BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Institute of Applied Statistics and Data Science - ECPv6.17.1//NONSGML v1.0//EN
CALSCALE:GREGORIAN
METHOD:PUBLISH
X-ORIGINAL-URL:https://isrt.ac.bd
X-WR-CALDESC:Events for Institute of Applied Statistics and Data Science
REFRESH-INTERVAL;VALUE=DURATION:PT1H
X-Robots-Tag:noindex
X-PUBLISHED-TTL:PT1H
BEGIN:VTIMEZONE
TZID:UTC
BEGIN:STANDARD
TZOFFSETFROM:+0000
TZOFFSETTO:+0000
TZNAME:UTC
DTSTART:20160101T000000
END:STANDARD
END:VTIMEZONE
BEGIN:VTIMEZONE
TZID:UTC
BEGIN:STANDARD
TZOFFSETFROM:+0000
TZOFFSETTO:+0000
TZNAME:UTC
DTSTART:20160101T000000
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTART;TZID=UTC:20200617T110000
DTEND;TZID=UTC:20200617T130000
DTSTAMP:20201030T062612Z
CREATED:20201030T062612Z
LAST-MODIFIED:20201030T062612Z
UID:4458-1592391600-1592398800@isrt.ac.bd
SUMMARY:Visualizing world-wide Covid-19 data using R\, especially ggplot2
DESCRIPTION:Title:  “Visualizing world-wide Covid-19 data using R\, especially ggplot2” \n  \nSpeaker: Professor Mahbub Latif \, ISRT\, University of Dhaka \nDate &Time: Wednesday\, June 17\, 2020 at 11.00 AM.
URL:https://isrt.ac.bd/event/visualizing-world-wide-covid-19-data-using-r-especially-ggplot2/
CATEGORIES:seminar
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=UTC:20200203T113000
DTEND;TZID=UTC:20200203T130000
DTSTAMP:20200130T024252Z
CREATED:20200130T022629Z
LAST-MODIFIED:20200130T024252Z
UID:4138-1580729400-1580734800@isrt.ac.bd
SUMMARY:Big Data Analytics: Wisdom or Folly!
DESCRIPTION:Title: Big Data Analytics: Wisdom or Folly! \n\nTime and venue: 11:30 am on 3rd of February (Monday) 2020 in ISRT Seminar Room\n\nSpeaker: Ejaz Ahmed\, PhD Professor at Brock University\, Canada\n\nAbstract:\n\nThere are hosts of buzzwords in today’s data-centric world\, and especially in digital and print media. We encounter data in every walks of life\, and for analytically and objectively-minded people\, data is everything. However\, making sense of the data and extracting meaningful information from it may not be an easy task. We come across buzzwords such as big data\, high dimensional data\, data science\, and open data without a proper definition of such words. The rapid growth in the size and scope of data sets in a host of disciplines has created a need for innovative statistical strategies analyzing such data. For example\, many private and public agencies are using sophisticated data mining strategies and/or big data analytics to reveal patterns based on collected information. Some examples of big data that have prompted demand are digital marketing\, customer service standards\, gene expression arrays\, social network modeling\, clinical\, genetics and phenotypic data. \nThe need for novel statistical strategies to analyze such data sets is pressing. This talk focuses on the development of statistical and computational strategies for a sparse regression model in the presence of mixed signals. The existing estimation methods have often ignored contributions from weak signals. However\, in real scenario many predictors altogether provide useful information for prediction\, although the amount of such useful information in a single predictor might be modest. The search for such signals\, sometimes called networks or pathways\, is for instance an important topic for those working on personalized medicine. We discuss a new “post selection shrinkage estimation strategy” that takes into account the joint impact of both strong and weak signals to improve the prediction accuracy and opens pathways for further research in such scenarios.
URL:https://isrt.ac.bd/event/big-data-analytics-wisdom-or-folly/
CATEGORIES:seminar
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=UTC:20200102T150000
DTEND;TZID=UTC:20200102T160000
DTSTAMP:20191230T090712Z
CREATED:20191230T084938Z
LAST-MODIFIED:20191230T090712Z
UID:3875-1577977200-1577980800@isrt.ac.bd
SUMMARY:Is Data Science the next step for the Statisticians?
DESCRIPTION:Data Science was hot a few years ago. It is no longer a hot topic. The tremendous growth in terms of using/adopting data science\, machine learning that the scientific community and the industry have observed over the past two years is noteworthy. Good thing is\, statisticians are gradually coming out of their cocoon to experience the new landscape. In this talk\, I will discuss why and how statisticians should take the next steps to learn machine learning before they (statisticians) potentially become obsolete in the industry.
URL:https://isrt.ac.bd/event/is-data-science-the-next-step-for-the-statisticians/
LOCATION:ISRT Seminar Room (3rd floor)\, Institute of Statistical Research and Training\, University of Dhaka\, Dhaka\, Please Select\, 1000\, Bangladesh
CATEGORIES:seminar
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=UTC:20191203T140000
DTEND;TZID=UTC:20191203T153000
DTSTAMP:20191124T172807Z
CREATED:20191124T172807Z
LAST-MODIFIED:20191124T172807Z
UID:3762-1575381600-1575387000@isrt.ac.bd
SUMMARY:PhD seminar talk on Tuesday\, December 3\, 2019 at 2pm
DESCRIPTION:Title: Modified Inferential Methods on Restricted Parameters in Multivariate Regression Analysis: Applications in Socio-demographic Research\n\nSpeaker: Sheikh Mohammad Sayem\, PhD researcher at ISRT\, DU\n\nAbstract:\n\nEfficient and significant empirical estimate of the multivariate regression parameters will be helpful for the policymaker to make the right decisions about sophisticated interrelated issues in the dynamic world. Since the end of the twentieth century\, statisticians are going forward to develop unique working methodology for estimating and testing restricted parameters. This study reviews existing methods and suggests modified maximum likelihood estimator\, modified multivariate t statistic and modified joint confidence interval to get efficient estimates for linear restricted parameters of multivariate regression with continuous responses. A Monte Carlo experiment is conducted to examine relative performance of the modified methods. The proposed methodology has been also applied to detect the numerical nexus among socioeconomic determinants\, food expenditure and total monthly expenditure in “Haor” areas of Bangladesh. The study reveals that logarithm form of total monthly expenditure and food expenditure as multivariate continuous responses are significantly related to total operating land\, logarithm form of family size and total monthly income considering a restriction on the parameters at different level of significance. The modified methods are found to perform significantly better than the existing methods.
