Quantitative Methods for Estimating the Size of a Drug-Using Population

1993 ◽  
Vol 23 (2) ◽  
pp. 185-216 ◽  
Author(s):  
Thomas D. Wickens
Keyword(s):  
Drug Use ◽  
System Dynamics ◽  
Quantitative Methods ◽  
Linear Models ◽  
Markov Models ◽  
Partially Observed ◽  
Capture Recapture ◽  
Closed Populations ◽  
Log Linear ◽  
Dynamics Models

The author describes several of the most important quantitative procedures for estimating the size of an unobserved or partially observed population, with specific application to the estimation of the prevalence of drug use. The methods discussed include synthetic estimation, truncated Poisson estimates, multiple-capture surveys in both closed populations (the capture-recapture model and log-linear models) and open populations (the Jolly-Seber model and Markov models), and, more briefly, system dynamics models.

scholarly journals Estimating infectious diseases incidence: validity of capture–recapture analysis and truncated models for incomplete count data

2007 ◽  
Vol 136 (1) ◽  
pp. 14-22 ◽  
Author(s):  
N. A. H. VAN HEST ◽  
A. D. GRANT ◽  
F. SMIT ◽  
A. STORY ◽  
J. H. RICHARDUS
Keyword(s):  
Infectious Disease ◽  
Count Data ◽  
Disease Surveillance ◽  
Cross Validation ◽  
Linear Models ◽  
Disease Incidence ◽  
Infectious Disease Surveillance ◽  
Number Of Patients ◽  
Capture Recapture ◽  
Log Linear

SUMMARYCapture–recapture analysis has been used to evaluate infectious disease surveillance. Violation of the underlying assumptions can jeopardize the validity of the capture–recapture estimates and a tool is needed for cross-validation. We re-examined 19 datasets of log-linear model capture–recapture studies on infectious disease incidence using three truncated models for incomplete count data as alternative population estimators. The truncated models yield comparable estimates to independent log-linear capture–recapture models and to parsimonious log-linear models when the number of patients is limited, or the ratio between patients registered once and twice is between 0·5 and 1·5. Compared to saturated log-linear models the truncated models produce considerably lower and often more plausible estimates. We conclude that for estimating infectious disease incidence independent and parsimonious three-source log-linear capture–recapture models are preferable but truncated models can be used as a heuristic tool to identify possible failure in log-linear models, especially when saturated log-linear models are selected.

scholarly journals A Test for the Underlying State-Structure of Hidden Markov Models: Partially Observed Capture-Recapture Data

2021 ◽  
Vol 9 ◽  
Author(s):  
Anita Jeyam ◽  
Rachel S. McCrea ◽  
Roger Pradel
Keyword(s):  
Hidden Markov Models ◽  
Markov Models ◽  
Hidden Markov ◽  
Canada Geese ◽  
State Structure ◽  
Data Set ◽  
Partial Observations ◽  
Partially Observed ◽  
Capture Recapture ◽  
Special Case

Hidden Markov models (HMMs) are being widely used in the field of ecological modeling, however determining the number of underlying states in an HMM remains a challenge. Here we examine a special case of capture-recapture models for open populations, where some animals are observed but it is not possible to ascertain their state (partial observations), whilst the other animals' states are assigned without error (complete observations). We propose a mixture test of the underlying state structure generating the partial observations, which assesses whether they are compatible with the set of states observed in the complete observations. We demonstrate the good performance of the test using simulation and through application to a data set of Canada Geese.

scholarly journals Capture–Recapture Techniques for Transport Survey Estimate Adjustment Using Permanently Installed Highway-Sensors

2019 ◽  
pp. 089443931987468 ◽  
Author(s):  
Jonas Klingwort ◽  
Bart Buelens ◽  
Rainer Schnell
Keyword(s):  
Logistic Regression ◽  
The Netherlands ◽  
Sensor Network ◽  
Linear Models ◽  
Sensor Data ◽  
Point Estimate ◽  
Road Freight ◽  
Downward Bias ◽  
Capture Recapture ◽  
Log Linear

In this article, survey, sensor, and administrative data are combined to correct for survey point estimate bias due to underreporting. The response to the Dutch Road Freight Transport Survey is linked to records from a road sensor network consisting of automated weighing stations installed on highways in the Netherlands. Capture–recapture (CRC) methods are used to estimate underreporting in the survey. Heterogeneity of the vehicles with respect to capture and recapture probabilities is modeled through logistic regression and log-linear models. Six different estimators are discussed and compared. Results show a downward bias in the survey estimate due to underreporting, whereas the CRC estimators yield larger estimates. This research is a new example of multisource statistics, a promising approach to improve the benefits of sensor data in the field of official statistics.

