning of experiments, regression analysis (linear and non-linear), ANOVA, random and non-random effects, categorical data, multivariate analysis Software: R, JMP, Unscrambler, some SAS Ph.D.
    [Show full text]
  • Bab 1 Pendahuluan
    BAB 1 PENDAHULUAN Bab ini akan membahas pengertian dasar statistik dengan sub-sub pokok bahasan sebagai berikut : Sub Bab Pokok Bahasan A. Sejarah dan Perkembangan Statistik B. Tokoh-tokoh Kontributor Statistika C. Definisi dan Konsep Statistik Modern D. Kegunaan Statistik E. Pembagian Statistik F. Statistik dan Komputer G. Soal Latihan A. Sejarah dan Perkembangan Statistik Penggunaan istilah statistika berakar dari istilah-istilah dalam bahasa latin modern statisticum collegium (“dewan negara”) dan bahasa Italia statista (“negarawan” atau “politikus”). Istilah statistik pertama kali digunakan oleh Gottfried Achenwall (1719-1772), seorang guru besar dari Universitas Marlborough dan Gottingen. Gottfried Achenwall (1749) menggunakan Statistik dalam bahasa Jerman untuk pertama kalinya sebagai nama bagi kegiatan analisis data kenegaraan, dengan mengartikannya sebagai “ilmu tentang negara/state”. Pada awal abad ke- 19 telah terjadi pergeseran arti menjadi “ilmu mengenai pengumpulan dan klasifikasi data”. Sir John Sinclair memperkenalkan nama dan pengertian statistics ini ke dalam bahasa Inggris. E.A.W. Zimmerman mengenalkan kata statistics ke negeri Inggris. Kata statistics dipopulerkan di Inggris oleh Sir John Sinclair dalam karyanya: Statistical Account of Scotland 1791-1799. Namun demikian, jauh sebelum abad XVIII masyarakat telah mencatat dan menggunakan data untuk keperluan mereka. Pada awalnya statistika hanya mengurus data yang dipakai lembaga- lembaga administratif dan pemerintahan. Pengumpulan data terus berlanjut, khususnya melalui sensus yang dilakukan secara teratur untuk memberi informasi kependudukan yang selalu berubah. Dalam bidang pemerintahan, statistik telah digunakan seiring dengan perjalanan sejarah sejak jaman dahulu. Kitab perjanjian lama (old testament) mencatat adanya kegiatan sensus penduduk. Pemerintah kuno Babilonia, Mesir, dan Roma mengumpulkan data lengkap tentang penduduk dan kekayaan alam yang dimilikinya.
    [Show full text]
  • Sigmaplot 11: Now with Total Sigmastat Integration
    SigmaPlot 11: Now with Total SigmaStat Integration Imagine my joy as I discovered a complete package of publication-quality graphics software with analytic and presentation tools John A. Wass, Ph.D., in: Scientific Computing International, Jan/Feb 2009 The SYSTAT people who market this product have thrown me a curve. For years, I have bemoaned the fact that most of the upgrade and development efforts that went into the SigmaPlot/SigmaStat software seemed to be biased to the plot side. When I observed that the new package was merely named SigmaPlot, and I further failed to find SigmaStat integration features (the stuff that connects the two programs), the Figure 1: SigmaPlot graphics and wizards, including the Quick Start natural conclusion seemed to be that the statistical Menu (upper right) and the graph program was jettisoned in favor of the graphics. wizard (bottom center) The above introductory narrative is intended to alert the reader to this editor’s long- time love affair with SigmaStat. It was the first statistical software that I used, (seemingly) the first to make a seamless transition from DOS to Windows, and the very first to offer that wonderful Wizard to we befuddled amateur statisticians. My introduction to SigmaPlot came much later, and use of that was only stimulated when the two became integrated. Later on, a pharmacology menu was added and the usage of the plotting software was greatly extended. Of course, the new version has added further graphics and helps to make an already useful program even easier to use. It is now a complete package of publication-quality graphics software with analytic and presentation tools.