URL:https://isrt.ac.bd/event/phd-seminar-talk-on-tuesday-december-3-2019-at-2pm/
CATEGORIES:seminar
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=UTC:20190827T140000
DTEND;TZID=UTC:20190827T150000
DTSTAMP:20190813T104343Z
CREATED:20190813T103955Z
LAST-MODIFIED:20190813T104343Z
UID:3597-1566914400-1566918000@isrt.ac.bd
SUMMARY:PhD seminar talk on August 27 at 2pm
DESCRIPTION:Title: Improved Statistical Approach for Climate Projection over Bangladesh using Downscaling of Global Climate Model (GCM) Outputs\n\nSpeaker: Md. Bazlur Rashid\n\nAbstract:\nGlobal Climate Model (GCM) has evolved from the Atmospheric General Circulation Models\n(AGCMs) widely used for daily\, seasonal and long term weather prediction. The most widely\nrecognized application is the projection of future climate states under various scenarios of\nincreasing atmospheric elements. Over the last few decades\, GCMs have been developed to\nemulate the present climate system and to project future climate scenarios. Despite notable\ndevelopment\, GCMs do not provide perfect simulations of reality and cannot provide the details\non very small spatial scales due to incomplete scientific understanding and limitations of\navailable observations in our country. For bridging the gap between the scale of GCMs and\nrequired resolution for practical applications\, downscaling provides climate change information\nat a suitable spatial and temporal scale from the GCM data. No downscaling for Bangladesh of\ndetail temperature\, precipitation\, wind speed\, pressure and humidity has been undertaken.\nCurrent research in Bangladesh has not addressed thermal comfort under climate change. In\naddition\, current studies for Bangladesh do not look at seasonality clearly. Extreme events\n(rainfall and temperature)\, thermal comfort\, humidity and wind characteristics\, along with\nseasonality\, under future climate in Bangladesh represent a further research gap and opportunity\nfor this research. The main object of study will attempt to find and/or develop efficient statistical\nmethods/tools for climate projection. The specific objectives are (i) to identify suitable model\nwith bias corrections for climate projection using climate model outputs; (ii) to explore the\neffectiveness of the bias correction statistical downscaling method in addressing the model-\nrelated uncertainties involved in future climate predictions; (iii) to identify a suitable\ndownscaling approach for climate model data to allow daily/ monthly or seasonal meteorological\nclimate impact studies; (iv) to develop modify algorithms for quantifying the time-variant\nuncertainty associated with meteorological extreme weather systems and persistent events under\nfuture climate scenarios and (v) to cross check between available statistical downscaling\ntechniques for future climate projections and scenarios generation over Bangladesh. So\, GCM\ninformation can be enhanced for better representation of the conditions in specific places by\nusing historically observed local climate information from weather stations. Statistical\nDownscaling of climate model can include independent components of climatic signals like El\nNino-Southern Oscillations (ENSO)\, Indian Ocean Dipole (IOD) and Pacific Decadal\nOscillations (PDO) for a long-lead weather forecast. So\, this information can also be used to\nimprove the future climate projections to assess potential impacts and guide climate-smart\ndecisions about climate resilience in Bangladesh.
URL:https://isrt.ac.bd/event/3597/
LOCATION:isrt seminar room
CATEGORIES:seminar
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=UTC:20190730T140000
DTEND;TZID=UTC:20190730T150000
DTSTAMP:20190727T010829Z
CREATED:20190727T010829Z
LAST-MODIFIED:20190727T010829Z
UID:3560-1564495200-1564498800@isrt.ac.bd
SUMMARY:Seminar on Tuesday\, 30th July 2019 from 2:00-3:00 pm
DESCRIPTION:Title: Optimum designs for multiple objectives \nSpeaker: Mahbub Latif\, PhD \nProfessor\, ISRT \nUniversity of Dhaka \nVenue: ISRT Seminar Room \nAbstract: \nTBA
URL:https://isrt.ac.bd/event/seminar-on-tuesday-30th-july-2019-from-200-300-pm/
CATEGORIES:seminar
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=UTC:20190115T140000
DTEND;TZID=UTC:20190115T150000
DTSTAMP:20190110T134806Z
CREATED:20190107T065821Z
LAST-MODIFIED:20190110T134806Z
UID:2996-1547560800-1547564400@isrt.ac.bd
SUMMARY:Seminar on 15 January Tuesday at 2 pm
DESCRIPTION:Title: Long-run relationship between the unemployment rate and the trade balance in the United States: an empirical analysis \nSpeaker: Haydory Akbar Ahmed \nMissouri State University \nDepartment of Economics\, 901 S National Avenue \nSpringfield\, MO 65897\, USA \n  \nAbstract: \nDynamics between the unemployment rate and the trade balance has both economic and political relevance.\nFrom a macroeconomic perspective\, the presence of a long run co-movement or equilibrium relationship\nalong with the nature of the short-run fluctuations in the long run co-movement will help us analyze the\ndynamics between the two in an objective manner. We use quarterly data from 1947: Q1 to 2017: Q4 on\nunemployment and trade balance to GDP ratio in the United States. Although traditional cointegration\ntests fail to detect a statistically significant long run co-movement\, a couple of threshold cointegration tests\nconfirm statistical evidence in favor of threshold cointegration or threshold long run co-movement between\nthe two. Estimated threshold vector error-correction model shows statistically significant evidence of falling\nunemployment rate with deteriorating trade balance. This finding indicates that as unemployment rates go\ndown\, the trade balance deteriorates to maintain the long run co-movement. Arguably\, as unemployment\ndecline imports rise faster than exports causing the trade balance to deteriorate.
