| 1. |
- Alam, Moudud
(författare)
-
An efficient algorithm for the pseudo likelihood estimation of the generalized linear mixed models (GLMM) with correlated random effects
- 2009
-
Rapport (övrigt vetenskapligt/konstnärligt)abstract
- This paper presents a two-step pseudo likelihood estimation technique for generalized linear mixed models with correlated random effects. The proposed estimation technique does not require reparametarisation of the model. Multivariate Taylor's approximation has been used to approximate the intractable integrals in the likelihood function of the GLMM. Based on the analytical expression for the estimator of the covariance matrix of the random effects, a condition has been presented as to when such a covariance matrix can be estimated through the estimates of the random effects. An application of the model with a binary response variable has been presented using a real data set on credit defaults from two Swedish banks. Due to the use of two-step estimation technique, proposed algorithm outperforms the conventional pseudo likelihood algorithms in terms of computational time.
|
|
| 2. |
- Alam, Moudud
(författare)
-
An efficient estimation of the GLMM with correlated random effects
- 2008
-
Ingår i: COMPSTAT'2008: International Conference on Computational Statistics. - Porto-Portugal.
-
Konferensbidrag (övrigt vetenskapligt/konstnärligt)abstract
- This paper presents a two-step pseudo likelihood estimation technique for the generalized linear mixed models (GLMM) with random effects being correlated (possibly between subjects). Due to the use of the two-step estimation technique the proposed algorithm outperforms the conventional pseudo likelihood algorithms, e.g. Wolfinger and O’Connell (1993), in terms of computational time. Moreover, it does not require any reparametarisation of the model such as Lindstrom and Bates (1989). Multivariate Taylor’s approximation has been used to approximate the intractable integrals in the likelihood function of the GLMM. Based on the analytical expression for the estimator of the covariance matrix of the random effects, a condition has been presented as to when such a covariance matrix can be estimated through the estimates of the random effects. An application of the estimation technique with a binary response variable is presented using a real data set on credit defaults.
|
|
| 3. |
- Alam, Moudud, 1976-, et al.
(författare)
-
Fitting conditional and simultaneous autoregressive spatial models in hglm
- 2015
-
Ingår i: The R Journal. - 2073-4859. ; 7:2, s. 5-18
-
Tidskriftsartikel (refereegranskat)abstract
- We present a new version (> 2.0) of the hglm package for fitting hierarchical generalized linear models (HGLMs) with spatially correlated random effects. CAR() and SAR() families for conditional and simultaneous autoregressive random effects were implemented. Eigen decomposition of the matrix describing the spatial structure (e.g., the neighborhood matrix) was used to transform the CAR/SAR random effects into an independent, but eteroscedastic, Gaussian random effect. A linear predictor is fitted for the random effect variance to estimate the parameters in the CAR and SAR models. This gives a computationally efficient algorithm for moderately sized problems.
|
|
| 4. |
- Alam, Moudud, et al.
(författare)
-
Fitting spatial models in the R package: hglm
- 2014
-
Rapport (övrigt vetenskapligt/konstnärligt)abstract
- We present a new version of the hglm package for fittinghierarchical generalized linear models (HGLM) with spatially correlated random effects. A CAR family for conditional autoregressive random effects was implemented. Eigen decomposition of the matrix describing the spatial structure (e.g. the neighborhood matrix) was used to transform the CAR random effectsinto an independent, but heteroscedastic, gaussian random effect. A linear predictor is fitted for the random effect variance to estimate the parameters in the CAR model.This gives a computationally efficient algorithm for moderately sized problems (e.g. n<5000).
|
|
| 5. |
- Alam, Moudud, et al.
(författare)
-
Har kommunala sommarjobb under gymnasieåren en positiv effekt på arbetskarriären senare i livet?
