Introdução: A incidência de câncer de tireóide vem aumentando em todo o mundo e não há um consenso sobre as razões deste fato. O município de São Paulo apresenta altos coeficientes de incidência desta doença, mas ainda não foi analisada sua tendência e nem sua distribuição espacial. Objetivos: Descrever os coeficientes de incidência (1997-2010) e de mortalidade (1981-2010), analisar a tendência dos coeficientes de incidência e mortalidade, segundo sexo, faixa etária, tipo morfológico (incidência), bem como os efeitos da idade, período e coorte, e examinar a distribuição espacial. Métodos: Este é um estudo ecológico. Foram analisados os casos novos de câncer de tireóide diagnosticados no período de 1997 a 2010 fornecidos pelo Registro de Câncer de Base Populacional de São Paulo e os óbitos por câncer de tireóide ocorridos entre 1981 e 2010 fornecidos pelo Sistema de Mortalidade do Ministério da Saúde (SIM-MS) e pelo Programa de Aprimoramento das Informações de Mortalidade (PRO-AIM). Foram calculados os coeficientes bruto e padronizado de incidência e de mortalidade, foi analisada a tendência destes coeficientes através do modelo de regressão, da mudança percentual anual e do modelo idade-período-coorte. Para a análise espacial foram criados mapas temáticos, calculado o índice de Moran e, para as variáveis com padrão cluster foi calculado o índice local de associação espacial (LISA) e estimados modelos de regressão, tendo como variável dependente os coeficientes e como variáveis independentes os indicadores socioeconômicos (IDH, taxa de alfabetização, coeficiente de Gini e número de moradores por domicílio). Resultados: O coeficiente médio de incidência (1997-2010) foi para o sexo feminino de 17,77 por 100.000 e para o sexo masculino 4,46 por 100.000. Ambos apresentaram tendência crescente. O coeficiente médio de mortalidade (1981-2010) foi para o sexo feminino de 0,50 por 100.000 e para o masculino 0,30 por 100.000, ambos apresentaram tendência decrescente. O tipo histológico papilífero apresentou tendência crescente em ambos os sexos. Para incidência (ambos os sexos) e para mortalidade feminina, os efeitos de idade-período e coorte ofereceram o melhor ajuste; para mortalidade apenas a idade. Na análise espacial incidência apresentou padrão cluster para homens e mulheres. Os modelos finais foram explicados pela índice de desenvolvimento humano e pela média de moradores por domicílio. Conclusão: Na cidade de São Paulo há um aumento da incidência do câncer de tireóide, possivelmente causado pelo diagnóstico precoce e/ou pela exposição a fatores de risco para o desenvolvimento do carcinoma papilífero. Por outro lado, a mortalidade vem decaindo, provavelmente pelo diagnóstico precoce / Introduction: The incidence of thyroid cancer has been increasing worldwide and the reason for this upward remains controversial. The incidence of this cancer is elevated in São Paulo city, however, trend and spatial analysis where never conducted before. Objective: This study aimed to describe incidence (1997-2010) and mortality (1981-2010) rates, to analyze incidence and mortality trends, by gender, by age group, by histologic type (incidence only) and by age-period-cohort effects and to evaluate the spatial distribution. Methods: This is an ecologic study. Incident thyroid cancer cases were selected from Population-Based Cancer Registry of São Paulo city, registered from 1997 to 2010 and data from thyroid cancer deaths were obtained from Ministry of Health Information System on Mortality (SIM-MS) and from Mortality Improvement Program (PRO-AIM), from 1981 to 2010. Crude and age-standardized incidence and mortality rates were calculated, incidence and mortality trends were estimated by regression models, by annual percentage change and by age-period-cohort effects. To analyze the spatial distribution, thematic maps were created, Moran Index was calculated and, for the variables with cluster pattern, Local Spatial Association (LISA) was calculated; regression models were estimated using as dependent variable the rates and as independents variables the socio-economic indicators. Results: The mean incidence rate (1997-2010), for females, was 17.77 per 100,000 and for males was 4.46 per 100,000. Both presented increasing trends during the period. The mean mortality rate (1981-2010) for females was 0.5 per 100.000 and for males was 0.3 per 100.000, both presented decreasing trends. The incidence of papillary cancer increased over the period study for females and males. Age, period and birth cohort effects significantly improved the model fit for incidence (females and males) and mortality (only females); for mortality, only the age effect significantly improved the model fit. There was a clustered spatial pattern for incidence (females and males). The final regression models were significantly fitted by human development index and by average number of inhabitants per household. Conclusion: The incidence of thyroid cancer has increased in São Paulo city, this may be due to increased detection of subclinical disease or/and by exposures to risk factors for development of papillary carcinoma. Otherwise, the mortality rates have decreased, probably because of the detection of subclinical disease