URL:https://isrt.ac.bd/event/seminar-on-15-january-tuesday-at-2-pm/
CATEGORIES:seminar
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=UTC:20181021T140000
DTEND;TZID=UTC:20181021T153000
DTSTAMP:20181019T063917Z
CREATED:20181019T063917Z
LAST-MODIFIED:20181019T063917Z
UID:2834-1540130400-1540135800@isrt.ac.bd
SUMMARY:Seminar on Sunday\, 21 October 2018 at 2 pm
DESCRIPTION:Title: Joint Modeling of Longitudinal Response and Time-To-Event Data Using Conditional Distributions: A Bayesian Perspective\n\n \nSpeaker: Arindom Chakraborty\, PhD\n\n               Assistant Professor\n               Department of Statistics\n               Visva-Bharati University\, India\n \nAbstract: Over last twenty or more years a lot of methodological development and clinical application of joint models of longitudinal and time-to-event outcomes have come up. In these studies patients are followed until an event\, such as death occurs. In most of the articles\, using subject specific random effects as frailty\, the dependency of these two processes has been established. In this article\, we propose a new joint model that consists of a linear mixed effects submodel for longitudinal data and an accelerated failure model for the time-to-event data. These two submodels are linked together by not only latent random process\, but also by the conditional distributional assumption. This model will capture the dependency of the time-to-event on the longitudinal measurements more directly. Using standard priors\, a Bayesian method is developed for estimation. All computations based on the Bayesian inference via MCMC is implemented using OpenBugs. Our proposed method is evaluated by a simulation study which shows the efficiency of the conditional model over two other models: joint models with local independence and independent models. One clinically motivating data on Duchenne muscular dystrophy (DMD) syndrome and a popular data on AIDS are also analyzed.
URL:https://isrt.ac.bd/event/seminar-on-sunday-21-october-2018-at-2-pm/
CATEGORIES:seminar
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=UTC:20180717T140000
DTEND;TZID=UTC:20180717T150000
DTSTAMP:20180709T074018Z
CREATED:20180709T074018Z
LAST-MODIFIED:20180709T074018Z
UID:2670-1531836000-1531839600@isrt.ac.bd
SUMMARY:Seminar on Tuesday\, July 17 at 2 pm
DESCRIPTION:Title: Non-inferiority testing under generalized Poisson distribution\n\nVenue: ISRT seminar room \n\nSpeaker:  Md Abu Manju\, PhD\n                Department of Mathematics and Computer Science\n                Eindhoven University of Technology\, Eindhoven\, The Netherlands\n\n \nAbstract: In recent years\, non-inferiority studies for count data have been increasingly used in the evaluation of new test methods or new treatments (e.g.\, microbiological test methods\, particle counters or drugs\, vaccines) and the Poisson distribution is commonly assumed as it provides a standard framework for the analysis of count data. A generalization of the Poisson distribution\, referred to as the generalized Poisson distribution (GPD)\, which models not only overdispersion\, but also underdispersion\, may be more appropriate in certain applications\, including comparison of microbiological test methods. We therefore propose tests for the assessment of non-inferiority and sample size calculation procedures under GPD. Asymptotic likelihood ratio test (LRT)\, Wald and Exact conditional tests are derived\, and the type I error rate and statistical power are computed for these three tests based on simulations. In terms of type I error rate and statistical power\, LRT and Wald test perform similarly\, but the Exact test is conservative and has less type I error rate and power than the LRT and Wald test. Finally\, expressions are derived for calculating the sample sizes that yield sufficient power to test the non-inferiority of the new methods or treatments based on Wald test and LRT.
URL:https://isrt.ac.bd/event/seminar-on-tuesday-july-17-at-2-pm/
CATEGORIES:seminar
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=UTC:20180606T103000
DTEND;TZID=UTC:20180606T120000
DTSTAMP:20180604T112349Z
CREATED:20180604T112349Z
LAST-MODIFIED:20180604T112349Z
UID:2568-1528281000-1528286400@isrt.ac.bd
SUMMARY:Seminar on Wednesday\, June 6\, 2018 at 10:30 am
DESCRIPTION:Title of the Talk: Can We Train Machine Learning Methods to Outperform the High-dimensional Propensity Score Algorithm?\n\nSpeaker: Dr. M. Ehsan Karim\n\n               Assistant Professor\, SPPH\, UBC\n               Scientist & Biostatistician\, CHEOS\, Canada\n\nVenue: ISRT Seminar room\n\n—————————————Abstract-——————————————————————-\nThe use of retrospective health care claims datasets is frequently criticized for the lack of complete information on potential confounders. Utilizing patient’s health status–related information from claims datasets as surrogates or proxies for mismeasured and unobserved confounders\, the high-dimensional propensity score algorithm enables us to reduce bias. Using a previously published cohort study of postmyocardial infarction statin use (1998–2012)\, we compare the performance of the algorithm with a number of popular machine learning approaches for confounder selection in high-dimensional covariate spaces: random forest\, least absolute shrinkage and selection operator\, and elastic net. Our results suggest that\, when the data analysis is done with epidemiologic principles in mind\, machine learning methods perform as well as the high-dimensional propensity score algorithm. Using a plasmode framework that mimicked the empirical data\, we also showed that a hybrid of machine learning and high-dimensional propensity score algorithms generally perform slightly better than both in terms of mean squared error\, when a bias-based analysis is used. This talk is based on a joint work with Menglan Pang and Robert W Platt from McGill University [Epidemiology: 2018\,29(2):191–198].\n———————————————————————————————————————–
URL:https://isrt.ac.bd/event/seminar-on-wednesday-june-6-2018-at-1030-am/
CATEGORIES:seminar
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=UTC:20180515T140000
DTEND;TZID=UTC:20180515T153000
DTSTAMP:20180515T040605Z
CREATED:20180515T040605Z
LAST-MODIFIED:20180515T040605Z
UID:2548-1526392800-1526398200@isrt.ac.bd
SUMMARY:Seminar on Tuesday\, 15 May 2018 at 2pm
DESCRIPTION:Title: Modified Inferential Methods on Restricted Parameters in Multivariate Regression Analysis: Applications in Socio-demographic Research \nSpeaker: Sheikh Mohammad Sayem\n\n               PhD Researcher\, ISRT\n \nAbstract: Multivariate regression analysis is getting increasing attention among the socio-demographers due to the complex nature of the interdependence of the response variables. This PhD research is to carry out detailed study on restricted parameters of multivariate regression analysis with continuous\, discrete or mixed responses to seek out or develop efficient point estimation strategy and hence develop appropriate hypothesis testing procedure for hypothesis involving restricted parameters.This seminar will give a clear idea about the specific objectives of the PhD research and about the way how the objectives will be met in line of the existing literature. In this study\, a modified maximum likelihood estimation technique is primarily used for estimating restricted parameters of multivariate regression analysis with continuous responses. A Monte Carlo simulation is carried out to evaluate the performance of the estimators. The relative efficiency of the modified maximum likelihood estimator is found to be higher than the ordinary least square or maximum likelihood estimators.
