Dealign with ERror Dealing with Error Oops I

Dealign with ERror Dealing with Error “Oops!… I did it again” --Britney Spears CS 128/ES 228 - Lecture 12 b 1

Sources of Error n n n n Lack of precision Lack of accuracy Transference error, e. g. typos Human error, including bias Poor sampling Improper analysis Data rot Hardware error CS 128/ES 228 - Lecture 12 b 2

What is error? n “Error is the physical difference between the real world and the GIS facsimile” -Heywood, Cornelius, & Carver, p. 178 n Errors are impossible to avoid, but can be accounted for? CS 128/ES 228 - Lecture 12 b 3

Accuracy vs. Precision Figure 10. 1, An Introduction to Geographic Information Systems by Heywood, Cornelius, and Carver CS 128/ES 228 - Lecture 12 b 4

Where does lack of precision come from? Sloppy measurement n Imprecise equipment n Poor input assumptions n Accumulated error n How do we fix it? n Get better equipment and use it carefully CS 128/ES 228 - Lecture 12 b 5

Imprecise equipment includes both hardware and software Aliasing is an intrinsic problem of GIS’s CS 128/ES 228 - Lecture 12 b 6

Where does lack of accuracy come from? Dubious source data n Incompatible source data n • Data collected at different times through different methods, possibly in different formats n Dubious modeling • Poor choice of model, e. g. raster vs. vector • Including issues of information loss involving file compression CS 128/ES 228 - Lecture 12 b 7

When is accuracy a bad thing? n Map simplification n Features are omitted n Area features become lines or points n Exaggeration n Features’ apparent size is “increased” (e. g. hydrants) n Features’ separation is increased on the map for visibility Must Mapquest be accurate? CS 128/ES 228 - Lecture 12 b 8

Another time for “less accuracy”? or CS 128/ES 228 - Lecture 12 b 9

Figure 10. 5, An Introduction to Geographic Information Systems by Heywood, Cornelius, and Carver CS 128/ES 228 - Lecture 12 b 10

Where does transference error come from? n Typos, etc. n n Can be prevented through diligence and software “sanity” checks Format conversion n Many inter-format conversions cause loss/corruption of data/information CS 128/ES 228 - Lecture 12 b 11

Transference Errors can be fun n “geographic information systems is an interesting course” n “지리적인 정보 시스템은 재미있는 과정 이다 ” n “The geography information system is the process which is fun” Thanks to http: //babelfish. altavista. com/babelfish/tr CS 128/ES 228 - Lecture 12 b 12

Digitization (transference) errors CS 128/ES 228 - Lecture 12 b 13

Where does human error come from? n Sloppiness n Bias • (an unintentional form of lack of accuracy) n Sources of bias • Mental maps • Cultural • Purposeful CS 128/ES 228 - Lecture 12 b 14

Where do errors of analysis come from? n Faulty understanding of statistics and statistical packages n n See CS 128/ES 228, Lab 10! “There are three kinds of lies: lies, damned lies, and statistics” - Benjamin Disraeli, British politician, 1804 -1881 CS 128/ES 228 - Lecture 12 b 15

Where do errors of data rot come from? n Link rot Not Found The requested URL /cs/dlevine/ was not found on this server. Apache/1. 3. 27 Server at www. xxx. edu Port 80 n Poor “style” n E. g. “Employees may appeal to Dr. Wickenheiser” as opposed to “Employees may appeal to the President of the University” CS 128/ES 228 - Lecture 12 b 16

Where do hardware errors come from? Hardware failure Hardware Limitations CS 128/ES 228 - Lecture 12 b 17

What is a hardware limitation? Numbers in a computer are stored in a finite number of bits. n Using too few bits can cause round-off error. n Box 9. 2, Principles of Geographic Information Systems by Burrough and Mc. Donnell CS 128/ES 228 - Lecture 12 b 18

Errors of Categorization n “It is nearly impossible, and intrinsically wrong to try to place errors into neat categories” --david levine CS 128/ES 228 - Lecture 12 b 19

How do we minimize (NOT avoid) error? “CONSTANT VIGILANCE” -- “Mad Eye” Moody Defense Against The Dark Arts Instructor Hogwarts School of Witchcraft and Wizardry CS 128/ES 228 - Lecture 12 b 20