Compartir
array:24 [
"pii" => "S0213911104720002"
"issn" => "02139111"
"doi" => "10.1016/S0213-9111(04)72000-2"
"estado" => "S300"
"fechaPublicacion" => "2004-01-01"
"aid" => "72000"
"copyright" => "Sociedad Española de Salud Pública y Administración Sanitaria"
"copyrightAnyo" => "2004"
"documento" => "article"
"crossmark" => 0
"licencia" => "http://creativecommons.org/licenses/by-nc-nd/4.0/"
"subdocumento" => "sco"
"cita" => "Gac Sanit. 2004;18:58-63"
"abierto" => array:3 [
"ES" => true
"ES2" => true
"LATM" => true
]
"gratuito" => true
"lecturas" => array:2 [
"total" => 2456
"formatos" => array:3 [
"EPUB" => 117
"HTML" => 1883
"PDF" => 456
]
]
"itemSiguiente" => array:19 [
"pii" => "S0213911104720014"
"issn" => "02139111"
"doi" => "10.1016/S0213-9111(04)72001-4"
"estado" => "S300"
"fechaPublicacion" => "2004-01-01"
"aid" => "72001"
"copyright" => "Sociedad Española de Salud Pública y Administración Sanitaria"
"documento" => "article"
"crossmark" => 0
"licencia" => "http://creativecommons.org/licenses/by-nc-nd/4.0/"
"subdocumento" => "sco"
"cita" => "Gac Sanit. 2004;18:64-7"
"abierto" => array:3 [
"ES" => true
"ES2" => true
"LATM" => true
]
"gratuito" => true
"lecturas" => array:2 [
"total" => 2623
"formatos" => array:3 [
"EPUB" => 103
"HTML" => 2120
"PDF" => 400
]
]
"es" => array:10 [
"idiomaDefecto" => true
"titulo" => "La sostenibilidad del sistema hospitalario en Cataluña. El balance de una década"
"tienePdf" => "es"
"tieneTextoCompleto" => 0
"tieneResumen" => array:2 [
0 => "es"
1 => "en"
]
"paginas" => array:1 [
0 => array:2 [
"paginaInicial" => "64"
"paginaFinal" => "67"
]
]
"titulosAlternativos" => array:1 [
"en" => array:1 [
"titulo" => "Viability of the hospital system in Catalonia [Spain]. Balance after a decade"
]
]
"contieneResumen" => array:2 [
"es" => true
"en" => true
]
"contienePdf" => array:1 [
"es" => true
]
"autores" => array:1 [
0 => array:2 [
"autoresLista" => "Francesc Cots"
"autores" => array:1 [
0 => array:2 [
"nombre" => "Francesc"
"apellidos" => "Cots"
]
]
]
]
]
"idiomaDefecto" => "es"
"EPUB" => "https://multimedia.elsevier.es/PublicationsMultimediaV1/item/epub/S0213911104720014?idApp=WGSE"
"url" => "/02139111/0000001800000001/v1_201310251603/S0213911104720014/v1_201310251603/es/main.assets"
]
"itemAnterior" => array:19 [
"pii" => "S0213911104719998"
"issn" => "02139111"
"doi" => "10.1016/S0213-9111(04)71999-8"
"estado" => "S300"
"fechaPublicacion" => "2004-01-01"
"aid" => "71999"
"copyright" => "Sociedad Española de Salud Pública y Administración Sanitaria"
"documento" => "article"
"crossmark" => 0
"licencia" => "http://creativecommons.org/licenses/by-nc-nd/4.0/"
"subdocumento" => "fla"
"cita" => "Gac Sanit. 2004;18:50-7"
"abierto" => array:3 [
"ES" => true
"ES2" => true
"LATM" => true
]
"gratuito" => true
"lecturas" => array:2 [
"total" => 2851
"formatos" => array:3 [
"EPUB" => 127
"HTML" => 2261
"PDF" => 463
]
]
"es" => array:10 [
"idiomaDefecto" => true
"titulo" => "Coste-efectividad de drotrecogina alfa (activada) en el tratamiento de la sepsis grave en España"
"tienePdf" => "es"
"tieneTextoCompleto" => 0
"tieneResumen" => array:2 [
0 => "es"
1 => "en"
]
"paginas" => array:1 [
0 => array:2 [
"paginaInicial" => "50"
"paginaFinal" => "57"
]
]
"titulosAlternativos" => array:1 [
"en" => array:1 [
"titulo" => "Cost-effectiveness of drotrecogin alpha [activated] in the treatment of severe sepsis in Spain"
]
]
"contieneResumen" => array:2 [
"es" => true
"en" => true
]
"contienePdf" => array:1 [
"es" => true
]
"autores" => array:1 [
0 => array:2 [
"autoresLista" => "José A. Sacristán, Luis Prieto, Teresa Huete, Antonio Artigas, Xavier Badia, Christopher Chinn, Peter Hudson"
"autores" => array:7 [
0 => array:2 [
"nombre" => "José A."
