Search or add a thesis

Advanced Search (Beta)
Home > Optimum Sample Size and Methods of Estimation for Multilevel Modeling

Optimum Sample Size and Methods of Estimation for Multilevel Modeling

Thesis Info

Access Option

External Link

Author

Iftikhar Ud Din

Program

PhD

Institute

University of Agriculture

City

Faisalabad

Province

Punjab

Country

Pakistan

Thesis Completing Year

2019

Thesis Completion Status

Completed

Subject

Statistics

Language

English

Link

http://prr.hec.gov.pk/jspui/bitstream/123456789/10622/1/Iftikhar_Ud_Din_Statistics.pdf

Added

2021-02-17 19:49:13

Modified

2024-03-24 20:25:49

ARI ID

1676724892359

Asian Research Index Whatsapp Chanel
Asian Research Index Whatsapp Chanel

Join our Whatsapp Channel to get regular updates.

Similar


An important problem in Multilevel Modeling (MLM) is to find sufficient sample size for accurate estimation purposes. In MLM apart from the general factors of sample size estimation i.e. the test size, the effect size, SE (standard error) of the effect size and power of the test, additional factors like, magnitude of the ICC (Intra Class Correlation), total number of clusters, the number of parameters to be estimated, and the information whether the design is balanced or unbalanced may play a significant role. In this study, the significance of these factors in the context of MLMs is evaluated and their mutual relationship is explored through simulation study. It is found that little problem will arise in estimation of sample size for fitting multi-level model if standardized effect size δ is 0.2 or lower and intra-class correlation ρ is also low (0.05 or less), here substantial power (0.80) can be achieved when J (Number of clusters) is 50 or more. A small upward shift in the ρ (0.1), causes alarming increase in the total number of clusters to be sampled. Secondly, it is observed that the number of clusters to be sampled is playing a greater role in power enhancement as compared to cluster size. Thirdly, significant changes in the power of estimation are observed when the effect size δ increases from 0.2 to 0.4. Fourthly, the level II covariate (with R2= 0.3, 0.6) if added in the model in the model it can significantly increase power of the multilevel models even in the presence of small number of clusters. Two methods of estimation commonly used for multilevel modeling, IGLS (Iterative Generalized Least Square Method) and MCMC (Monte Carlo Markov Chain) are compared with variety of models using limited and extended simulations. The study reveals that the MCMC estimates for the fixed effect is superior to its counterpart IGLS on all the three grounds i.e. unbiasedness, efficiency, and the proportion of the true value captured by the confidence interval/credible interval. As far as estimation of the random effect is concerned, MCMC is better on the proportion of the true value covered, however, IGLS gain considerable lead on the unbiased and efficiency criterion. Further, it is observed that MCMC respond more positively to the extended simulations as compared to IGLS.
Loading...
Loading...

Similar Books

Loading...

Similar Chapters

Loading...

Similar News

Loading...

Similar Articles

Loading...

Similar Article Headings

Loading...

حسن فانی اے

حسن فانی اے
بہتے ناز کریندیئے کڑیئے ناں کر اتنا شور
سسی وی سی ناز کریندی، رُل موئی بھنبھور
کڑیئے فانی حسن تے ناں ہوئیے ایڈا مغرور
جد وی جوبن ٹٹنا تینوں ہونا دکھ ضرور
کسے ناں تینوں پچھنا بھاویں دنیا دی توں حور
جو بنیا اوس ٹٹنا ایتھے ہونا ہور دا ہور
ہیر سیال نے رانجھے دے نال عشق نبھایا اے
مجھیں باراں سال چرائیاں ، نالے چاک اکھوایا اے
عشق چ اوڑک جوگی بنیا، بوہتا دکھ اٹھایا اے
قیدو نے تاں مڑ وی نہیں سی چھڈیا اوہدا کھور
سوہنی ایتھے عشق دی ڈاہڈی لاج نبھائی اے
دلبر تے جند واری، ناں ای اکھ پرتائی اے
اس دنیا دے کچے گھڑے نے جان گنوائی اے
گوتے کھاندی رہ گئی ، نہ کوئی چلیا اوہدا زور
قادریؔ سائیں عشق ماہی وچ ہوئے ڈاہڈے خوار
دلبر باہجھ نہ دل نوں کدھرے آوے چین قرار
سوہنا سانول جے کر مینوں جھلک دیوے ہک وار
موہنجھ منجھاری ، کرماں ہاری منگساں نہ کجھ ہور

Status of Abandoned Children: A Comparative Study of Islamic and Pakistani Law

This paper deals with the rights of abandoned children in the context of Pakistani society. The main issue is regarding legal status of such children which results in violation of their rights. Islamic law provides for rules for abandoned children which can be provided as a source for legislation in Pakistan. The paper argues that there is a need to formulate a clear legislation to ensure rights and protection of abandoned children. Currently the laws enacted in Pakistan lack provisions related to abandoned children. On the one hand the solutions like adoption/kafalah should be channelized and regularized and on the other hand serious efforts should be made to create awareness regarding rights of abandoned children among the masses. This is a comparative study which discusses and analyses relevant provisions in Islamic as well as Pakistani law.