URL:https://isrt.ac.bd/event/seminar-on-tuesday-15-may-2018-at-2pm/
CATEGORIES:seminar
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=UTC:20180508T140000
DTEND;TZID=UTC:20180508T150000
DTSTAMP:20180507T011847Z
CREATED:20180507T011827Z
LAST-MODIFIED:20180507T011847Z
UID:2530-1525788000-1525791600@isrt.ac.bd
SUMMARY:Seminar on Tuesday\, April 8 at 2 pm
DESCRIPTION:Title: Approximation of the Formal Bayesian Model Comparison using the Extended Conditional Predictive Ordinatecriterion\n\nSpeaker: Md. Rashedul Hoque\, Assistant Professor\, ISRT\n \nVenue and Time: ISRT seminar room\, 2 pm\n\nAbstract: The optimal method for Bayesian model comparison is the formal Bayes factor (BF)\, according to decision theory. The formal BF is computationally troublesome for more complex models. If predictive distributions under the competing models do not have a closed form\, a cross-validation idea\, called the conditional predictive ordinate (CPO) criterion can be used. In the cross-validation sense\, this is a ‘leave-out one’ approach. CPO can be calculated directly from the Monte Carlo (MC) outputs\, and the resulting Bayesian model comparison is called the pseudo-Bayes factor (PBF). We can get closer to the formal Bayesian model comparison by increasing the ‘leave-out size’\, and at ‘leave-out all’ we recover the formal BF. But\, the MC error increases with increasing ‘leave-out size’. In this study\, we examine this for linear and logistic regression models.\nOur study reveals that the Bayesian model comparison can favor a different model for PBFcompared to BF when comparing two close linear models. So\, larger ‘leave-out sizes’ are preferred which provide result close to the optimal BF. On the other hand\, MC samples based formal Bayesian model comparisons are computed with more MC error for increasing ‘leave-out sizes’; this is observed by comparing with the available closed-form results. Still\, considering a reasonable error\, we can use ‘leave-out size’ more than one instead of fixing it at one. These findings can be extended to logistic models where closed form solution is\nunavailable.
URL:https://isrt.ac.bd/event/seminar-on-tuesday-april-8-at-2-pm/
CATEGORIES:seminar
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=UTC:20180424T140000
DTEND;TZID=UTC:20180424T150000
DTSTAMP:20180424T115140Z
CREATED:20180422T010527Z
LAST-MODIFIED:20180424T115140Z
UID:2468-1524578400-1524582000@isrt.ac.bd
SUMMARY:Seminar on Tuesday 24 April\, 2018 at 2 PM
DESCRIPTION:Title: Ongoing Upgrading in RMG Enterprises: Preliminary Results from a Survey\n\n\nVenue and time: ISRT seminar room\, 2 PM\n\nSpeaker: Dr. Khondaker Golam Moazzem\n               Research Director\n               Centre For Policy Dialogue (CPD) \n               Bangladesh
URL:https://isrt.ac.bd/event/seminar-on-tuesday-24-april-2018-at-2-pm/
CATEGORIES:seminar
ATTACH;FMTTYPE=image/jpeg:https://isrt.ac.bd/wp-content/uploads/2018/04/talk_ap24_2018-1.jpg
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=UTC:20180419T080000
DTEND;TZID=UTC:20180504T170000
DTSTAMP:20180423T224937Z
CREATED:20180423T040434Z
LAST-MODIFIED:20180423T224937Z
UID:2474-1524124800-1525453200@isrt.ac.bd
SUMMARY:ISRT's Indoor Games for 2018 started on the 19th of April 2018
DESCRIPTION:The Indoor Games Tournament 2018 of ISRT started with an inauguration ceremony on Thursday\, 19th of April 2018. This year Batch 21 (the current 4th year) is organizing the event. Badminton\, table tennis\, ludo\, chess\, dart throwing\, indoor cricket are some of the many exciting games. Students\, teachers and staffs are taking part in different events. More information about the event including fixtures and rules of games can be found from the following link: \nhttps://sites.google.com/isrt.ac.bd/indoorgame2018/home
URL:https://isrt.ac.bd/event/isrts-indoor-games-for-2018-started-on-the-19th-of-april-2018/
CATEGORIES:seminar
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=UTC:20180417T140000
DTEND;TZID=UTC:20180417T153000
DTSTAMP:20180416T172613Z
CREATED:20180416T172613Z
LAST-MODIFIED:20180416T172613Z
UID:2455-1523973600-1523979000@isrt.ac.bd
SUMMARY:Seminar on Tuesday\, April 17 at 2 pm
DESCRIPTION:Title: Evolution of Reproductive Health in Bangladesh\n \nSpeaker: Dr. Halida Hanum Akhter \n               Faculty Member \n               Bloomberg School of Public Health \n               John Hopkins University\, Baltimore\, USA\n\nVenue: ISRT seminar room\n               \n\nAbstract: \nIn Bangladesh\, the government family planning program started in 1965 and at NGO level in around 1952. The government program was a vertical program with only IUD (intra uterine device) and high dose oral pills as a pilot program. With a demonstration project on post-partum tubal ligation in four urban clinics\, under the Family Planning Board\, the program was implemented in the whole country. In 1974\, MFSTC (Mohammadpur Fertility Services and Training Center) started as a special project of Ministry of Health and Family Planning\, Then around 1978 family planning and MCH was integrated and named MCH based family planning program. Subsequently in 1994\, ICPD (International  Conference on Population and Development) also named as Cairo conference where Reproductive health concept and definition was introduced\, vetted and cosigned by 198 countries of the world. All these countries were the cosignatory of this ‘program of action’ document and agreed to introduce reproductive health in the country program. Reproductive health is a rights based approach committing to address Life Cycle approach to women’s health issues.  Since 1994\, many international instruments\, such as ICPD POA\, ICPD +5\, ICPD +15 monitored programs nationally and globally. \nThe speaker talks about the accomplishment thus far and the unfinished agenda in reproductive health in Bangladesh.