"apellidos" => "Sacristán"
]
1 => array:2 [
"nombre" => "Luis"
"apellidos" => "Prieto"
]
2 => array:2 [
"nombre" => "Teresa"
"apellidos" => "Huete"
]
3 => array:2 [
"nombre" => "Antonio"
"apellidos" => "Artigas"
]
4 => array:2 [
"nombre" => "Xavier"
"apellidos" => "Badia"
]
5 => array:2 [
"nombre" => "Christopher"
"apellidos" => "Chinn"
]
6 => array:2 [
"nombre" => "Peter"
"apellidos" => "Hudson"
]
]
]
]
]
"idiomaDefecto" => "es"
"EPUB" => "https://multimedia.elsevier.es/PublicationsMultimediaV1/item/epub/S0213911104719998?idApp=WGSE"
"url" => "/02139111/0000001800000001/v1_201310251603/S0213911104719998/v1_201310251603/es/main.assets"
]
"es" => array:14 [
"idiomaDefecto" => true
"titulo" => "Datos incompletos: una mirada crítica para su manejo en estudios sanitarios"
"tieneTextoCompleto" => 0
"paginas" => array:1 [
0 => array:2 [
"paginaInicial" => "58"
"paginaFinal" => "63"
]
]
"autores" => array:1 [
0 => array:4 [
"autoresLista" => "Maylée Cañizares, Isabel Barroso, Karen Alfonso"
"autores" => array:3 [
0 => array:4 [
"nombre" => "Maylée"
"apellidos" => "Cañizares"
"email" => array:1 [
0 => "mcperez@yahoo.com"
]
"referencia" => array:1 [
0 => array:2 [
"etiqueta" => "<span class="elsevierStyleSup">*</span>"
"identificador" => "cor0005"
]
]
]
1 => array:2 [
"nombre" => "Isabel"
"apellidos" => "Barroso"
]
2 => array:2 [
"nombre" => "Karen"
"apellidos" => "Alfonso"
]
]
"afiliaciones" => array:1 [
0 => array:1 [
"entidad" => "Instituto Nacional de Higiene, Epidemiología y Microbiología (INHEM). La Habana. Cuba"
]
]
"correspondencia" => array:1 [
0 => array:3 [
"identificador" => "cor0005"
"etiqueta" => "*"
"correspondencia" => "Correspondencia: Instituto Nacional de Higiene, Epidemiología y Microbiología (INHEM). Infanta 1158 entre Clavel y Llinás. Centro Habana. Ciudad de La Habana. Cuba."
]
]
]
]
"titulosAlternativos" => array:1 [
"en" => array:1 [
"titulo" => "Methods for handling incomplete data in health research: a critical look"
]
]
"pdfFichero" => "main.pdf"
"tienePdf" => true
"fechaRecibido" => "2003-05-12"
"fechaAceptado" => "2003-10-20"
"PalabrasClave" => array:2 [
"es" => array:1 [
0 => array:4 [
"clase" => "keyword"
"titulo" => "Palabras clave"
"identificador" => "xpalclavsec268676"
"palabras" => array:5 [
0 => "Valores ausentes"
1 => "Datos incompletos"
2 => "Imputaciones"
3 => "Casos completos"
4 => "Imputaciones múltiples"
]
]
]
"en" => array:1 [
0 => array:4 [
"clase" => "keyword"
"titulo" => "Key words"
"identificador" => "xpalclavsec268675"
"palabras" => array:5 [
0 => "Missing data"
1 => "Incomplete data"
2 => "Imputations"
3 => "Casecomplete analysis"
4 => "Multiple imputations"
]
]
]
]
"tieneResumen" => true
"resumen" => array:2 [
"es" => array:2 [
"titulo" => "Resumen"
"resumen" => "<span class="elsevierStyleSectionTitle">Objetivo</span><p id="spar0005" class="elsevierStyleSimplePara elsevierViewall">Ilustrar los procedimientos para el manejo de datos incompletos en las investigaciones sanitarias.</p> <span class="elsevierStyleSectionTitle">Métodos</span><p id="spar0010" class="elsevierStyleSimplePara elsevierViewall">Se discuten dos estrategias para el manejo de los datos incompletos: a) análisis de casos completos, y b) imputaciones, que incluye asignar la media al valor ausente, predecir el valor ausente mediante modelos de regresión e imputaciones múltiples. Para ilustrar estos procedimientos, se elabora un ejemplo en el contexto de la regresión logística con datos procedentes de la «Segunda encuesta nacional de factores de riesgo y afecciones crónicas no trasmisibles», realizada en Cuba en el año 2001.