Introdução: Os linfomas abrangem um grupo heterogêneo de neoplasias originadas no sistema linfático, diferentes quanto à sua histologia, prognóstico e epidemiologia, embora possa haver grande número de aspectos clínicos comuns. De acordo com sua morfologia, dividem-se dois grupos: os linfomas Hodgkin (LH) e os linfomas não-Hodgkin (LNH). Objetivo: Avaliar a tendência temporal da incidência de linfomas no período de 1997 a 2012, identificando a influência de fatores como o sexo, a idade, o período e a coorte e nascimento. Metodologia: Trata-se de um estudo ecológico. Foram obtidas, do Registro de Câncer de Base Populacional de São Paulo (RCBP-SP), informações sobre todos os casos novos de linfomas no Município de São Paulo, diagnosticados no período de 1997 a 2012. Informações sobre o número de habitantes do Município foram obtidas online através do site do Departamento de Informática do SUS. Para avaliar a tendência da incidência de linfomas no decorrer do período, segundo sexo e faixa etária, foram ajustados modelos lineares generalizados (MLG). Para avaliar a influência da idade, do período de diagnóstico e das coortes de nascimento na tendência da incidência dos linfomas, foi utilizado o modelo idade-período-coorte (IPC). Resultados e conclusões: Dos 18.037 casos analisados, 20,5% eram do tipo LH e 79,5% do tipo LNH. Entre os casos de LH, 52,6% eram homens e 70,0% tinham entre 20 e 39 anos. A taxa de incidência de LH padronizada por idade, por 100 mil habitantes, variou de 5,0 em 1997 para 4,0 em 2012, entretanto, não foi detectada nenhuma tendência significativa na incidência ao longo do tempo (p>0,05). O risco de desenvolver LH foi maior no sexo masculino do que no feminino apenas na faixa etária de 0 a 14 anos (p<0,001), nas demais, o risco foi semelhante para ambos os sexos (p>0,05). O risco de desenvolver LH segundo a faixa etária apresentou um padrão etário bimodal. No sexo feminino, os maiores riscos ocorreram nas faixas de 20 a 39 e de 65 anos e mais e, no masculino, nas faixas de 15 a 19 e de 65 anos e mais. O modelo IPC apontou uma influência da coorte de nascimento na incidência de LH em mulheres: para aquelas nascidas antes de 1960, quanto mais antiga a coorte, maior o risco de LH; para as nascidas após 1960, o risco relativo permaneceu estável. Entre os casos de LNH, 51,6% eram homens e 77,4% tinham mais de 40 anos. A taxa de incidência de LNH padronizada por idade, por 100 mil habitantes, passou de 22,6 em 1997 para 17,0 em 2012. Foi detectada uma tendência de decréscimo na incidência de LNH de 1,7% ao ano em todas as faixas etárias, em ambos os sexos (p<0,001). O risco de desenvolver LNH aumentou continuamente com o avançar da idade, em ambos os sexos. O modelo IPC não detectou efeitos de período. Para os homens, as coortes mais velhas apresentam maior risco e, as mais jovens, menor risco. Para as mulheres nascidas antes de 1960 o comportamento foi semelhante ao dos homens, para as nascidas após 1960, o risco relativo permaneceu estável. / Introduction: Lymphomas comprise a heterogeneous group of neoplasias originating in the lymphatic system, different in their histology, prognosis and epidemiology, although there may be a large number of common clinical aspects. According to their morphology, two groups are divided: Hodgkin\'s lymphomas (HL) and non-Hodgkin\'s lymphomas (NHL). Objective: To evaluate the temporal trend of the incidence of lymphomas in the period from 1997 to 2012, identifying the influence of factors such as sex, age, period and cohort and birth. Methodology: This is an ecological study. Information about all new cases of lymphomas in the city of São Paulo, diagnosed in the period from 1997 to 2012, were obtained from the São Paulo Population Based Cancer Registry. Information on the number of inhabitants of the Municipality were obtained online through the website of the SUS Department of Informatics. To evaluate the trend of lymphoma incidence during the period, according to sex and age group, generalized linear models (GLM) were adjusted. The age-period-cohort (APC) model was used to evaluate the influence of age, diagnosis period and birth cohorts on the trend of lymphoma incidence. Results and conclusions: Of the 18,037 cases analyzed, 20.5% were HL type and 79.5% NHL type. Among the cases of HL, 52.6% were men and 70.0% were between 20 and 39 years old. The age-standardized incidence rate of HL per 100,000 population ranged from 5.0 in 1997 to 4.0 in 2012, however, no significant trend in incidence over time was detected (p> 0.05). The risk of developing HL was greater in males than in females only in the age group 0 to 14 years (p <0.001), in the others, the risk was similar for both sexes (p> 0.05). The risk of developing HL according to the age group presented a bimodal age pattern. In females, the highest risks occurred in the 20-39 and 65-year-olds, and in the male, in the 15-19 and 65 years and older ranges. The APC model pointed to an influence of the birth cohort on the incidence of HL in women: for those born before 1960, the older the cohort, the higher the risk of HL; for those born after 1960, the relative risk remained stable. Among the cases of NHL, 51.6% were men and 77.4% were over 40 years old. The age-standardized incidence rate of NHL per 100,000 population increased from 22.6 in 1997 to 17.0 in 2012. A trend of a decrease in the incidence of NHL of 1.7% per year was observed in all ranges in both sexes (p <0.001). The risk of developing NHL increased steadily with advancing age in both sexes. The APC model did not detect period effects. For men, older cohorts are at higher risk, and younger cohorts are at lower risk. For women born before 1960 the behavior was similar to that of men, for those born after 1960, the relative risk remained stable.

