Bayesian models for data missing not at random in health examination surveys

In epidemiological surveys, data missing not at random (MNAR) due to survey nonresponse may potentially lead to a bias in the risk factor estimates. We propose an approach based on Bayesian data augmentation and survival modelling to reduce the nonresponse bias. The approach requires additional information based on follow-up data. We present a case study of smoking prevalence using FINRISK data collected between 1972 and 2007 with a follow-up to the end of 2012 and compare it to other commonly applied missing at random (MAR) imputation approaches. A simulation experiment is carried out to study the validity of the approaches. Our approach appears to reduce the nonresponse bias substantially…

Reilu ruokamurros : Polkuja kestävään ja oikeudenmukaiseen ruokajärjestelmään

Ruokajärjestelmämme kärsivät monista yhteen kietoutuneista kestävyysongelmista. Ongelmia ei korjata yksittäisillä teknologisilla ratkaisuilla, vaan muutoksia tarvitaan läpi koko ruokajärjestelmän. Muutosten laajuuden vuoksi on syytä puhua järjestelmän perustavanlaatuisesta muuttamisesta eli ruokamurroksesta. Tässä julkaisussa tarkastelemme, miten ruokajärjestelmän ilmastopäästöjä voitaisiin vähentää Suomessa siten, että ruokaturva ei vaarannu. Arvioimme ilmastotoimien toteutusta eri murrospoluilla, jotka keskittyvät maankäytön, ruokavalioiden, maatalous- ja ruokateknologioiden muutoksiin. Arvioimme eri murrospolkujen vaikutuksia maatalouteen eri alueilla ja eri väestöryhmien ravitsemukseen.…

Correction: Correcting for non-ignorable missingness in smoking trends

Adjusting for selective non-participation with re-contact data in the FINRISK 2012 survey

Aims: A common objective of epidemiological surveys is to provide population-level estimates of health indicators. Survey results tend to be biased under selective non-participation. One approach to bias reduction is to collect information about non-participants by contacting them again and asking them to fill in a questionnaire. This information is called re-contact data, and it allows to adjust the estimates for non-participation. Methods: We analyse data from the FINRISK 2012 survey, where re-contact data were collected. We assume that the respondents of the re-contact survey are similar to the remaining non-participants with respect to the health given their available background informa…

Participation rates by educational levels have diverged during 25 years in Finnish health examination surveys

Background Declining participation rates in health examination surveys may impair the representativeness of surveys and introduce bias into the comparison of results between population groups if participation rates differ between them. Changes in the characteristics of non-participants over time may also limit comparability with earlier surveys. Methods We studied the association of socio-economic position with participation, and its changes over the past 25 years. Occupational class and educational level are used as indicators of socio-economic position. Data from six cross-sectional FINRISK surveys conducted between 1987 and 2012 in Finland were linked to national administrative registers…

Correcting for non-ignorable missingness in smoking trends

Data missing not at random (MNAR) is a major challenge in survey sampling. We propose an approach based on registry data to deal with non-ignorable missingness in health examination surveys. The approach relies on follow-up data available from administrative registers several years after the survey. For illustration we use data on smoking prevalence in Finnish National FINRISK study conducted in 1972-1997. The data consist of measured survey information including missingness indicators, register-based background information and register-based time-to-disease survival data. The parameters of missingness mechanism are estimable with these data although the original survey data are MNAR. The u…

Selection bias was reduced by recontacting nonparticipants

Objective One of the main goals of health examination surveys is to provide unbiased estimates of health indicators at the population level. We demonstrate how multiple imputation methods may help to reduce the selection bias if partial data on some nonparticipants are collected. Study Design and Setting In the FINRISK 2007 study, a population-based health study conducted in Finland, a random sample of 10,000 men and women aged 25–74 years were invited to participate. The study included a questionnaire data collection and a health examination. A total of 6,255 individuals participated in the study. Out of 3,745 nonparticipants, 473 returned a simplified questionnaire after a recontact. Both…

Systematic handling of missing data in complex study designs : experiences from the Health 2000 and 2011 Surveys

We present a systematic approach to the practical and comprehensive handling of missing data motivated by our experiences of analyzing longitudinal survey data. We consider the Health 2000 and 2011 Surveys (BRIF8901) where increased non-response and non-participation from 2000 to 2011 was a major issue. The model assumptions involved in the complex sampling design, repeated measurements design, non-participation mechanisms and associations are presented graphically using methodology previously defined as a causal model with design, i.e. a functional causal model extended with the study design. This tool forces the statistician to make the study design and the missing-data mechanism explicit…

Psychomotor speed in a random sample of 7,979 subjects aged 30 years and over.

Background and aims: Slowing of psychomotor speed among older individuals has been shown in numerous studies. However, in most cases these studies were based on small and selected groups of people and, in some cases, the test procedures did not allow separation of decision time and motor components of the overall performance. The purpose of the present study was to analyse in a large, randomly selected population sample the differences in decision and movement times in simple and multiple-choice test conditions. The association of educational background with psychomotor speed was also examined. Methods: Data on psychomotor speed were collected from a representative nation-wide sample of the…

Recommendations for design and analysis of health examination surveys under selective non-participation

Background The decreasing participation rates and selective non-participation peril the representativeness of health examination surveys (HESs). Methods Finnish HESs conducted in 1972–2012 are used to demonstrate that survey participation rates can be enhanced with well-planned recruitment procedures and auxiliary information about survey non-participants can be used to reduce selection bias. Results Experiments incorporated to pilot surveys and experience from previously conducted surveys lead to practical improvements. For example, SMS reminders were taken as a routine procedure to the Finnish HESs after testing their effect on a pilot study and finding them as a cost-effective way to inc…

Non-participation modestly increased with distance to the examination clinic among adults in Finnish health examination surveys

Aims: Health examination surveys (HES) provide important information about population health and health-related factors, but declining participation rates threaten the representativeness of collected data. It is hard to conduct national HESs at examination clinics near to every sampled individual. Thus, it is interesting to look into the possible association between the distance from home to the examination clinic and non-participation, and whether there is a certain distance after which the participation activity decreases considerably. Methods: Data from two national HESs conducted in Finland in 2011 and 2012 were used and a logistic regression model was fitted to investigate how distanc…