</p> <span class="elsevierStyleSectionTitle">Resultados</span><p id="spar0015" class="elsevierStyleSimplePara elsevierViewall">Al imputar por las medias y por modelos de regresión, los resultados fueron similares y se obtuvo una odds ratio (OR) sobrestimada por encima del 10%. El análisis de casos completos obtuvo los resultados más alejados de las estimaciones de las OR de referencia, con una diferencia del 2 hasta el 65% de variación. Los 3 métodos invirtieron la relación entre la edad y la hipertensión. Las imputaciones múltiples fueron el método que proveyó las estimaciones más cercanas a las de referencia, con una variación menor al 16%. Éste fue el único procedimiento que preservó la relación entre la edad y la hipertensión.</p> <span class="elsevierStyleSectionTitle">Conclusiones</span><p id="spar0020" class="elsevierStyleSimplePara elsevierViewall">La elección de los procedimientos para el manejo de datos incompletos resulta una tarea compleja, pues en determinadas situaciones un mismo procedimiento puede producir estimaciones precisas y en otras no. El análisis de los datos completos debe realizarse con cautela por la pérdida sustancial de información que se genera. Las imputaciones por medias y modelos de regresión producen estimaciones poco fiables bajo mecanismos MAR (missing at random).</p>"
]
"en" => array:2 [
"titulo" => "Abstract"
"resumen" => "<span class="elsevierStyleSectionTitle">Objective</span><p id="spar0025" class="elsevierStyleSimplePara elsevierViewall">To illustrate methods for handling incomplete data in health research.</p> <span class="elsevierStyleSectionTitle">Methods</span><p id="spar0030" class="elsevierStyleSimplePara elsevierViewall">Two strategies for handling missing data are presented: complete-case analysis and imputations. The imputations used were mean imputations, regression imputations, and multiple imputations. These strategies are illustrated in the context of logistic regression through an example using data from the «Second Cuban national survey on risk factors and non communicable disease», carried out in 2001.</p> <span class="elsevierStyleSectionTitle">Results</span><p id="spar0035" class="elsevierStyleSimplePara elsevierViewall">The results obtained via mean and regression imputation were similar. The odds ratios were overestimated by 10%. The results of complete-case analysis showed the greatest difference from the reference odds ratios, with a variation of between 2 and 65%. The three methods distorted the relationship between age and hypertension. Multiple imputations produced estimates closest to those of the reference estimates with a variation of less than 16%. This was the only procedure preserving the relationship between age and hypertension.</p> <span class="elsevierStyleSectionTitle">Conclusions</span><p id="spar0040" class="elsevierStyleSimplePara elsevierViewall">Selecting methods for handling missing data is difficult, since the same procedure can give precise estimations in certain circumstances and not in others. Completecase analysis should be used with caution due to the substantial loss of information it produces. Mean and regression imputations produce unreliable estimates under missing at random (MAR) mechanisms.</p>"
]
]
"bibliografia" => array:2 [
"titulo" => "Bibliografía"
"seccion" => array:1 [
0 => array:2 [
"identificador" => "bibs0005"
"bibliografiaReferencia" => array:12 [
0 => array:3 [
"identificador" => "bib1"
"etiqueta" => "1."
"referencia" => array:1 [
0 => array:2 [
"contribucion" => array:1 [
0 => array:2 [
"titulo" => "Multiple imputation for nonresponse in surveys"
"autores" => array:1 [
0 => array:2 [
"etal" => false
"autores" => array:1 [
0 => "D.B. Rubin"
]
]
]
]
]
"host" => array:1 [
0 => array:1 [
"LibroEditado" => array:1 [
"serieFecha" => "1987"
]
]
]
]
]
]
1 => array:3 [
"identificador" => "bib2"
"etiqueta" => "2."
"referencia" => array:1 [
0 => array:2 [
"contribucion" => array:1 [
0 => array:2 [
"titulo" => "Analysis of incomplete multivariate data"
"autores" => array:1 [
0 => array:2 [
"etal" => false
"autores" => array:1 [
0 => "J.L. Shaffer"
]
]
]
]
]
"host" => array:1 [
0 => array:1 [
"LibroEditado" => array:1 [
"serieFecha" => "1997"
]
]
]
]
]
]
2 => array:3 [
"identificador" => "bib3"
"etiqueta" => "3."
