24
1 Local and Global Scores in Selective Editing Dan Hedlin Statistics Sweden

Local and Global Scores in Selective Editing

Embed Size (px)

DESCRIPTION

Local and Global Scores in Selective Editing. Dan Hedlin Statistics Sweden. Local score. Common local (item) score for item j in record k : w k design weight predicted value z kj reported value  j standardisation measure. Global score. - PowerPoint PPT Presentation

Citation preview

Page 1: Local and Global Scores in Selective Editing

1

Local and Global Scores in Selective Editing

Dan Hedlin

Statistics Sweden

Page 2: Local and Global Scores in Selective Editing

2

Local score

• Common local (item) score for item j in record k:

• wk design weight

• predicted value

• zkj reported value

j standardisation measure

jkjkjkkj zyw ~~

kjy~

Page 3: Local and Global Scores in Selective Editing

3

Global score

• What function of the local scores to form a global (unit) score?

• The same number of items in all records

• p items, j = 1, 2, … p

• Let a local score be denoted by kj

• … and a global score by kg γ

Page 4: Local and Global Scores in Selective Editing

4

Common global score functions

In the editing literature:

• Sum function:

• Euclidean score:

• Max function: kjj

max

p

jkj

1

2

p

jkj

1

Page 5: Local and Global Scores in Selective Editing

5

• Farwell (2004): ”Not only does the Euclidean score perform well with a large number of key items, it appears to perform at least as well as the maximum score for small numbers of items.”

Page 6: Local and Global Scores in Selective Editing

6

Unified by…

• Minkowski’s distance

• Sum function if = 1

• Euclidean = 2

• Maximum function if infinity

1

1

;

p

jkjkg γ

1

Page 7: Local and Global Scores in Selective Editing

7

• NB extreme choices are sum and max

• Infinite number of choices in between = 20 will suffice for maximum unless

local scores in the same record are of similar size

Page 8: Local and Global Scores in Selective Editing

8

Global score as a distance

• The axioms of a distance are sensible properties such as being non-negative

• Also, the triangle inequality

• Can show that a global score function that does not satisfy the triangle inequality yields inconsistencies

lklk ggg γγγγ

Page 9: Local and Global Scores in Selective Editing

9

• Hence a global score function should be a distance

• Minkowski’s distance appears to be adequate for practical purposes

• Minkowski’s distance does not satisfy the triangle inequality if < 1

• Hence it is not a distance for < 1

Page 10: Local and Global Scores in Selective Editing

10

Parametrised by

• Advantages: unified global score simplifies presentation and software implementation

• Also gives structure: orders the feasible choices…from smallest: = 1…to largest: infinity

Page 11: Local and Global Scores in Selective Editing

11

• Turning to geometry…

Page 12: Local and Global Scores in Selective Editing

12

Sum function = City block distance

p = 3, ie three items

Page 13: Local and Global Scores in Selective Editing

13

Euclidean distance

Page 14: Local and Global Scores in Selective Editing

14

Supremum (maximum, Chebyshev’s) distance

Page 15: Local and Global Scores in Selective Editing

15

Imagine questionnaires with three items

1k

Record k2k

3k Euclidean distance

Page 16: Local and Global Scores in Selective Editing

16

Page 17: Local and Global Scores in Selective Editing

17

The Euclidean function, two items

A sphere in 3DThreshold

Threshold

Page 18: Local and Global Scores in Selective Editing

18

The max function

A cube in 3D Same threshold

Page 19: Local and Global Scores in Selective Editing

19

The sum function

An octahedron in 3D

Page 20: Local and Global Scores in Selective Editing

20

Page 21: Local and Global Scores in Selective Editing

21

• The sum function will always give more to edit than any other choice, with the same threshold

Page 22: Local and Global Scores in Selective Editing

22

Three editing situations

1. Large errors remain in data, such as unit errors

2. No large errors, but may be bias due to many small errors in the same direction

3. Little bias, but may be many errors

Page 23: Local and Global Scores in Selective Editing

23

Can show that if…1. Situation 32. Variance of error is

3. Local score is

• Then the Euclidean global score will minimise the sum of the variances of the remaining error in estimates of the total

2~kjkjkj zyVar

jkjkjkkj zyw ~~

Page 24: Local and Global Scores in Selective Editing

24

Summary

• Minkowski’s distance unifies many reasonable global score functions

• Scaled by one parameter• The sum and the maximum functions are

the two extreme choices• The Euclidean unit score function is a good

choice under certain conditions