Estimating the prevalence and incidence of multiple sclerosis in the Lorraine region, France, by the capture–recapture method

2012 ◽  
Vol 18 (9) ◽  
pp. 1244-1250 ◽  
Author(s):  
Haritina El Adssi ◽  
Marc Debouverie ◽  
Francis Guillemin ◽  
Keyword(s):  
Multiple Sclerosis ◽  
Medical Records ◽  
Linear Models ◽  
Health Insurance System ◽  
Regional Health ◽  
Crude Incidence ◽  
Capture Recapture ◽  
Log Linear ◽  
Incident Cases ◽  
Crude Prevalence

Objective: The objective of this study was to assess the prevalence and incidence of multiple sclerosis (MS) in the Lorraine region, in France. Methods: Data from three sources – Regional Health Insurance System, medical records departments and the Lorraine registry of MS – and a capture–recapture method with log-linear models were used to estimate the prevalence and incidence of MS. Results: We identified 7193 records of reported MS corresponding to 4299 unique suspected cases of MS existing on 31 December 2008, in Lorraine. On the basis of the 4001 validated cases, the observed crude prevalence of MS was 170.9 cases per 100,000 inhabitants (95% confidence interval [CI]: 165.7; 176.3), and the observed annual crude incidence of MS was 4.4 cases per 100,000 inhabitants (95% CI: 3.6; 5.4). With the capture–recapture method, the estimated prevalence of MS was 4405.7 (95% CI: 4261.5; 4629.7), so an estimated 405 cases were not identified by the three sources. The estimated prevalence was 188.2 cases per 100,000 inhabitants (95% CI: 182.7; 193.8), and the estimated annual incidence was 8.5 cases per 100,000 inhabitants (95% CI: 7.3; 9.7). Conclusions: The capture–recapture method allowed us to estimate an additional 10.1% of unobserved prevalent cases and to anticipate 47.5% of unobserved incident cases.

Log-Linear Models for Capture-Recapture

Biometrics ◽  
1989 ◽  
Vol 45 (2) ◽  
pp. 395 ◽  
Author(s):  
R. M. Cormack
Keyword(s):  
Linear Models ◽  
Capture Recapture ◽  
Log Linear

Estimate General Practitioners Active Supply in Iran: Capture-Recapture Method for Three Data Sources

2020 ◽  
Author(s):  
Azad SHOKRI ◽  
Ali AKBARI-SARI ◽  
Mahboubeh BAYAT ◽  
Mahmoud KHODADOST ◽  
Abbas RAHIMI FOROUSHANI ◽  
...  
Keyword(s):  
Human Resource ◽  
General Practitioners ◽  
Linear Models ◽  
Cross Sectional Study ◽  
Data Sources ◽  
Accurate Estimation ◽  
Medical Council ◽  
Cross Sectional ◽  
Capture Recapture ◽  
Log Linear

Background: Accurate estimation of active general practitioners (GPs) is a concern for health authorities to estimate requirements. This study aimed to accurately estimate GPs active supply in Iran using three sources capture-recapture (CRC) method. Methods: This cross-sectional study collected data during 2015-2016, targeting all GPs registered in three independent data sources; a national survey from all hospitals, database of human resource management office at health ministry and physicians' offices databank. Variables including medical council codes, GP names, surnames and national ID codes were used for data linkage among the three sources. Three sources CRC method was applied using log-linear models to estimate the total number of active GPs in STATA software. Results: Overall, 27,048 GPs were identified after removing the duplicate records. Based on CRC three sources data, the total number of GPs were 53,630 in 2015-2016. Distribution of GPs per 1,000 population among the provinces indicates that provinces of Kohgiluyeh & Boyer Ahmad, Mazandaran, Golestan and Yazd with ratios of 1.28, 1.28, 1.21 and 1.17 physicians rank the highest proportion of GPs and the provinces of Sistan & Baluchestan, Ilam, Zanjan, Alborz, North Khorasan with corresponding ratios of 0.24, 0.40, 0.40, 0.43 and 0.45 GPs ranked the lowest. Conclusion: CRC method is known to be the best and rapidest method to estimate active GP due to its compatibility for the current situation of databanks in Iran. Therefore, this method is a good application in human resource distribution and planning.

Measuring the Change in Contingency Tables Using Markov Models — Application to the Effect of Preceding Conception on the Next one

1982 ◽  
Vol 21 (01) ◽  
pp. 31-33
Author(s):  
A. K. Saleh ◽  
M. A. A. Moussa ◽  
H. Hathout ◽  
R. Kasraoui
Keyword(s):  
Linear Models ◽  
Markov Models ◽  
Transition Probabilities ◽  
Sequence Data ◽  
Contingency Tables ◽  
Maternity Hospital ◽  
Time Sequence ◽  
Maximum Likelihood Estimates ◽  
Previous Pregnancy ◽  
Log Linear

A method is described for the analysis of time sequence data viewed as contingency tables. This includes 1.) determining the maximum likelihood estimates of stationary and transition probabilities; 2.) testing stationarity of transition probabilities in first and second order Markov models by fitting the data to the appropriate configuration of log-linear models; 3.) assessing the order of dependence through fitting log-linear models. Data based on a study recently conducted on women delivered in the Principal Maternity Hospital in Kuwait is used for illustration. It is concluded that conception outcome depends on pregnancy order as well as on at least two previous pregnancy outcomes.

Sign in / Sign up

Export Citation Format

Share Document