"referencia" => array:1 [
0 => array:2 [
"contribucion" => array:1 [
0 => array:2 [
"titulo" => "Segunda encuesta de factores de riesgo y afecciones no trasmisibles"
"autores" => array:1 [
0 => array:2 [
"etal" => true
"autores" => array:3 [
0 => "M. Bonet"
1 => "P. Mas"
2 => "M. Chang"
]
]
]
]
]
"host" => array:1 [
0 => array:1 [
"LibroEditado" => array:1 [
"serieFecha" => "2002"
]
]
]
]
]
]
3 => array:3 [
"identificador" => "bib4"
"etiqueta" => "4."
"referencia" => array:1 [
0 => array:2 [
"contribucion" => array:1 [
0 => array:2 [
"titulo" => "Statistical Analysis with missing data"
"autores" => array:1 [
0 => array:2 [
"etal" => false
"autores" => array:2 [
0 => "R.J.A. Little"
1 => "D.B. Rubin"
]
]
]
]
]
"host" => array:1 [
0 => array:1 [
"LibroEditado" => array:1 [
"serieFecha" => "1987"
]
]
]
]
]
]
4 => array:3 [
"identificador" => "bib5"
"etiqueta" => "5."
"referencia" => array:1 [
0 => array:2 [
"contribucion" => array:1 [
0 => array:2 [
"titulo" => "Linear mixed models for longitudinal data"
"autores" => array:1 [
0 => array:2 [
"etal" => false
"autores" => array:2 [
0 => "G. Verbeke"
1 => "G. Molenberghs"
]
]
]
]
]
"host" => array:1 [
0 => array:1 [
"LibroEditado" => array:1 [
"serieFecha" => "2000"
]
]
]
]
]
]
5 => array:3 [
"identificador" => "bib6"
"etiqueta" => "6."
"referencia" => array:1 [
0 => array:2 [
"contribucion" => array:1 [
0 => array:2 [
"titulo" => "A comparison of analytic methods for non-random missingness of outcome data"
"autores" => array:1 [
0 => array:2 [
"etal" => false
"autores" => array:3 [
0 => "S.L. Crawford"
1 => "S.L. Tennstedt"
2 => "J.B. McKinlay"
]
]
]
]
]
"host" => array:1 [
0 => array:1 [
"Revista" => array:6 [
"tituloSerie" => "J Clin Epidemiol"
"fecha" => "1995"
"volumen" => "48"
"paginaInicial" => "209"
"paginaFinal" => "219"
"link" => array:1 [
0 => array:2 [
"url" => "https://www.ncbi.nlm.nih.gov/pubmed/7869067"
"web" => "Medline"
]
]
]
]
]
]
]
]
6 => array:3 [
"identificador" => "bib7"
"etiqueta" => "7."
"referencia" => array:1 [
0 => array:2 [
"contribucion" => array:1 [
0 => array:2 [
"titulo" => "A comparison of imputation techniques for handling missing data"
"autores" => array:1 [
0 => array:2 [
"etal" => false
"autores" => array:4 [
0 => "C.M. Musil"
1 => "C.B. Warner"
2 => "P.K. Yobas"
3 => "S.L. Jones"
]
]
]
]
]
"host" => array:1 [
0 => array:1 [
"Revista" => array:5 [
"tituloSerie" => "West J Nursing Res"
"fecha" => "2002"
"volumen" => "24"
"paginaInicial" => "815"
"paginaFinal" => "829"
]
]
]
]
]
]
7 => array:3 [
"identificador" => "bib8"
"etiqueta" => "8."
"referencia" => array:1 [
0 => array:2 [
"contribucion" => array:1 [
0 => array:2 [
"titulo" => "The case of the missing data: methods of dealing with dropout and other research vagaries"
"autores" => array:1 [
0 => array:2 [
"etal" => false
"autores" => array:1 [
0 => "D.L. Streiner"
]
]
]
]
]
"host" => array:1 [
0 => array:1 [
"Revista" => array:6 [
"tituloSerie" => "Can J Psychiatry"
"fecha" => "2002"
"volumen" => "47"
"paginaInicial" => "68"
"paginaFinal" => "75"
"link" => array:1 [
0 => array:2 [
"url" => "https://www.ncbi.nlm.nih.gov/pubmed/11873711"
"web" => "Medline"
]
]
]
]
]
]
]
]
8 => array:3 [
"identificador" => "bib9"
"etiqueta" => "9."
