Statistické metody pro analýzu dat s chybějícími pozorováními
Mechanisms of missing data and methods are described in this thesis. Three mechanisms are considered - MCAR, MAR, MNAR. Two simple methods using deletion of incomplete records are shown and their properties and shortcomings are demonstrated. Secondly, the principle of simple imputations is explained...
Main Author: | |
---|---|
Other Authors: | |
Format: | Dissertation |
Language: | Czech |
Published: |
2016
|
Online Access: | http://www.nusl.cz/ntk/nusl-352770 |
id |
ndltd-nusl.cz-oai-invenio.nusl.cz-352770 |
---|---|
record_format |
oai_dc |
spelling |
ndltd-nusl.cz-oai-invenio.nusl.cz-3527702017-09-20T04:20:24Z Statistické metody pro analýzu dat s chybějícími pozorováními Statistical analysis of datasets with missing observations Janoušková, Kateřina Omelka, Marek Kulich, Michal Mechanisms of missing data and methods are described in this thesis. Three mechanisms are considered - MCAR, MAR, MNAR. Two simple methods using deletion of incomplete records are shown and their properties and shortcomings are demonstrated. Secondly, the principle of simple imputations is explained. EM algorithm which uses the classical statistics and the algorithm of data augmentation which uses Bayesian framework are derived and compared. The last method included in the thesis is the multiple imputation. The described methods are compared on real data set, first on continuous variables and then on a contingency table. 1 2016 info:eu-repo/semantics/masterThesis http://www.nusl.cz/ntk/nusl-352770 cze info:eu-repo/semantics/restrictedAccess |
collection |
NDLTD |
language |
Czech |
format |
Dissertation |
sources |
NDLTD |
description |
Mechanisms of missing data and methods are described in this thesis. Three mechanisms are considered - MCAR, MAR, MNAR. Two simple methods using deletion of incomplete records are shown and their properties and shortcomings are demonstrated. Secondly, the principle of simple imputations is explained. EM algorithm which uses the classical statistics and the algorithm of data augmentation which uses Bayesian framework are derived and compared. The last method included in the thesis is the multiple imputation. The described methods are compared on real data set, first on continuous variables and then on a contingency table. 1 |
author2 |
Omelka, Marek |
author_facet |
Omelka, Marek Janoušková, Kateřina |
author |
Janoušková, Kateřina |
spellingShingle |
Janoušková, Kateřina Statistické metody pro analýzu dat s chybějícími pozorováními |
author_sort |
Janoušková, Kateřina |
title |
Statistické metody pro analýzu dat s chybějícími pozorováními |
title_short |
Statistické metody pro analýzu dat s chybějícími pozorováními |
title_full |
Statistické metody pro analýzu dat s chybějícími pozorováními |
title_fullStr |
Statistické metody pro analýzu dat s chybějícími pozorováními |
title_full_unstemmed |
Statistické metody pro analýzu dat s chybějícími pozorováními |
title_sort |
statistické metody pro analýzu dat s chybějícími pozorováními |
publishDate |
2016 |
url |
http://www.nusl.cz/ntk/nusl-352770 |
work_keys_str_mv |
AT janouskovakaterina statistickemetodyproanalyzudatschybejicimipozorovanimi AT janouskovakaterina statisticalanalysisofdatasetswithmissingobservations |
_version_ |
1718539077654937600 |