- 2013
-
Rapport (övrigt vetenskapligt/konstnärligt)abstract
- Att erbjuda sommarjobb till ungdomar ses i många länder som ett sätt att förbättra ungdomars möjligheter att komma in och etablera sig på arbetsmarknaden. I Sverige erbjuder de flesta kommuner, delvis finansierat med statliga medel, sommarjobb till ungdomar. Den forskning som finns kring effekten av sommarjobb för ungdomar pekar dock i olika riktningar och lider ofta av metodproblem. Vi undersöker här med bättre metodologiska förutsättningar om kommunala sommarjobb för gymnasieungdomar i Falu kommun har någon positiv effekt på den postgymnasiala inkomstutvecklingen. Vi följer 2 650 ungdomar som, under första året i gymnasiet, ansökte om kommunalt sommarjobb. Vi följer dem tills de når en ålder av som mest 29 år. De kommunala sommarjobben fördelades genom ett lotteriförfarande där alla som ansökte hade lika stor chans att bli tilldelad ett sommarjobb. Vi finner ingen programeffekt för män. För kvinnor upptäcker vi en positiv effekt och då speciellt för kvinnor med låga betyg från grundskolan.
|
|
| 6. |
- Alam, Moudud, et al.
(författare)
-
High-School Students´ Summer Jobs and their Ensuing Labor Market Achievement : the Long Term Effect
- 2013
-
Rapport (övrigt vetenskapligt/konstnärligt)abstract
- In part because of high and persistent youth unemployment, adolescent students’ transition from school to work is an important policy and research topic. Many countries have implemented public programs offering summer jobs or work while in high-school as measures to smooth the transition. While the immediate effect of the programs on school attendance, school grades, and disposable income is well documented, their effect on the transition to the labor market remains an open question. Observational studies have shown strong positive effects of summer jobs, but also that the estimated effect is highly vulnerable to selection bias. In this paper, some 3700 high-school students applying for summer jobs in the period 1995-2003,via a program, are followed to 30 years of age. A quarter of the applicants were randomly offered a summer job each year. Among the remaining students, 50% had a (non-program related) summer job while in high-school. We find the income, post high-school, for the offered and non-offered groups to be similar and conclude that the effect of summer jobs on the transition to the labor market is inconsequential.
|
|
| 7. |
|
|
| 8. |
- Alam, Moudud
(författare)
-
Industry shocks and empirical evidences on defaults comovement
- 2009
-
Rapport (övrigt vetenskapligt/konstnärligt)abstract
- It is commonly agreed that the credit defaults are correlated. However, the mechanism of such dependence is not yet fully understood. This paper contributes to the current understanding about the defaults comovement in the following way. Assuming that the industries provides the basis of defaults comovement it provides empirical evidence as to how such comovements can be modeled using correlated industry shocks. Generalized linear mixed model (GLMM) with correlated random effects is used to model the defaults comovement. Empirical evidences are drawn through analyzing individual borrower level credit history data obtained from two major Swedish banks between the period 1994-2000. The results show that the defaults are correlated both within and between industries but not over time (quarters). A discussion has also been presented as to how a GLMM for defaults correlation can be explained.
|
|
| 9. |
- Alam, Moudud, et al.
(författare)
-
Likelihood estimate of treatment effects under selection bias
- 2012
-
Rapport (övrigt vetenskapligt/konstnärligt)abstract
- We consider methods for estimating causal effects of treatment in the situation where the individuals in the treatment and the control group are self selected, i.e., the selection mechanism is not randomized. In this case, simple comparison of treated and control outcomes will not generally yield valid estimates of casual effects. The propensity score method is frequently used for the evaluation of treatment effect. However, this method is based onsome strong assumptions, which are not directly testable. In this paper, we present an alternative modeling approachto draw causal inference by using share random-effect model and the computational algorithm to draw likelihood based inference with such a model. With small numerical studies and a real data analysis, we show that our approach gives not only more efficient estimates but it is also less sensitive to model misspecifications, which we consider, than the existing methods.
|
|
| 10. |
- Alam, Moudud, et al.
(författare)
-
Likelihood estimate of treatment effects under selection bias
- 2013
-
Ingår i: Statistics and its Interface. - 1938-7989 .- 1938-7997. ; 6:3, s. 349-359
-
Tidskriftsartikel (refereegranskat)abstract
- We consider methods for estimating the causal effects of treatment in the situation where the individuals in the treatment and the control group are self selected, i.e., the selection mechanism is not randomized. In this case, a simple comparison of treated and control outcomes will not generally yield valid estimates of casual effect. The propensity score method is frequently used for the evaluation of treatment effect. However, this method is based on some strong assumptions, which are not directly testable. In this paper, we present an alternative modelling approach to draw causal inferences by using a shared random-effect model and the computational algorithm to draw likelihood based inference with such a model. With small numerical studies and a real data analysis, we show that our approach gives not only more efficient estimates but also is less sensitive to model misspecifications, which we consider, than existing methods.
|
|