Introdução: Os linfomas abrangem um grupo heterogêneo de neoplasias originadas no sistema linfático, diferentes quanto à sua histologia, prognóstico e epidemiologia, embora possa haver grande número de aspectos clínicos comuns. De acordo com sua morfologia, dividem-se dois grupos: os linfomas Hodgkin (LH) e os linfomas não-Hodgkin (LNH). Objetivo: Avaliar a tendência temporal da incidência de linfomas no período de 1997 a 2012, identificando a influência de fatores como o sexo, a idade, o período e a coorte e nascimento. Metodologia: Trata-se de um estudo ecológico. Foram obtidas, do Registro de Câncer de Base Populacional de São Paulo (RCBP-SP), informações sobre todos os casos novos de linfomas no Município de São Paulo, diagnosticados no período de 1997 a 2012. Informações sobre o número de habitantes do Município foram obtidas online através do site do Departamento de Informática do SUS. Para avaliar a tendência da incidência de linfomas no decorrer do período, segundo sexo e faixa etária, foram ajustados modelos lineares generalizados (MLG). Para avaliar a influência da idade, do período de diagnóstico e das coortes de nascimento na tendência da incidência dos linfomas, foi utilizado o modelo idade-período-coorte (IPC). Resultados e conclusões: Dos 18.037 casos analisados, 20,5% eram do tipo LH e 79,5% do tipo LNH. Entre os casos de LH, 52,6% eram homens e 70,0% tinham entre 20 e 39 anos. A taxa de incidência de LH padronizada por idade, por 100 mil habitantes, variou de 5,0 em 1997 para 4,0 em 2012, entretanto, não foi detectada nenhuma tendência significativa na incidência ao longo do tempo (p>0,05). O risco de desenvolver LH foi maior no sexo masculino do que no feminino apenas na faixa etária de 0 a 14 anos (p<0,001), nas demais, o risco foi semelhante para ambos os sexos (p>0,05). O risco de desenvolver LH segundo a faixa etária apresentou um padrão etário bimodal. No sexo feminino, os maiores riscos ocorreram nas faixas de 20 a 39 e de 65 anos e mais e, no masculino, nas faixas de 15 a 19 e de 65 anos e mais. O modelo IPC apontou uma influência da coorte de nascimento na incidência de LH em mulheres: para aquelas nascidas antes de 1960, quanto mais antiga a coorte, maior o risco de LH; para as nascidas após 1960, o risco relativo permaneceu estável. Entre os casos de LNH, 51,6% eram homens e 77,4% tinham mais de 40 anos. A taxa de incidência de LNH padronizada por idade, por 100 mil habitantes, passou de 22,6 em 1997 para 17,0 em 2012. Foi detectada uma tendência de decréscimo na incidência de LNH de 1,7% ao ano em todas as faixas etárias, em ambos os sexos (p<0,001). O risco de desenvolver LNH aumentou continuamente com o avançar da idade, em ambos os sexos. O modelo IPC não detectou efeitos de período. Para os homens, as coortes mais velhas apresentam maior risco e, as mais jovens, menor risco. Para as mulheres nascidas antes de 1960 o comportamento foi semelhante ao dos homens, para as nascidas após 1960, o risco relativo permaneceu estável. / Introduction: Lymphomas comprise a heterogeneous group of neoplasias originating in the lymphatic system, different in their histology, prognosis and epidemiology, although there may be a large number of common clinical aspects. According to their morphology, two groups are divided: Hodgkin\'s lymphomas (HL) and non-Hodgkin\'s lymphomas (NHL). Objective: To evaluate the temporal trend of the incidence of lymphomas in the period from 1997 to 2012, identifying the influence of factors such as sex, age, period and cohort and birth. Methodology: This is an ecological study. Information about all new cases of lymphomas in the city of São Paulo, diagnosed in the period from 1997 to 2012, were obtained from the São Paulo Population Based Cancer Registry. Information on the number of inhabitants of the Municipality were obtained online through the website of the SUS Department of Informatics. To