"referencia" => array:1 [
0 => array:2 [
"contribucion" => array:1 [
0 => array:2 [
"titulo" => "Imputation strategies for missing data in a school-based multi-centre study: the Pathway study"
"autores" => array:1 [
0 => array:2 [
"etal" => false
"autores" => array:4 [
0 => "S. Hunsberger"
1 => "D. Murray"
2 => "C.E. Davis"
3 => "R.R. Fabsitz"
]
]
]
]
]
"host" => array:1 [
0 => array:1 [
"Revista" => array:6 [
"tituloSerie" => "Stat Med"
"fecha" => "2001"
"volumen" => "20"
"paginaInicial" => "305"
"paginaFinal" => "316"
"link" => array:1 [
0 => array:2 [
"url" => "https://www.ncbi.nlm.nih.gov/pubmed/11169604"
"web" => "Medline"
]
]
]
]
]
]
]
]
9 => array:3 [
"identificador" => "bib10"
"etiqueta" => "10."
"referencia" => array:1 [
0 => array:2 [
"contribucion" => array:1 [
0 => array:2 [
"titulo" => "Multiple imputation in public health research"
"autores" => array:1 [
0 => array:2 [
"etal" => false
"autores" => array:3 [
0 => "X.H. Zhou"
1 => "G.J. Eckert"
2 => "W.M. Tierney"
]
]
]
]
]
"host" => array:1 [
0 => array:1 [
"Revista" => array:6 [
"tituloSerie" => "Stat Med"
"fecha" => "2001"
"volumen" => "20"
"paginaInicial" => "1541"
"paginaFinal" => "1549"
"link" => array:1 [
0 => array:2 [
"url" => "https://www.ncbi.nlm.nih.gov/pubmed/11343373"
"web" => "Medline"
]
]
]
]
]
]
]
]
10 => array:3 [
"identificador" => "bib11"
"etiqueta" => "11."
"referencia" => array:1 [
0 => array:2 [
"contribucion" => array:1 [
0 => array:2 [
"titulo" => "Use of multiple imputation to correct for nonresponse bias in a survey of urology symptoms among African-American men"
"autores" => array:1 [
0 => array:2 [
"etal" => false
"autores" => array:6 [
0 => "J.M. Taylor"
1 => "K.L. Cooper"
2 => "J.T. Wei"
3 => "A.V. Sarma"
4 => "T.E. Raghunathan"
5 => "S.G. Heeringa"
]
]
]
]
]
"host" => array:1 [
0 => array:1 [
"Revista" => array:6 [
"tituloSerie" => "Am J Epidemiol"
"fecha" => "2002"
"volumen" => "156"
"paginaInicial" => "774"
"paginaFinal" => "782"
"link" => array:1 [
0 => array:2 [
"url" => "https://www.ncbi.nlm.nih.gov/pubmed/12370166"
"web" => "Medline"
]
]
]
]
]
]
]
]
11 => array:3 [
"identificador" => "bib12"
"etiqueta" => "12."
"referencia" => array:1 [
0 => array:2 [
"contribucion" => array:1 [
0 => array:2 [
"titulo" => "A multivariate method for estimating mortality rates among children under 5 years from health and social indicators in Iraq"
"autores" => array:1 [
0 => array:2 [
"etal" => false
"autores" => array:2 [
0 => "R. Garfield"
1 => "C.S. Leu"
]
]
]
]
]
"host" => array:1 [
0 => array:1 [
"Revista" => array:6 [
"tituloSerie" => "Int J Epidemiol"
"fecha" => "2000"
"volumen" => "29"
"paginaInicial" => "510"
"paginaFinal" => "515"
"link" => array:1 [
0 => array:2 [
"url" => "https://www.ncbi.nlm.nih.gov/pubmed/10869324"
"web" => "Medline"
]
]
]
]
]
]
]
]
]
]
]
]
]
"idiomaDefecto" => "es"
"url" => "/02139111/0000001800000001/v1_201310251603/S0213911104720002/v1_201310251603/es/main.assets"
"Apartado" => array:4 [
"identificador" => "636"
"tipo" => "SECCION"
"es" => array:2 [
"titulo" => "Nota Metodológica"
"idiomaDefecto" => true
]
"idiomaDefecto" => "es"
]
"PDF" => "https://static.elsevier.es/multimedia/02139111/0000001800000001/v1_201310251603/S0213911104720002/v1_201310251603/es/main.pdf?idApp=WGSE&text.app=https://gacetasanitaria.org/"
"EPUB" => "https://multimedia.elsevier.es/PublicationsMultimediaV1/item/epub/S0213911104720002?idApp=WGSE"
]