URL:https://isrt.ac.bd/event/seminar-on-tuesday-april-17-at-2-pm/
CATEGORIES:seminar
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=UTC:20180410T140000
DTEND;TZID=UTC:20180410T153000
DTSTAMP:20180330T080110Z
CREATED:20180330T075816Z
LAST-MODIFIED:20180330T080110Z
UID:2413-1523368800-1523374200@isrt.ac.bd
SUMMARY:Seminar on Tuesday\, April 10\, 2018 at 2 pm
DESCRIPTION:Title: A model for repeated binary outcomes and comparison with quasi-likelihood based approaches\n\nSpeaker: Jahida Gulshan\n                Associate Professor\, ISRT
URL:https://isrt.ac.bd/event/seminar-on-tuesday-april-10-2018-at-2-pm/
CATEGORIES:seminar
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=UTC:20180403T140000
DTEND;TZID=UTC:20180403T150000
DTSTAMP:20180330T080220Z
CREATED:20180318T085610Z
LAST-MODIFIED:20180330T080220Z
UID:2399-1522764000-1522767600@isrt.ac.bd
SUMMARY:Seminar on Tuesday\, April 3 at 2 pm
DESCRIPTION:Title: The Bangladesh paradox: health gains despite poverty and income inequality  \n\n\n\n\n\nSpeaker:  Dr. Ahmed Mushtaque Raza Chowdhury \n\n                Vice Chairperson\, BRAC\n                 and\n                 Professor of Clinical Population and Family Health\n                 Joseph L. Mailman School of Public Health\n                 Columbia University\, USA
URL:https://isrt.ac.bd/event/seminar-on-tuesday-april-3-at-2-pm/
CATEGORIES:seminar
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=UTC:20180109T140000
DTEND;TZID=UTC:20180109T153000
DTSTAMP:20180106T163145Z
CREATED:20180106T163145Z
LAST-MODIFIED:20180106T163145Z
UID:2236-1515506400-1515511800@isrt.ac.bd
SUMMARY:Seminar on Tuesday\, January 9 at 2 pm
DESCRIPTION:Title: Panjer Recursion to evaluate total claim distribution recursively\n\n \nSpeaker: Dr. Abdul H. Sharif\n              Adjunct Professor\n              Mathematical Sciences Department\n              Central Connecticut State University\, USA. \n   \nAbstract: The usual method of evaluating the distribution function of the total claims incurred in a fixed period of time\, requires the computation of many convolutions of the conditional distribution of the amount of a claim given that a claim has occurred. When the expected number of claims is large\, the computation can become unwieldy even with modern large-scale electronic computers. In this presentation\, a recursive definition of the distribution of total claims is developed for a family of claim number distributions and arbitrary claim amount distributions. When the claim amount is discrete\, the recursive definition can be used to compute the distribution of total claims without the use of convolutions. This can reduce the number of required computations by several orders of magnitude for sufficiently large portfolios.\n\nFinally\, I will discuss some current research on total claim modeling. Assuming the diversified level of the audience\, the level of mathematics will be kept to probability generating function(PGF) and moment generating function (MGF).
URL:https://isrt.ac.bd/event/seminar-on-tuesday-january-9-at-2-pm/
CATEGORIES:seminar
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=UTC:20171219T140000
DTEND;TZID=UTC:20171219T150000
DTSTAMP:20171105T044817Z
CREATED:20171105T044808Z
LAST-MODIFIED:20171105T044817Z
UID:2051-1513692000-1513695600@isrt.ac.bd
SUMMARY:Seminar on Tuesday\, December 19 at 2 pm
DESCRIPTION:Title: Developing Public Speaking Skills in Statistical Communication\n \nSpeaker: Mohammed Shahidullah\, PhD\, MPH\n              State Demographer\n              Illinois Department of Public Health and\n              Adjunct Faculty\n              The University of Illinois\, Springfield\, USA\n    \n Abstract: Public speaking is the process or act of performing a speech to a live audience. The objective of public speaking is to inform\, persuade or to entertain the audience. It helps in skill building\, professional credibility\, networking and finding suitable jobs. As an applied statistician it is a challenge how we communicate with our audience including our students\, colleagues and consulting clients. My talk will concentrate on: Benefits of Public Speaking\, Steps in Successful Public Speaking and Resources Available to Improve Public Speaking. Toastmasters International club (www.toastmasters.org) is a great way to learn how to formulate\, express\, and sell your ideas and yourself with confidence. I will share with you my experience with this club and how it works. My recommendation will be to join such a club to improve your skills in public speaking and leadership. 