    [Show full text]
  • 1 Reliability of Programming Software: Comparison of SHAZAM and SAS
    Reliability of Programming Software: Comparison of SHAZAM and SAS. Oluwarotimi Odeh Department of Agricultural Economics, Kansas State University, Manhattan, KS 66506-4011 Phone: (785)-532-4438 Fax: (785)-523-6925 Email: [email protected] Allen M. Featherstone Department of Agricultural Economics, Kansas State University, Manhattan, KS 66506-4011 Phone: (785)-532-4441 Fax: (785)-523-6925 Email: [email protected] Selected Paper for Presentation at the Western Agricultural Economics Association Annual Meeting, Honolulu, HI, June 30-July 2, 2004 Copyright 2004 by Odeh and Featherstone. All rights reserved. Readers may make verbatim copies for commercial purposes by any means, provided that this copyright notice appears on all such copies. 1 Reliability of Programming Software: Comparison of SHAZAM and SAS. Introduction The ability to combine quantitative methods, econometric techniques, theory and data to analyze societal problems has become one of the major strengths of agricultural economics. The inability of agricultural economists to perform this task perfectly in some cases has been linked to the fragility of econometric results (Learner, 1983; Tomek, 1993). While small changes in model specification may result in considerable impact and changes in empirical results, Hendry and Richard (1982) have shown that two models of the same relationship may result in contradicting result. Results like these weaken the value of applied econometrics (Tomek, 1993). Since the study by Tice and Kletke (1984) computer programming software have undergone tremendous improvements. However, experience in recent times has shown that available software packages are not foolproof and may not be as efficient and consistent as researchers often assume. Compounding errors, convergence, error due to how software read, interpret and process data impact the values of analytical results (see Tomek, 1993; Dewald, Thursby and Anderson, 1986).
    [Show full text]
  • Peer Institution Research: Recommendations and Trends 2016
    Peer Institution Research: Recommendations and Trends 2016 New Mexico State University Abstract This report evaluates the common technology services from New Mexico State University’s 15 peer institutions. Based on the findings, a summary of recommendations and trends are explained within each of the general areas researched: peer institution enrollment, technology fees, student computing, software, help desk services, classroom technology, equipment checkout and loan programs, committees and governing bodies on technology, student and faculty support, printing, emerging technologies and trends, homepage look & feel and ease of navigation, UNM and UTEP my.nmsu.edu comparison, top IT issues, and IT organization charts. Peer Institution Research 1 Table of Contents Peer Institution Enrollment ................................................................................. 3 Technology Fees ................................................................................................. 3 Student Computing ............................................................................................. 6 Software ............................................................................................................. 8 Help Desk Services .............................................................................................. 9 Classroom Technology ...................................................................................... 11 Equipment Checkout and Loan Programs .........................................................
    [Show full text]
  • Insight MFR By
