Statistical Packages While you can still perform statistical
- Slides: 16
Statistical Packages: • While you can still perform statistical tests by hand with a calculator, it is much easier to use a computer software package. • In 1940 s - Data Analysis used Pen and Mechanical Calculators • In 1950 s - Large Computers calculated Large Data Sets, Sets and performed Data Calculations, Calculations never before possible. • In 1960 s - Statistics Packages were developed. • In 1970 s - Non-Programmers and Non-Statisticians were able to do the Complex Calculations performed in 1940 s.
Modern Day Statistical Software Packages: • 1980 s – – Brought together Complex Systems for Statistical Analysis, Analysis including Software Packing, Packing Terminals, Terminals Programming Language, Language Editors, Editors Operating Systems and Output Devices and Data Analysis • 1990 s – – Brought Windows-Based Software Packages, Packages so easy that anyone with Limited Statistical Knowledge can perform Complex Analysis
Computer Software Available for Facilitating Statistical Tests: • Spreadsheets: – Excel, Quatro Pro, Lotus 123 • Databases: – Access • Commercial Statistical Packages: – SPSS, STATA, SAS, etc.
Computer Software Available for Facilitating Statistical Tests: (contd. . ) • Freeware Statistical Packages : – BV 4. 1 – Geo. DA – IDAMS/Win. IDAMS – MINUIT – Win. BUGS : Bayesian analysis using Markov chain Monte Win. BUGS : Bayesian analysis Carlo methods – Winpepi – package of statistical programs for epidemiologists Winpepi
Computer Software Available for Facilitating Statistical Tests: (contd. . ) • Geographic Information Packages • User-Written Software • Modeling Packages
Spreadsheets • Spreadsheets: MS-Excel – Advantages: • Easy to Use • Easy to Manipulate Data • Some Built-in Statistical Tests (Analysis) • Limited Programming Capability – Limitations: • Limited Data Capacity • Limited Number of Analytical Options • No Transaction Log.
Databases: • Advantages: • Large Data Capacity. • Efficient Data Manipulations and Queries. • Good Transaction Log. • Some Built-in Analysis. • Limitations: • Not designed for science.
Statistical Packages: • Advantages: • Wide Range of Built-in Analysis. • Pre-formatted Output. • Good Transaction Logs. • Limitations: • Hard to Learn to Operate. • Easy to Generate Probabilities Without Knowledge of Statistics.
Statistical Packages: Classification Statistical Packages Compute from Partially Analyzed Data Epi Calc 2000 Compute from Raw Data EPI Info SPSS Stata SAS
Compute from Partially Analyzed Data:
Compute from Raw Data: http: //www. cdc. gov/epiinfo/ http: //www. stata. com http: //www. spss. com http: //www. sas. com
• http: //www. sas. com • Powerful, but Difficult to Learn and Inflexible Powerful • Struggling to keep up with the times, times especially graphically • Very Popular, especially in business circles Popular
• http: //www. stata. com • Powerful stats program • Now with GUI interface • Typically the choice of Economics Crowd
• http: //www. spss. com • Very easy to use GUI • Syntax is inflexible ¬ too powerful – However contains several procedures otherwise not available in menu system
SPSS (contd. . ) • Recently updated graphics (v. 13. 0) are much improved • Very popular, but expensive popular – Affordable copies are crippled
If you think you can you can poem
If you can imagine it you can achieve it
Measurement quotes
If you can't measure it you can't manage it
You can t improve what you don t measure
Goldene bilanzregel
Stand still laddie
What can you do to control your emotions while driving
Albuterol costco
Do while loop
Perform operations on functions
Chapter 14 test physical science
Kinds of comparison
You can tell harris about it just ____(easily) as i can
Positive degree examples
Through you blind eyes are open
You have much to learn
