statistics - Global closest fit calculation of missing value -
i trying understand calculation of global closest fit method calculate missing attribute value. trying understand example shown here on page 10, chapter: 2.8 global closest fit
i understand how did computed distance example between case 1 , 3 shown in th table 1.10
i grateful human-like explanation :).
the distance between 2 cases sum of distances between attributes. cases have 3 attributes: temperature, headache, , nausea. compare them 1 one:
temperature
| case 1 | case 3 | | high | ? |
distance = 1.
reason: 1 of cases has ?, falls under condition 2 of distance(xi, yi) formula ("xi = ? or yi = ?").
headache
| case 1 | case 3 | |--------|--------| | ? | no |
distance = 1.
reason: 1 of cases has ? again.
nausea
| case 1 | case 3 | |--------|--------| | no | no |
distance = 0
reason: both same, falls under condition 1 ("xi = yi")
conclusion
| attribute | case 1 | case 3 | distance | |-------------|--------|--------|----------| | temperature | high | ? | 1 | | headache | ? | no | 1 | | nausea | no | no | 0 | |-------------|--------|--------|----------| | total | | | 2 |
distance = 2
reason: sum distances between attributes, according formula @ top of page 10.
Comments
Post a Comment