evaluate the trend of lymphoma incidence during the period, according to sex and age group, generalized linear models (GLM) were adjusted. The age-period-cohort (APC) model was used to evaluate the influence of age, diagnosis period and birth cohorts on the trend of lymphoma incidence. Results and conclusions: Of the 18,037 cases analyzed, 20.5% were HL type and 79.5% NHL type. Among the cases of HL, 52.6% were men and 70.0% were between 20 and 39 years old. The age-standardized incidence rate of HL per 100,000 population ranged from 5.0 in 1997 to 4.0 in 2012, however, no significant trend in incidence over time was detected (p> 0.05). The risk of developing HL was greater in males than in females only in the age group 0 to 14 years (p <0.001), in the others, the risk was similar for both sexes (p> 0.05). The risk of developing HL according to the age group presented a bimodal age pattern. In females, the highest risks occurred in the 20-39 and 65-year-olds, and in the male, in the 15-19 and 65 years and older ranges. The APC model pointed to an influence of the birth cohort on the incidence of HL in women: for those born before 1960, the older the cohort, the higher the risk of HL; for those born after 1960, the relative risk remained stable. Among the cases of NHL, 51.6% were men and 77.4% were over 40 years old. The age-standardized incidence rate of NHL per 100,000 population increased from 22.6 in 1997 to 17.0 in 2012. A trend of a decrease in the incidence of NHL of 1.7% per year was observed in all ranges in both sexes (p <0.001). The risk of developing NHL increased steadily with advancing age in both sexes. The APC model did not detect period effects. For men, older cohorts are at higher risk, and younger cohorts are at lower risk. For women born before 1960 the behavior was similar to that of men, for those born after 1960, the relative risk remained stable.

Mirtingumo nuo įvairių ligų įvertinimas ir prognozavimas pagal atlikto tyrimo duomenis – dažnas statistinės analizės uždavinys medicinoje. Juose siekiama prognozuoti tikėtiną mirčių nuo tiriamos ligos skaičių, susirgimo tam tikra liga tikimybę ar išskirti rizikos grupes, įvertinant tyrimo metu surinktų stebimos populiacijos imties kintamųjų duomenis ir nustatant, kokia priklausomybę juos sieja. Pagrindiniai šio darbo tikslai: susipažinti su statistikos metodais, taikomais mirtingumo duomenų analizei; sudaryti statistinės analizės modelius turimiems mirtingumo duomenims; realizuoti sudarytus modelius programiškai, panaudojant SAS sistemą ir SAS makro programavimo galimybes. Panaudojus Puasono, logistinės ir Kokso regresin��s analizės metodus sudaryti mirtingumo nuo galvos smegenų insulto (GSI) prognozavimo modeliai. Sudaryti modeliai realizuoti programiškai, panaudojus SAS programavimo kalbą, SAS/IML posistemės galimybes ir SAS makro programavimo priemones. Sukurti regresinės analizės modeliai ir programines priemonės panaudotos Kauno medicinos universiteto Kardiologijos instituto 1980-2004 metais atliktų tyrimų metu surinktų Kauno miesto 25-64 m. amžiaus gyventojų mirtingumo nuo GSI duomenų analizei atlikti. / Estimation and forecasting of mortality from various diseases are very frequent data analysis tasks in medicine nowadays. In order to estimate expected number of deaths, probability to die from a disease or trends in mortality we should apply the most suitable statistical methods. Data analysis models were created using Poisson, logistic, Cox regression methods and realized in SAS macros. Created software also contains models for goodness of fit analysis, graphical visualization and prepares a report of data analysis in RTF (Rich Text Format) format. Analysis was made for mortality from stroke data among Kaunas population aged 25 to 64 during the period 1980-2004. The study contains the description of applying created data analysis models, SAS macros and received results.

