R Heshmat, A.a Keshtkar, R Sheykh-Ol-Eslam, M Baghery, A Nadim,
Volume 1, Issue 1 (12-2005)
Abstract
Background and Objectives:To compare three different methods of signal detection applied to the Adverse Drug Reactions registered in the Iranian Pharmacovigilance database from 1998 to 2005.
Materials and Methods:All Adverse Drug Reactions (ADRs) reported to Iranian Pharmacovigilance Center from March 1998 through January 2005, were included in the analysis. The data were analyzed based on three different signal detection methods including Reporting Odds Ratios (PRRs), Bayesian Propagation Neural Network (BCPNN) and Reporting Odds Ratios (RORs). Signals detected by each method were categorized based on the number of reports per drug-adverse event combination, severity of the event and labeled or unlabeled ADRs. The methods applied to signal detection were then compared in recognizing different types of adverse events.
Results: A total of 6353 cases of ADR reports, describing 11130 reactions, were reported to Iranian Pharmacovigilance Center (IPC) during the study period. The dataset involved 4975 drug-event combinations, which were assessed for detecting signals.
The counts of drug-event combinations was 1, 2 and 3 or more for 3470, 727 and 779 combinations, respectively. There were 500 drug items responsible for 468 reaction terms in the database. According to PRR and 95% Confidence Interval, there were 2838, 872 and 488 drug-event combinations known as a signal for the pairs with the reporting frequency of ³1, ³2 and ³3 reports, respectively. The signals detected with the criteria of PRR³2, c2³4 were 2930, 872 and 480 for the pairs with the same reporting frequencies.
Estimates of RORs and the 95% Confidence Interval showed that 2722, 862 and 481 drug-event combinations were detected to be signal for the pairs with the reporting frequency of ³1, ³2 and ³3 reports, respectively, while measuring IC and IC-2SD detected 1120, 378 and 235 cases for the same reporting frequencies. There were 234 signals detected by all three methods.
Conclusion: Despite the similarities between data mining methodologies for signal detection, there are differences in the numbers of signals detected by each method. The study findings suggest that quantitative signal detection methods should be added to the routine Pharmacovigilance activities in Iran and the trends for quantitative measures over time should be monitored.
J Hassan Zadeh , M Nasehi, A Rajaeifard, D Roshani , E Ghaderi ,
Volume 10, Issue 2 (9-2014)
Abstract
Recently, capture-recapture studies have been used and researchers tend to use these studies in the health field. Therefore, we discussed the basic concepts of these studies. First, we described capture-recapture studies. Then, the important assumptions and calculations were presented according to the close population assumption. Statistical formulas were presented for two-capture methods and dependency between the two lists was discussed. Then, we addressed more than two capture methods.
M Saadati, A Bagheri,
Volume 12, Issue 2 (8-2016)
Abstract
Sampling hidden populations is challenging due to the lack of convenience statistical frames. Since most populations exposed to special diseases are hidden and hard to reach, sampling methods that produce representative and efficient samples from the populations have become a study subject for researches all over the world. Because of the unknown probability of selecting samples in conventional sampling methods and also invalidity of generalizing the results of non-probability sampling methods to the statistical population, the necessity of introducing probability chain-referral sampling methods, such as the respondent driven sampling method becomes imperative. In this article, besides introducing the respondent driven sampling method, some of the advantages of this method as relative decrease of the bias of estimates, declining the non-response rate by paying incentives and allocating weights proportional to reciprocal of the social network size of respondents to produce unbiased estimates are described. Moreover, some disadvantages of this method such as lack of producing differential samples by selecting similar seeds, lack of reaching more efficient method than snowball sampling by implementing this method improperly and lack of achieving to equilibrium by existing weak social networks among members of interested population are stated. Another aim of this article is to compare sampling methods of hidden population with the respondent driven sampling method which are the results of implementing this method in different surveys and existing simulations.
R Ali Akbari Khoei, E Bakhshi, A Azarkeivan, A Biglarian,
Volume 12, Issue 3 (10-2016)
Abstract
Background and Objectives: A small sample size can influence the results of statistical analysis. A reduction in the sample size may happen due to different reasons, such as loss of information, i.e. existing missing value in some variables. This study aimed to apply bootstrap and jackknife resampling methods in survival analysis of thalassemia major patients.
Methods: In this historical cohort study, the data of 296 patients with thalassemia major who were visited at Zafar Clinic, Tehran, from 1994 to 2013 were used. Parametric survival models were used to analyze the data. The log – normal survival model was selected as the best model and then the bootstrap and jackknife resampling algorithms were used for this model. Data analysis was carried out with the STATA 12.0 software.
Results: The results of the resampling methods showed that standard errors decreased and confidence intervals were shortened. In addition, the result of the bootstrap and jackknife resampling methods showed that age group and the relationship of the parents (P<0.001) were significant compared with the log-normal model (P>0.900).
Conclusion: Comparison of the confidence intervals suggests that the jackknife resampling method can be used when the sample size is small.