URL:https://isrt.ac.bd/event/seminar-on-tuesday-december-19-at-2-pm/
CATEGORIES:seminar
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=UTC:20171217T110000
DTEND;TZID=UTC:20171217T123000
DTSTAMP:20171206T021626Z
CREATED:20171206T021626Z
LAST-MODIFIED:20171206T021626Z
UID:2108-1513508400-1513513800@isrt.ac.bd
SUMMARY:Seminar on Sunday\, December 17 at 11 am
DESCRIPTION:Title: Testing equality of two normal means using combined samples of paired and unpaired data\n\nSpeaker: Professor Nizam Uddin \, Department of Statistics\, University of Central Florida\n \nAbstract: A test statistic for testing equality of two normal means when data consist of both paired and unpaired observations is proposed. The proposed test statistic is compared with two other standard methods known in the literature with respect to the type I error rate and power using simulation results.\n\nHe will also talk about the Big data analytics PhD program offered in the University of Central Florida. 
URL:https://isrt.ac.bd/event/seminar-on-sunday-december-17-at-11-am/
CATEGORIES:seminar
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=UTC:20171212T150000
DTEND;TZID=UTC:20171212T160000
DTSTAMP:20171210T095348Z
CREATED:20171210T095238Z
LAST-MODIFIED:20171210T095348Z
UID:2112-1513090800-1513094400@isrt.ac.bd
SUMMARY:Seminar on Tuesday\, December 12 at 3 pm
DESCRIPTION:Title: Statisticians in the Data Science Era\n\nSpeaker: Enayetur Raheem\, Data Scientist at Carolinas HealthCare System\, North Carolina\, USA\n\nAbstract: In this talk I will discuss what it really means to be a data scientist from a statistician’s perspective. In particular\, I will share my experience about the US job market for statisticians. This will give you some ideas about your future job prospects in the US and in Bangaldesh.
URL:https://isrt.ac.bd/event/seminar-on-tuesday-december-12-at-3-pm/
LOCATION:isrt seminar room
CATEGORIES:seminar
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=UTC:20171128T143000
DTEND;TZID=UTC:20171128T160000
DTSTAMP:20171128T035929Z
CREATED:20171127T092148Z
LAST-MODIFIED:20171128T035929Z
UID:2085-1511879400-1511884800@isrt.ac.bd
SUMMARY:Seminar on Tuesday\, November 28 at 2:30 pm
DESCRIPTION:Title: Business Intelligence and Data Science\n\nSpeaker: Business Intelligence team\, Grameenphone\n\nSummary: The main focus of the seminar will be- to shed some light on the current business trends\, and the challenges the industry faces in this 21st century\, and also to delineate the prospects of Business Intelligence and Data Science in Bangladesh. The sessions will be conducted by a team of 8-10 presenters/speakers from the Business Intelligence Department of Grameenphone.
URL:https://isrt.ac.bd/event/seminar-on-tuesday-december-28-at-230-pm/
CATEGORIES:seminar
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=UTC:20171119T110000
DTEND;TZID=UTC:20171119T130000
DTSTAMP:20171105T044943Z
CREATED:20171105T044554Z
LAST-MODIFIED:20171105T044943Z
UID:2049-1511089200-1511096400@isrt.ac.bd
SUMMARY:Seminar on Sunday\, November 19 at 11 am
DESCRIPTION:Title: Survival Ensembles and Representative Trees for Cancer Prognostication\n \nSpeaker: Mousumi Banerjee\, PhD\n              Research Professor of Biostatistics\n              School of Public Health & Comprehensive Cancer Center\,\n              Director of Biostatistics\n              Center for Healthcare Outcomes and Policy\n              The University of Michigan\, Ann Arbor\, USA.\n    \n Abstract: Tree-based methods have become popular for analyzing right censored survival data where the primary goal is the prognostic stratification of patients. Ensemble techniques such as random forest improve the accuracy in prediction and address the instability in a single tree by growing an ensemble of trees and aggregating. However\, individual trees are lost in the forest. This talk will first provide an overview of the methodological aspects of tree-based modeling in the censored data setting. Next\, we propose a methodology for identifying the most representative trees in a forest for survival data\, based on several tree distance metrics. For any two trees\, the metrics are chosen to (1) measure similarity of the covariates used to split the trees; (2) reflect similar clustering of patients in the terminal nodes of the trees; and (3) measure similarity in predictions from the two trees. While the latter focuses on prediction\, the first two metrics focus on the architectural similarity between two trees. The most representative trees in the forest are chosen based on the average distance between a tree and all other trees in the forest. Out of bag estimate of error rate is obtained using neighborhoods of representative trees. Simulations and data examples show gains in predictive accuracy when averaging over such neighborhoods. Although our focus is on trees for censored data\, the ideas are also applicable to classification and regression trees. We illustrate our methods using data from a thyroid cancer study.