Submitted by Renata Lopes (renatasil82@gmail.com) on 2016-10-06T17:59:14Z No. of bitstreams: 1 christianemariameureralves.pdf: 1154792 bytes, checksum: 93b03559e6d95acbb4dbb3661f857e03 (MD5) / Approved for entry into archive by Adriana Oliveira (adriana.oliveira@ufjf.edu.br) on 2016-10-07T12:14:33Z (GMT) No. of bitstreams: 1 christianemariameureralves.pdf: 1154792 bytes, checksum: 93b03559e6d95acbb4dbb3661f857e03 (MD5) / Made available in DSpace on 2016-10-07T12:14:33Z (GMT). No. of bitstreams: 1 christianemariameureralves.pdf: 1154792 bytes, checksum: 93b03559e6d95acbb4dbb3661f857e03 (MD5) Previous issue date: 2009-02-13 / Introdução: O câncer de colo de útero, desde a década de 50, dispõe de um exame capaz de detectá-lo em fase incipiente e curável. A disponibilidade do teste de Papanicolaou parece ser a principal motivação para a queda de mortalidade por câncer de colo de útero em vários países ao redor do mundo. Buscou-se com este estudo avaliar o comportamento da mortalidade por câncer de colo de útero e útero porção não especificada, no período de 1980-2005, no Estado de Minas Gerais. Optou-se pela utilização de modelo de regressão linear e pela abordagem idadeperíodo-coorte. Material e Métodos: Foram coletados os dados de óbito e população disponíveis no DATASUS. Para avaliação da tendência de mortalidade por idade e período, utilizou-se o modelo de regressão linear; as taxas também foram log-transformadas para que se obtivesse o percentual de mudança da mortalidade por ano. A análise período-coorte foi feita através do método não paramétrico de Tarone e Chu. Resultados: Encontrou-se queda na mortalidade por câncer de colo de útero e útero porção não especificada para a análise idade e período. A redução foi principalmente relacionada com os casos de câncer de útero porção não especificada. Na análise idade-período-coorte houve redução menor que a esperada para as coortes de 1901-1908 e 1921-1928. Houve redução maior que a esperada para as coortes de 1913-1920, 1929-1932, 1937-1946, 1949-1956, 19631970 e 1969-1976. Encontrou-se ainda redução maior que a esperada para o período de 2000-2001. Conclusão: Foi evidenciada a redução da mortalidade por câncer de colo de útero e útero porção não especificada no Estado de Minas Gerais no período estudado. Os achados mostram influência das coortes de nascimento sobre a queda da mortalidade. / Introduction: Cervical cancer has had since the fifties, an exam capable of detecting it in its early and curable stage. The availability of the Papanicolaou smear test seems to be the principal reason for the fall in the mortality due to cervical cancer in many countries throughout the world. The aim of this study was to assess the trends of the mortality due to cervical cancer and uterus not otherwise specified (NOS) in the period from 1980-2005, in the state of Minas Gerais. We opted for the model of linear regression and the age-period-cohort approach. Material and Methods: Data related to death and population available at DATASUS were collected. To assess the tendency of mortality by age and period the approach of linear regression was used; the taxes were also log transformed in order to obtain the percentage of change in the mortality by year. The period-cohort analysis was carried out using Tarone & Chu’s non parametric method. Results: A reduction in the mortality due to cervical cancer and uterus not otherwise specified (NOS) for the age and period analyzed was found. The reduction was mainly related with the cases of cancer of uterus not otherwise specified (NOS). In the age-period-cohort analysis the reduction was less than expected for the cohorts from 1901-1908 and 1921-1928. There was a reduction bigger than expected for the cohorts from 1913-1920, 1929-1932, 1937-1946, 19491956, 1963-1970 and 1969-1976. It was also found a bigger reduction than expected for the period from 2000-2001. Conclusion: The reduction in the mortality due to cervical cancer and uterus not otherwise specified (NOS) in the state of Minas Gerais was unmistakable in the period studied. The findings show the influence of the birth cohorts over the decrease in mortality.

L’encéphalopathie spongiforme bovine (ESB) est une maladie neuro-dégénérative fatale affectant les bovins ; elle est également une zoonose à l’origine du variant de la maladie de Creutzfeldt-Jakob. Identifiée pour la première fois au Royaume-Uni en 1986, cette maladie s’est rapidement étendue en Europe, malgré la mise en place de mesures de contrôle. En raison des particularités épidémiologiques de l’ESB (longue période d’incubation, âge précoce à l’infection et diagnostic post-mortem possible uniquement en fin d’incubation), l’évolution temporelle de l’exposition des bovins à l’ESB ne peut être appréhendée qu’à partir de la modélisation. Nous avons utilisé le modèle Age-Période-Cohorte afin de (ré)évaluer, en relation avec les principales mesures de contrôle, l’évolution de l’épizootie d’ESB à la lumière des données de surveillance les plus récente, en France, et dans six autres pays européens : Allemagne, Irlande, Italie, Pays-Bas, Pologne et Royaume-Uni. / Bovine spongiform encephalopathy is a fatal neurodegenerative disease affecting cattle and transmissible to humans as the cause of variant Creutzfeldt-Jakob disease. BSE was first identified in 1986 in United Kingdom, before spreading to European countries despite the implementation of control measures. Due to BSE epidemiological characteristics (long incubation period, early age at infection and post-mortem diagnostic at end stage of incubation period), time trend of BSE cattle exposure can only be estimated by modeling. We used age-period-cohort model in order to (re)evaluate, in relation to the main control measures, the trend of BSE epidemic, using the most recent surveillance data in France and six other European countries: Germany, Ireland, Italy, the Netherlands, Poland and United Kingdom.