    Manufacturers, Publishers and Suppliers by Product Category 11/6/2017 10/100 Hubs & Switches ASCEND COMMUNICATIONS CIS SECURE COMPUTING INC DIGIUM GEAR HEAD 1 TRIPPLITE ASUS Cisco Press D‐LINK SYSTEMS GEFEN 1VISION SOFTWARE ATEN TECHNOLOGY CISCO SYSTEMS DUALCOMM TECHNOLOGY, INC. GEIST 3COM ATLAS SOUND CLEAR CUBE DYCONN GEOVISION INC. 4XEM CORP. ATLONA CLEARSOUNDS DYNEX PRODUCTS GIGAFAST 8E6 TECHNOLOGIES ATTO TECHNOLOGY CNET TECHNOLOGY EATON GIGAMON SYSTEMS LLC AAXEON TECHNOLOGIES LLC. AUDIOCODES, INC. CODE GREEN NETWORKS E‐CORPORATEGIFTS.COM, INC. GLOBAL MARKETING ACCELL AUDIOVOX CODI INC EDGECORE GOLDENRAM ACCELLION AVAYA COMMAND COMMUNICATIONS EDITSHARE LLC GREAT BAY SOFTWARE INC. ACER AMERICA AVENVIEW CORP COMMUNICATION DEVICES INC. EMC GRIFFIN TECHNOLOGY ACTI CORPORATION AVOCENT COMNET ENDACE USA H3C Technology ADAPTEC AVOCENT‐EMERSON COMPELLENT ENGENIUS HALL RESEARCH ADC KENTROX AVTECH CORPORATION COMPREHENSIVE CABLE ENTERASYS NETWORKS HAVIS SHIELD ADC TELECOMMUNICATIONS AXIOM MEMORY COMPU‐CALL, INC EPIPHAN SYSTEMS HAWKING TECHNOLOGY ADDERTECHNOLOGY AXIS COMMUNICATIONS COMPUTER LAB EQUINOX SYSTEMS HERITAGE TRAVELWARE ADD‐ON COMPUTER PERIPHERALS AZIO CORPORATION COMPUTERLINKS ETHERNET DIRECT HEWLETT PACKARD ENTERPRISE ADDON STORE B & B ELECTRONICS COMTROL ETHERWAN HIKVISION DIGITAL TECHNOLOGY CO. LT ADESSO BELDEN CONNECTGEAR EVANS CONSOLES HITACHI ADTRAN BELKIN COMPONENTS CONNECTPRO EVGA.COM HITACHI DATA SYSTEMS ADVANTECH AUTOMATION CORP. BIDUL & CO CONSTANT TECHNOLOGIES INC Exablaze HOO TOO INC AEROHIVE NETWORKS BLACK BOX COOL GEAR EXACQ TECHNOLOGIES INC HP AJA VIDEO SYSTEMS BLACKMAGIC DESIGN USA CP TECHNOLOGIES EXFO INC HP INC ALCATEL BLADE NETWORK TECHNOLOGIES CPS EXTREME NETWORKS HUAWEI ALCATEL LUCENT BLONDER TONGUE LABORATORIES CREATIVE LABS EXTRON HUAWEI SYMANTEC TECHNOLOGIES ALLIED TELESIS BLUE COAT SYSTEMS CRESTRON ELECTRONICS F5 NETWORKS IBM ALLOY COMPUTER PRODUCTS LLC BOSCH SECURITY CTC UNION TECHNOLOGIES CO FELLOWES ICOMTECH INC ALTINEX, INC.
    [Show full text]
  • Catalogo Generale ADALTA N. 25
    SOFTWARE PER L’INNOVAZIONE SOFTWARE Catalogo Generale catalogo completo su: www.adalta.it www.adalta.it L’innovazione tecnologica è fondamentale per le aziende e le istituzioni italiane per essere più competitive. Adalta propone e supporta in Italia l’utilizzo di alcuni tra i più importanti software al mondo per l’innovazione tecnologica, la ricerca e lo sviluppo. Durante più di 20 anni di attività, Adalta ha selezionato nel proprio catalogo i migliori software disponibili, che sono divenuti lo standard mondiale nei diversi settori di applicazione. Centinaia di aziende private, istituzioni pubbliche, università italiane si avvalgono dei servizi di grandissima qualità offerti da Adalta: supporto nell’individuare il prodotto più adatto alle specifi che esigenze, consulenza e formazione per sfruttare al meglio le potenzialità del software. I clienti Adalta vengono costantemente aggiornati grazie alle newsletter tecnico scientifi che ricche di utili informazioni, che vengono pubblicate e rese disponibili per la consultazione gratuita sul sito. Supporto Pre-Vendita Adalta Notizie » www.adalta.it/Contatti » www.adalta.it/AdaltaNotizie Contattaci telefonicamente o via email ti aiuteremo a identi- Informazioni utili, novità, applicazioni per utilizzare al meglio i fi care il software più adatto al tuo lavoro e a determinare la software distribuiti da Adalta. Viene inviata una breve email miglior tipologia di licenza in base alla tue esigenze. con il sommario delle notizie pubblicate. Supporto Post-Vendita Consulenza e Corsi di Formazione » www.adalta.it/Supporto » www.adalta.it/Consulenza Adalta è rivenditore autorizzato e importatore diretto per l’Ita- Adalta aiuta costantemente i tecnici e i professionisti a cono- lia di tutti i prodotti a catalogo.