Antimicrobial Resistance and Genotyping of Extended Spectrum Beta-Lactamase Producing Clinical Isolates

The development of resistance mechanism in Gram-Negative bacteria is growing all over the world affecting developing countries the most. Extended Spectrum Beta-lactamase (ESBLs) production is one of the widespread mechanisms of resistance associated with irrational or excessive use of extended spectrum cephalosporins. The ground objective of this study was to investigate the prescribing pattern of broad spectrum antibiotics in hospital setup and the prevalence of ESBL production in Gram-Negative clinical isolates collected from an outpatient source by both phenotypic and genotypic detection. The study also focused on the treatment options available to treat resistant clinical isolates of Escherichia coli, Klebsiella pneumoniae, Pseudomonas aeruginosa and Proteus mirabilis. Total 685 in-patient data were collected over a period of three months for the prescribing patterns of extended spectrum antibiotics used alone or in combination. The data were analyzed for the utilization of extended spectrum antibiotics in various wards either empiric or prophylactic use of broad spectrum cephalosporins. For the prevalence of ESBL production, 1005 clinical isolates of E. coli, K. pneumoniae, P. aeruginosa and P. mirabilis were collected from an out-patient source. Antimicrobial susceptibility and resistance patterns were determined by Kirby-Bauer disc diffusion method under the recommended guidelines of Clinical Laboratory Standard Institute (CLSI). Phenotypic detection of ESBL was performed on 352 clinical isolates using the double disc synergy test between amoxicillin/clavulanic acid (10μg) and ceftazidime or cefotaxime (30μg) disc. Multidrug resistance among ESBL positive isolates was also determined. Pearson’s or Fisher’s exact Chi-square test was used to analyze statistical association between ESBLs and Non ESBLs at 0.05 level of significance. Furthermore, polymerase chain reaction was used for the identification of TEM, SHV and CTX-M gene in ESBL positive clinical isolates. The prescribing pattern in hospital setup revealed that 75% of the overall antibiotics were prescribed for prophylactic treatments, whereas, among all prescribed antibiotics the frequency of broad spectrum cephalosporins alone or in combination was found to be the highest. Out of 1005 gram-negative clinical isolates, prevalence was found to be E. coli 680 (67.66 %), K. pneumoniae 248 (24.67%), P. mirabilis 3 (0.3 %) and P. aeruginosa XIII 74 (7.36%). Out of 352 clinical isolates, 96 (27.27%) were ESBL positive, female preponderance was found in 62 (67%), whereas 32 (33%) were males. E. coli was the most prevalent ESBL producers 79 (82%), followed by K. pneumoniae 16 (17%) and P. mirabilis 1 (1%). The urinary tract infections were the most commonly recovered infections i.e., 72 (75%), and among them 63 and 9 were E. coli and K. pneumoniae respectively. Age groups of 16-30 and 46-60 years were most affected with ESBL producing uropathogenic E. coli with a high prevalence in females. A high rate of resistance was observed against broad spectrum cephalosporins, fluoroquinolones, amoxicillin/clavulanic acid, sulfamethoxazole/trimethoprim and ampicillin. Whereas, amikacin, imipenem, tazobactam/piperacillin and fosfomycin were found effective antibiotic choices. The rate of multidrug-resistance was found to be 95%, 62.5% and 100% in ESBL producing E. coli, K. pneumoniae and P. mirabilis respectively. Statistical evaluation between ESBLs and Non ESBLs revealed significant association in E. coli (p 0.0004) and K. pneumoniae (p 0.032). Genotype identification revealed the presence of TEM, SHV and CTX-M genes in 82.14% (69/84) of the isolates. CTX-M was the most prevalent gene found in 59.5% (50/84) of the isolates, followed by TEM 41.6% (35/84) and SHV 13% (11/84). CTX-M was dominant among uropathogenic E. coli related to community acquired urinary tract infections. The study concluded an increased prevalence rate of ESBLs in E. coli, most of them recovered from urinary tract infections. The study also found an increased rate of multidrug-resistance among Gram-Negative clinical isolates. These incidences can be reduced by the restricted use of broad spectrum cephalosporins. The spread of ESBL producing uropathogenic E. coli can be controlled by implementing ESBL screening along with limiting the use of empiric therapy. Nevertheless, hygienic practices must be employed to reduce the incidence of community onset urinary tract infections.