為瞭解臺灣地區男女自殺死亡率的差異，本文採用Held and Riebler (2010)所建議的多元年齡-年代-世代模型，同時探討男女性自殺死亡率在年齡、年代及世代三種效應上的差異，我們同時使用非條件概似函數法（或稱對數線性模型法）及條件概似函數法（或稱多項式邏輯模型法）對台灣地區男女自殺死亡資料來配適模型。結果發現在假設世代效應與性別無關的前提下，年齡方面， 女性的自殺死亡率在10歲到24歲時顯著比男性高，在15到19歲這個年齡層差異達到最大，20歲之後差異開始變小，到了25至34歲，兩性則已無顯著差異，35歲之後男性的自殺死亡率開始顯著大於女性，並且隨著年齡增長兩性的差異越大，直到60歲之後差異才開始減小，到70歲時兩性無顯著差異。年代方面，男女的自殺死亡率在1959年到1973年間沒有顯著的差異，在1974到1988年女性的自殺死亡率顯著大於男性並於1979年到1983年來到最低點，也就是差異最大，之後差異開始變小，到了1989年時兩性已無顯著差異，從1994年開始男性的自殺死亡率反而開始顯著大於女性，而且隨著年代增加差異越大，並於2004到2008這個年代層差異達到最大。 / To understand the differences in suicide mortality between men and women in Taiwan, this study uses the Multivariate Age-Period-Cohort model proposed by Held and Riebler (2010), and explores the differences in suicide mortality between men and women on age, period and cohort effects adjusted for the other two. We use both unconditional likelihood function method (or log-linear model) and conditional likelihood function method (or multinomial logit model) to fit the model. Assuming that the cohort effect is independent of the gender, female suicide mortality in the age of 10 to 24 years old appears significantly higher than that of male, and the maximum age difference appears at the age of 15 to 19 years old. The difference is getting smaller after the age of 20, and gender difference is no longer significant between age of 25 to 34. After 35-year-old, male suicide death rate starts to exceed that of female, and the difference increases until the age of 60. After 60 years old, the difference starts to decrease till age of 70 at which there is no significant gender differences. There is no significant gender-specific suicide mortality difference between years 1959 and 1973. From 1974 to 1988 female suicide mortality rate is significantly greater than male. The difference reaches the peak in1979 to 1983. After that, the difference is getting smaller, and gender difference is no longer significant between 1989 and 1993. From 1994, suicide mortality for men begins to be significantly greater than women, and the difference increases with period. This difference reaches the maximum level in 2004 to 2008.

台灣地區居民近年的死亡率下降速度加快，使得我國國民的平均壽命在公元2000年已超過美國，成為長壽的國家之一。其中我國國民死亡率的下降幅度因年齡而不同，且各個年代、世代也不相同，與APC（Age-Period-Cohort）模型採年齡、年代與世代三個因子分析死亡率頗為一致，因此本文計畫以APC模型研究台灣的死亡率。然而，由於「年代＝年齡＋世代」之線性相關，參數估計值有甄別問題（Identification Problem），使得參數估計值不唯一。 文獻中有不同方法解決APC模型的參數估計問題，近年又有Fu（2000）提出之本質估計量（Intrinsic Estimator），可直接解決參數估計及其變異數。因此本文首先以電腦模擬驗證本質估計量，以及過去其他估計方法，檢測這些方法是否可得出理論的結果。本文的第二部分則以西元1961至2005年的資料探討APC模型的實用性，分析APC與Lee-Carter模型的優劣；研究發現APC模型用於估計死亡率時，整體而言雖不如Lee-Carter模型，但可彌補Lee-Carter模型在高年齡有較大誤差的不足，唯在年輕族群則仍有改善空間，未來或可考慮APC與Lee-Carter模型的結合。 / The mortality rates in Taiwan area have been experiencing dramatic decreases in recent years. The life expectancy has surpassed that in the United States in 2000 and Taiwan has become one of the longevity countries. Besides, the falling of mortality rates varies in different age, period, and cohort groups, which corresponds to the APC (Age-Period-Cohort) model. Therefore, the goal of this paper is to study the mortality rates in Taiwan area with APC model. However, due to the linear dependency of age, period and cohort (Period = Age + Cohort), there is the identification problem, that is, the parameter estimates are not unique. A number of solutions to the identification problem in APC model have been provided in the literature. Fu (2000) introduce a new estimator, the Intrinsic Estimator (IE), which can solve parameter estimates and variance directly. In the first part of this research, computer simulation is conducted to examine the IE, compared with other methodologies. In the second part of this research, data from 1961 to 2005 are used for verifying the validity of APC model in fitting mortality rates, and we analyze the strengths and weaknesses between the APC and Lee-Carter model. The results from our study indicate that the APC model in estimating mortality rates does not show as well as the Lee-Carter model as a whole. However, the APC model performs better than the Lee-Carter model for the elderly mortality rates, but is still needed to be improved in young groups. In the future, it can be considered to combine the APC and Lee-Carter model.