URL:https://isrt.ac.bd/event/seminar-on-sunday-november-19-at-11-pm/
CATEGORIES:seminar
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=UTC:20171010T140000
DTEND;TZID=UTC:20171010T150000
DTSTAMP:20171009T161343Z
CREATED:20171002T165427Z
LAST-MODIFIED:20171009T161343Z
UID:1946-1507644000-1507647600@isrt.ac.bd
SUMMARY:Seminar on Tuesday\, October 10 at 2 pm
DESCRIPTION:Title: Conditional dependence in joint modelling of longitudinal non-Gaussian outcomes\n \nSpeaker: Mili Roy\, MSc\n              Research Assistant\n              Werklund School of Education\n              University of Calgary\, Canada \n   \nAbstract: The study is motivated by the limitations of conventional joint modelling strategies based\n\n\non linear and generalized linear mixed models (LMMs/GLMMs). The class of so-called Gaussian\ncopula mixed models (GCMMs)\, introduced by Wu and de Leon (2014) to generalize conventional\nLMMs/GLMMs to non-Gaussian settings\, was adopted\, and simulations were conducted to in-\nvestigate the impact of incorrectly ignoring the conditional dependence between outcomes\, given\nthe random effects\, on the performance of maximum likelihood estimates (MLEs). A variety of\nscenarios involving shared or correlated random effects were considered\, and implementation of\nthe correct and misspecied joint models was done in SAS’s PROC NLMIXED. Although MLEs of\nfixed effects were only slightly impacted by the conditional independence misspecication\, MLEs\nbased on the correct GCMM yielded generally better performances than those from the incorrect\nmodel. Data on pediatric pain (Weiss\, 2005; Withanage et al.\, 2015) were used for illustration.
URL:https://isrt.ac.bd/event/seminar-on-october-10-at-11-am/
CATEGORIES:seminar
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=UTC:20171004T100000
DTEND;TZID=UTC:20171004T113000
DTSTAMP:20170928T054536Z
CREATED:20170928T052103Z
LAST-MODIFIED:20170928T054536Z
UID:1924-1507111200-1507116600@isrt.ac.bd
SUMMARY:Seminar on Wednesday\, October 4 at 10 am
DESCRIPTION:Big Data: Opportunities to Explore \n\nPresenter: DataSoft Systems Bangladesh Limited
URL:https://isrt.ac.bd/event/seminar-on-wednesday-october-4-at10-am/
CATEGORIES:seminar
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=UTC:20170821T140000
DTEND;TZID=UTC:20170821T150000
DTSTAMP:20170819T193147Z
CREATED:20170801T083324Z
LAST-MODIFIED:20170819T193147Z
UID:660-1503324000-1503327600@isrt.ac.bd
SUMMARY:Seminar on Monday\, August 21\, 2017
DESCRIPTION:Title: Spectrum sharing in cellular networks: Optimisation and post-optimisation techniques\n \nSpeaker: Md Asaduzzaman\, PhD\n              Associate Professor\n              ISRT\, University of Dhaka \n \nAbstract: \n\nDynamic spectrum sharing aims to provide secondary access to under-utilized spectrum in cellular networks. The main aim of the talk is twofold. Firstly\, the secondary operator aims to borrow spectrum bandwidths under the assumption that more spectrum resources exist considering a merchant mode. Two optimization models are proposed using stochastic and optimization models in which the secondary operator (i) spends the minimal cost to achieve the target grade of service assuming unrestricted budget or (ii) gains the maximal profit to achieve the target grade of service assuming restricted budget. Results obtained from each model are then compared with results derived from algorithms in which spectrum borrowings are random. Comparisons showed that the gain in the results obtained from our proposed stochastic-optimization framework is significantly higher than heuristic counterparts. Secondly\, post-optimization performance analysis of the operators in the form of blocking probability in various scenarios is investigated to determine the probable performance gain and degradation of the secondary and primary operators respectively. We mathematically modelled the sharing agreement scenario and derive the closed form solution of blocking probabilities for each operator. Results showed how the secondary operator perform in terms of blocking probability under various offered loads and sharing capacity. 
URL:https://isrt.ac.bd/event/seminar-on-monday-august-22-2017/
LOCATION:isrt seminar room
CATEGORIES:seminar
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=UTC:20170807T140000
DTEND;TZID=UTC:20170807T150000
DTSTAMP:20170801T083409Z
CREATED:20170801T082912Z
LAST-MODIFIED:20170801T083409Z
UID:656-1502114400-1502118000@isrt.ac.bd
SUMMARY:Seminar on Monday\, August 7\, 2017
DESCRIPTION:Title: Energy Expenditure Prediction from Raw Accelerometer  Data: A Comparison between Linear and Nonlinear Models\n\nSpeaker: Dr. Munni Begum\n              Professor of Mathematical Sciences\n              Ball State University\, USA\n\nAbstract:\n\nThis study had three purposes\, all related to evaluating energy expenditure (EE) prediction accuracy from body-worn accelerometers: (1) compare linear regression to linear mixed models\, (2) compare linear models to artificial neural network models\, and (3) compare accuracy of accelerometers placed on the hip\, thigh\, and wrists. Forty individuals performed 13 activities in a 90 min semi-structured\, laboratory-based protocol. Participants wore accelerometers on the right hip\, right thigh\, and both wrists and a portable metabolic analyzer (EE criterion). Four EE prediction models were developed for each accelerometer: linear regression\, linear mixed\, and two ANN models. EE prediction accuracy was assessed using correlations\, root mean square error (RMSE)\, and bias and was compared across models and accelerometers using repeated-measures analysis of variance. For all accelerometer placements\, there were no significant differences for correlations or RMSE between linear regression and linear mixed models. For the thighworn accelerometer\, there were no differences in correlations or RMSE between linear and ANN models. Conversely\, one ANN had higher correlations and lower RMSE than both linear models for the hip and both ANNs had higher correlations and lower RMSE than both linear models for the wrist-worn accelerometers. For studies using wrist-worn accelerometers\, machine-learning models offer a significant improvement in EE prediction accuracy over linear models. Conversely\, linear models showed similar EE prediction accuracy to machine learning models for hip- and thigh-worn accelerometers and may be viable alternative modeling techniques for EE prediction for hip or thigh-worn accelerometers.