    [Show full text]
  • Statistical Softwares: Introduction Team Maarten Jansen 1
    Statistical softwares: introduction Team Maarten Jansen 1. Maarten Jansen and Toufik Zahaf 2. Teaching assistant: Bastien Marquis http://homepages.ulb.ac.be/˜majansen/teaching/STAT-F-413/ c Maarten Jansen STAT-F-413 — Statistical softwares: introduction p.1 Objectives Forbidden data • Retrieve and analyse your own real data Not allowed: • Use at least two different software systems and two different types of analyses (typ- • Time series: time dependence of your data is allowed (longitudinal), but ically ANOVA and regression, but others are equally welcome: principle component analysis etc.) time must not be the dominant explanatory variable • Find your data • Birth weights of babies 1. at a company, hospital, banks, insurance company: this option is by far the best. If you get data, then also try to get to know what sort of business questions the company/organization is trying to answer: use the data to respond to the questions. 2. Otherwise (but less preferable) on the internet, e.g.: government data (such as statbel.gov.be) This option has the drawback that it is harder to be original and harder to focus on specific business questions. The data should be original, in the sense that they must not be popular in scien- tific papers or textbooks as illustration of a method. – Number of births per communality – Macro-economical data; per country, european, regional, provinces etc. – Socio-economical data c Maarten Jansen STAT-F-413 — Statistical softwares: introduction p.2 c Maarten Jansen STAT-F-413 — Statistical softwares: introduction p.3 Why not time-series Note on the data size: large enough..
    [Show full text]
  • Spatial Tools for Econometric and Exploratory Analysis
    Spatial Tools for Econometric and Exploratory Analysis Michael F. Goodchild University of California, Santa Barbara Luc Anselin University of Illinois at Urbana-Champaign http://csiss.org Outline ¾A Quick Tour of a GIS ¾Spatial Data Analysis ¾CSISS Tools Spatial Data Analysis Principles: 1. Integration ¾Linking data through common location the layer cake ¾Linking processes across disciplines spatially explicit processes e.g. economic and social processes interact at common locations 2. Spatial analysis ¾Social data collected in cross- section longitudinal data are difficult to construct ¾Cross-sectional perspectives are rich in context can never confirm process though they can perhaps falsify useful source of hypotheses, insights 3. Spatially explicit theory ¾Theory that is not invariant under relocation ¾Spatial concepts (location, distance, adjacency) appear explicitly ¾Can spatial concepts ever explain, or are they always surrogates for something else? 4. Place-based analysis ¾Nomothetic - search for general principles ¾Idiographic - description of unique properties of places ¾An old debate in Geography The Earth's surface ¾Uncontrolled variance ¾There is no average place ¾Results depend explicitly on bounds ¾Places as samples ¾Consider the model: y = a + bx Tract Pop Location Shape 1 3786 x,y 2 2966 x,y 3 5001 x,y 4 4983 x,y 5 4130 x,y 6 3229 x,y 7 4086 x,y 8 3979 x,y Iij = EiAjf (dij) / ΣkAkf (dik) Aj d Ei ij Types of Spatial Data Analysis ¾ Exploratory Spatial Data Analysis • exploring the structure of spatial data • determining
    [Show full text]
  • Software for Food Engineering Applications - Bon, J
    FOOD ENGINEERING – Vol. IV - Software for Food Engineering Applications - Bon, J. SOFTWARE FOR FOOD ENGINEERING APPLICATIONS Bon, J. Department of Food Technology, Polytechnic University of Valencia,Spain Keywords: Food engineering, software, software sources, engineering software, units operations. Contents 1. Introduction 2. Software Sources 3. Software Tools 3.1. General Software 3.2. Food Physical Properties 3.3. Process Simulation and Design 3.4. Control 3.5. Other 3.6. On-Line Executable Software 4. Conclusions Glossary Bibliography Biographical Sketch Summary Currently, there are industry standard flowsheeting and design programs available, which are widely used by chemical engineers. However, existing programs for food processing applications are limited in their ability to handle the wide variety of processes and products encountered in the food industry. The scientific impediments involved consist of a lack of knowledge of relationships between physicochemical and sensory properties, complexity of food components, their chemical/biomedical behavior, and intricacy of on-line measurement of product properties. A main problem lies in the fact that most of the changes are irreversible. The food engineer deals with computers in one of two ways: 1) understanding how to use commercialUNESCO software that usually perf–orms EOLSS well and has a forthcoming interface making it user-friendly and 2) understanding how to develop software that can solve specific problems,SAMPLE because many calculations CHAPTERSfound in one’s professional career will be unique. Nowadays, a great deal of more or less general-purpose software exists that could be useful in Food Engineering, the main drawback in most cases being the calculation of physical properties.
    [Show full text]