20世紀以來，因為衛生醫療等因素的進步，各年齡死亡率均大幅下降，使得平均壽命大幅延長。壽命延長的效果近年逐漸顯現，其中的人口老化及其相關議題較受重視，因為人口老化已徹底改變國人的生活規劃，死亡率是否會繼續下降遂成為熱門的研究課題。描述死亡率變化的模型很多，近代發展的Age–Period–Cohort模型(簡稱APC模型)，同時考慮年齡、年代與世代三個解釋變數，是近年廣受青睞的模型之一。這個模型將死亡率分成年齡、年代與世代三個效應，常用於流行病學領域，探討疾病、死亡率是否與年齡、年代、世代三者有關，但一般僅作為資料的大致描述，本研究將評估APC模型分析死亡率的可能性。 APC模型最大的問題在於不可甄別(Non–identification)，即年齡、年代與世代三個變數存有共線性的問題，眾多的估計APC模型參數方法因應甄別問題而生。本研究預計比較七種較常見的APC模型估計方法，包括本質估計量(IE)、限制的廣義線性模型(cglim_age、cglim_period與cglim_cohort)、序列法ACP、序列法APC與自我迴歸模型(AR)，以確定哪一種估計方法較為穩定，評估包括電腦模擬與實證分析兩部份。 電腦模擬部份比較各估計方法，衡量何者有較小的年齡別死亡率及APC參數的估計誤差；實證分析則考慮交叉分析，尋找用於死亡率預測的最佳估計方法。另外，也將以蒙地卡羅檢驗APC的模型假設，以確定這個模型的可行性。初步研究發現，以台灣死亡資料做為實證，本研究考量的估計方法在估計年齡別死亡率大致相當，只是在年齡–年代–世代這三者有不同的詮釋，且模型假設並非很符合。交叉分析上，Lee–Cater模型及其延展模型相對於APC模型有較小的預測誤差，整體顯示Lee–Cater 模型較佳。 / Since the beginning of the 20th century, the human beings have been experiencing longer life expectancy and lower mortality rates, which can attributed to constant improvements of factors such as medical technology, economics, and environment. The prolonging life expectancy has dramatically changed the life planning and life style after the retirement. The change would be even more severe if the mortality rates have larger reduction, and thus the study of mortality become popular in recent years. Many methods were proposed to describe the change of mortality rates. Among all methods, the Age-Period-Cohort model (APC) is a popular method used in epidemiology to discuss the relation between diseases, mortality rate, age, period and cohort. Non-identification (i.e. collinearity) is a serious problem for APC model, and many methods used in the procedure included estimation of parameter. In the first part of this paper, we use simulation compare and evaluate popular estimation methods of APC model, such as Intrinsic Estimator (IE), constrained of age, period and cohort in the Generalized Linear Model (c–glim), sequential method, and Auto-regression (AR) Model. The simulation methods considered include Monte-Carlo and cross validation. In addition, the morality data in Taiwan (Data sources: Ministry of Interior), are used to demonstrate the validity and model assumption of these methods. In the second part of this paper, we also apply similar research method to the Lee-Carter model and compare it to the APC model. We found Lee–Carter model have smaller prediction errors than APC models in the cross–validation.