URL:https://isrt.ac.bd/event/seminar-on-monday-august-7-at-2-pm/
LOCATION:isrt seminar room
CATEGORIES:seminar
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=UTC:20170529T100000
DTEND;TZID=UTC:20170529T110000
DTSTAMP:20170807T124825Z
CREATED:20170807T124825Z
LAST-MODIFIED:20170807T124825Z
UID:856-1496052000-1496055600@isrt.ac.bd
SUMMARY:Seminar on Monday\, May 29\, 2017
DESCRIPTION:Construction of Ensembles by Exploiting the Richness of Feature Variables in High-Dimensional Data with Application in Protein Homology\n\n\nMay 23\, 2017 – 7:13pm \n\n\n\nFull Title:\nConstruction of Ensembles by Exploiting the Richness of Feature Variables in High-Dimensional Data with Application in Protein Homology\n\n\nSpeaker:\nDr. Jabed Tomal\n\n\n\nAssistant Professor\nDepartment of Computer and Mathematical Sciences\nThe University of Toronto Scarborough\, Canada.\n\n\nDate/Time:\nMonday\, May 29\, 2017\, 10 a.m.\n\n\nVenue:\nISRT seminar room\n\n\n\n  \n\nABSTRACT\nHigh-dimensional data may contain complementary subsets of useful feature variables which could bevaluable in predicting a response. In this work\, I have developed a predictionmodel which exploits the richness of information contained in the complementary subsets ofuseful feature variables in high-dimensional data. The proposed model – which is an aggregated collection of logistic regression models (LRM) – is called an ensemble\, where each constituent LRM is fitted to a subset of feature variables. An algorithm is developed to cluster the feature variables into subsets in a way that the variables in a subset are good to put together in an LRM\, and the variables in different subsets are good in separate LRMs. Each subset of variables is called a “phalanx”\, and the resulting ensemble is called an “ensemble of phalanxes (EPX).” The strength of the ensembledepends on the algorithm’s ability to identify/output strong and diverse subsets of feature variables.\nHomologous proteins are considered to havea common evolutionary origin\, i.e.\, the bearers of homologous proteins share a common ancestor. To develop an evolutionary sequence of proteins\, a scientist needs to predict their biological homogeneity. The proposed ensembleis applied to the protein homology data\, obtained from the 2004 KDD cup competition\,and used to predict biological homogeneity of proteins. In this application\, the feature variables are various scores representing structural similarity and amino acid sequence identity of proteins. Theunderlying assumption\, for model building\,is that the structural similarity and amino acid sequence identityare predictive to proteins’ biological homogeneity.As the proportion of homologous proteins is rare\, the prediction performances of theensemble are evaluated by checking its ability to rank rare homologous proteins ahead of the non-homologous proteins. While prediction performances of an EPX are competitive to contemporary state-of-the-art ensembles\, a big leap of improvement in prediction performances is achieved by aggregating two diverse EPXs obtained from optimizing two complementary evaluation metrics.Here\, the algorithm and complementary-metrics guaranteed increased strength and diversity\, respectively\, among the ensembles of phalanxes to aggregate. Importantly\, the performances of the two aggregated EPXs are robust against individual EPX when one EPX is good for detecting close homologs and the other is good for detecting distant homologs. Using parallel computing\, the proposed ensemble is shown computationally efficient as well.
URL:https://isrt.ac.bd/event/seminar-on-monday-may-29-2017/
CATEGORIES:seminar
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=UTC:20170517T140000
DTEND;TZID=UTC:20170517T150000
DTSTAMP:20170814T034940Z
CREATED:20170807T125348Z
LAST-MODIFIED:20170814T034940Z
UID:859-1495029600-1495033200@isrt.ac.bd
SUMMARY:Seminar on Wednesday\, May 17\, 2017
DESCRIPTION:Assessment of predictors selected for epidemiologic risk models using automated variable selection methods\n\n\n\nMay 17\, 2017 – 12:57pm \n\n\n\nFull Title:\nAssessment of predictors selected for epidemiologic risk models using automated variable selection methods\n\n\nSpeaker:\nDr. Haider Mannan\n\n\n\nWestern Sydney University\, Australia\n\n\nDate/Time:\nWednesday\, May 17\, 2017\, 2 p.m.\n\n\nVenue:\nISRT Seminar Room\n\n\n\n  \n\nABSTRACT\nTBA
URL:https://isrt.ac.bd/event/seminar-on-wednesday-may-17-2017-2-p-m/
CATEGORIES:seminar
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=UTC:20170509T140000
DTEND;TZID=UTC:20170509T153000
DTSTAMP:20170814T035014Z
CREATED:20170807T125545Z
LAST-MODIFIED:20170814T035014Z
UID:861-1494338400-1494343800@isrt.ac.bd
SUMMARY:Seminar on Tuesday\, May 9\, 2017
DESCRIPTION:A Tutorial of Creating R Packages under Microsoft Windows\n\n\n\nApril 23\, 2017 – 11:02am \n\n\n\nFull Title:\nA Tutorial of Creating R Packages under Microsoft Windows\n\n\nSpeaker:\nDr. Md. Hasinur Rahman Khan\n\n\n\nAssociate Professor\, ISRT\n\n\nDate/Time:\nTuesday\, May 9\, 2017\, 14.00-15.30\n\n\nVenue:\nISRT Seminar Room\n\n\n\n  \n\nABSTRACT\nCreating an R package is my hobby- a very few number of R programmers or practitioners over the world might claim this but most of them would like to love to document their R code and disseminate their research which is possible only by creating R package because creating R package forces to document own code and provide test examples to ensure that it actually works. This also becomes an ideal way of making sure others have access to own work. This talk is a tutorial of how to create an R package under Windows environment. At the end of the talk\, a demonstration with my latest R package called DNAseqtest would be presented as the guideline of gaining confidence for the potential R package builders
URL:https://isrt.ac.bd/event/seminar-on-tuesday-may-9-2017-14-00-15-30/
CATEGORIES:seminar
END:VEVENT
END:VCALENDAR