Eylem Seç
A comparison of density estimation techniques based on incomplete data
Başlık:
A comparison of density estimation techniques based on incomplete data
Yazar:
Mill, Gwendolyn Muriel, author.
ISBN:
9780438053656
Yazar Ek Girişi:
Fiziksel Tanımlama:
1 electronic resource (114 pages)
Genel Not:
Source: Dissertation Abstracts International, Volume: 76-08C.
Advisors: D. M. Titterington.
Özet:
In this thesis we derive and compare various methods of density estimation with emphasis on the situation where the data can be regarded as incomplete. The concept of missing data is discussed in an introductory section and thought is given to the circumstances in which the data can he regarded as "missing at random". In the first chapter we introduce (with examples) the kernel method of density estimation for complete data. Attention is then turned to various ways of adapting the kernel method to encompass incomplete data. Three such methods, AE, ASr and B, are discussed in detail and examples given. Each of the methods aims to produce a kernel function for an incomplete observation (y, z) of which z represents the missing components. Method AE does this by imputing the conditional expected value of z given y, method ASr simulates r independent values z (1),...z(r) of z from an estimate of the true conditional density f(.
Notlar:
School code: 0547
Konu Başlığı:
Tüzel Kişi Ek Girişi:
Mevcut:*
Yer Numarası | Demirbaş Numarası | Shelf Location | Lokasyon / Statüsü / İade Tarihi |
---|---|---|---|
XX(684469.1) | 684469-1001 | Proquest E-Tez Koleksiyonu | Arıyor... |
On Order
Liste seç
Bunu varsayılan liste yap.
Öğeler başarıyla eklendi
Öğeler eklenirken hata oldu. Lütfen tekrar deneyiniz.
:
Select An Item
Data usage warning: You will receive one text message for each title you selected.
Standard text messaging rates apply.