La présente thèse de doctorat visait d’abord à valider les résultats des études antérieures démontrant un accroissement de la prévalence des problèmes de santé mentale et ensuite, à évaluer l’importance du contexte social dans l’explication des changements de prévalence, à partir des effets d’âge, de période et de cohorte. L’atteinte de ces objectifs s’est faite à partir de deux études empiriques, chacune ciblant sa propre problématique en santé mentale. La première étude, basée sur les données de l’Enquête longitudinale nationale sur les enfants et les jeunes (ELNEJ) de Statistique Canada, a permis de conclure à un accroissement réel de la prévalence du diagnostic de trouble déficitaire de l’attention/hyperactivité (TDA/H) et de la consommation de psychostimulants chez les enfants canadiens entre 1994 et 2007. Toutefois, cette tendance n’est ni constante, ni universelle, puisque des effets de période et d’âge apparaissent clairement : l’augmentation des prévalences est uniquement remarquée dans les années 2000, et survient seulement chez les enfants d’âge scolaire. L’identification d’inégalités de prévalence dues à la période historique et à l’âge des enfants souligne l’importance du contexte social dans la problématique du diagnostic de TDA/H et de la consommation de psychostimulants. La seconde étude a été réalisée à partir des données du Panel Study of Belgian Households (PSBH) et cherchait à expliquer l’accroissement des symptômes dépressifs observé ces vingt dernières années chez les adultes belges. L’utilisation de l’analyse multiniveaux longitudinale permettant la distinction des effets d’âge et des effets de cohortes a été privilégiée. Bien que l’intensité des symptômes dépressifs ait varié de manière relativement importante chez les individus au cours des années 1990, nos conclusions démontrent que les symptômes auto-rapportés de dépression sont davantage associés aux conditions de vie, qu’à la personnalité. L’augmentation résulte d’un effet de la succession des cohortes, où les individus des cohortes les plus récentes rapportent toujours une plus grande intensité de symptômes dépressifs que les individus des cohortes précédentes. Les membres d’une même cohorte de naissance partagent donc des expériences communes à un âge similaire, ce qui a un impact durable sur leurs comportements et sur leur santé mentale. De manière générale, les résultats des deux articles empiriques ont, chacun à leur manière, confirmé la réalité de l’accroissement des problèmes de santé mentale dans les sociétés occidentales contemporaines, et permis de constater que la prévalence diffère selon l’âge et la cohorte de naissance des individus, ainsi que selon la période historique, renforçant ainsi l’hypothèse de l’importance des facteurs sociaux dans l’étiologie des problèmes de santé mentale. Bien que la nature de ces facteurs n’ait pu être testée de manière directe, de nombreuses explications sociales furent tout de même proposées. À cet égard, des changements dans les normes comportementales associées à l’âge, dans les normes sociales, dans la conceptualisation des troubles mentaux, des modifications dans la sphère éducative, ainsi que des innovations pharmacologiques, médicales et technologiques constituent des explications sociales aux effets d’âge, de période et de cohorte qui ont été observés. / This doctoral dissertation aimed to validate findings from previous studies indicating an increase in the prevalence of mental health problems, and to evaluate the importance of contextual factors in explaining this increase in prevalence. Age, period and cohort effects were considered proxies for social context factors. These objectives were achieved through two empirical studies, each one focusing on a specific mental health problem. The first study analyzed data from the Statistics Canada National longitudinal survey on children and youth (NLSCY) and found significant increase in the prevalence of Attention-deficit/hyperactivity disorder (ADHD) diagnosis and the prescription of ADHD medications for Canadian children between 1994 and 2007. However, this tendency was not constant, or linear, as some period and age effects were found: an increase in prevalence was found only during the 2000s, and only for school-age children. These differences in prevalence rate by historical period and children’s age underline the importance of the social context in the diagnosing of ADHD diagnosis and prescription of ADHD medications. The second study used the data from the Panel Study of Belgian Households (PSBH) and aimed to explain the increase of depressive symptoms observed recently among Belgian adults. A longitudinal multilevel analysis, allowing for the disentanglement of age and cohort effects, was conducted. Our findings demonstrate that, despite a variation in the intensity of depressive symptoms within individuals during the 1990s, self-reported symptoms are mostly associated with a reaction to life conditions rather than with personality. The increase over time results from an effect of cohort succession, where individuals from the most recent cohort always report more depressive symptoms than individuals from the oldest cohorts. Members from the same cohort share common experiences at a similar age, which has a durable impact on their behaviors and mental health. In general, results from our two empirical studies confirmed, each in their own way, that mental health problems have increased in contemporary Western societies. Moreover, findings demonstrated that prevalence differs according to age, birth cohort and historical period, thus reinforcing the importance of social factors in the etiology of mental health problems. Although the true nature of these social factors could not be directly examined, many social explanations were proposed. For example, the changes in behavioral norms associated with age, social norms, the conceptualization of mental health problems, and to the school system, as well as innovations in pharmacological, medical and technological fields across this period are all potential factors explaining these age, period and cohort effects.