• Journal of Preventive Medicine and Public Health
• /
• v.40 no.6
• /
• pp.495-504
• /
• 2007

Objectives : This study attempts to show how studies using non-experimental data can strengthen causal inferences by applying propensity score and instrumental variable methods based on the counterfactual framework. For illustrative purposes, we examine the effect of having private health insurance on the probability of experiencing at least one hospital admission in the previous year. Methods : Using data from the 4th wave of the Korea Labor and Income Panel Study, we compared the results obtained using propensity score and instrumental variable methods with those from conventional logistic and linear regression models, respectively. Results : While conventional multiple regression analyses fail to identify the effect, the results estimated using propensity score and instrumental variable methods suggest that having private health insurance has positive and statistically significant effects on hospital admission. Conclusions : This study demonstrates that propensity score and instrumental variable methods provide potentially useful alternatives to conventional regression approaches in making causal inferences using non-experimental data.

• Journal of Microbiology
• /
• v.45 no.1
• /
• pp.58-63
• /
• 2007

In this study, the relative synonymous codon and amino acid usage biases of the broad-host range phage, KVP40, were investigated in an attempt to understand the structure and function of its proteins/protein-coding genes, as well as the role of its tRNAs. Synonymous codons in KVP40 were determined to be AT-rich at the third codon positions, and their variations are dictated principally by both mutational bias and translational selection. Further analysis revealed that the RSCU of KVP40 is distinct from that of its Vibrio hosts, V. cholerae and V. parahaemolyticus. Interestingly, the expression of the putative highly expressed genes of KVP40 appear to be preferentially influenced by the abundant host tRNA species, whereas the tRNAs expressed by KVP40 may be required for the efficient synthesis of all its proteins in a diverse array of hosts. The data generated in this study also revealed that KVP40 proteins are rich in low molecular weight amino acid residues, and that these variations are influenced primarily by hydropathy, mean molecular weight, aromaticity, and cysteine content.

• Survey Research
• /
• v.5 no.1
• /
• pp.93-101
• /
• 2004

In business survey, cut-off sampling is usual, The contribution from cut-off part of the population is at least small in comparison with the remaining population. In this case, part of the target population is excluded from the selection and parameter estimations are only based on Take-all and Take-some stratum. It may be tempting not to use resources on enterprises that contribute little to the overall results of the survey. And this reduces the response burden for these small enterprises. But, the size of cut-off stratum has been increased as a way to manage reduced budgets. This leads to additional bias. In this study, the population have been separated as three stratum, cut -off, take-some, take-all, and we will estimate cut-off part using auxiliary variable.

• The korean journal of orthodontics
• /
• v.48 no.3
• /
• pp.200-211
• /
• 2018

The aim of this systematic review was to evaluate the effectiveness and complications of corticotomy and piezocision in canine retraction. Five electronic databases (PubMed, SCOPUS, Web of Science, Embase, and CENTRAL) were searched for articles published up to July 2017. The databases were searched for randomized control trials (RCTs), with a split-mouth design, using either corticotomy or piezocision. The primary outcome reported for canine retraction was either the amount of tooth movement, rate of tooth movement, or treatment time. The secondary outcome was complications. The selection process was based on the PRISMA guidelines. A risk of bias assessment was also performed. Our search retrieved 530 abstracts. However, only five RCTs were finally included. Corticotomy showed a more significant (i.e., 2 to 4 times faster) increase in the rate of tooth movement than did the conventional method. For piezocision, both accumulative tooth movement and rate of tooth movement were twice faster than those of the conventional method. Corticotomy (with a flap design avoiding marginal bone incision) or flapless piezocision procedures were not detrimental to periodontal health. Nevertheless, piezocision resulted in higher levels of patient satisfaction. The main limitation of this study was the limited number of primary research publications on both techniques. For canine retraction into the immediate premolar extraction site, the rate of canine movement after piezocision was almost comparable to that of corticotomy with only buccal flap elevation.

• The Journal of Asian Finance, Economics and Business
• /
• v.7 no.10
• /
• pp.663-673
• /
• 2020

To enhance the performance of privatized firms and state-owned enterprises, Vietnamese government set up a specialized monitoring body named State Capital Investment Corporation (SCIC) in 2006 to supervise their performance. This motivated us to conduct this study to investigate the effective control of SCIC on privatized firms' performance. We collected the annual reports of 500 non-financial privatized firms listed on HSX and HNX during the period from 2007 to 2017 from Thomson Reuters. Observations with missing values were removed and trimming outliers were implemented resulting in a dataset comprising of 4146 firm-year observations. We applied a quadratic regression model of state ownership on firms' performance, and applied the method of Baron and Kenny (1986) to test the moderating effect of SCIC control. To fix "selection bias" that may occur and result in endogeneity of moderator (M), we utilized the PSM technique to analyze the marginal effect of the moderator (SCIC) on privatized firms' performance. Our findings indicate a positive moderating role of SCIC on the relationship between the state ownership and firms' performance. This implies that there is a positive effect of liberating the management of the private firms from government control, which also means that lesser the intervention of government in the day to day operational activities of a private firm, better the performance of a privatized firm is.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.8 no.1
• /
• pp.196-212
• /
• 2014

Facial expression recognition is an important part in emotional interaction between human and machine. This paper proposes a facial expression recognition approach based on multi-classifier fusion with stacking algorithm. The kappa-error diagram is employed in base-level classifiers selection, which gains insights about which individual classifier has the better recognition performance and how diverse among them to help improve the recognition accuracy rate by fusing the complementary functions. In order to avoid the influence of the chance factor caused by guessing in algorithm evaluation and get more reliable awareness of algorithm performance, kappa and informedness besides accuracy are utilized as measure criteria in the comparison experiments. To verify the effectiveness of our approach, two public databases are used in the experiments. The experiment results show that compared with individual classifier and two other typical ensemble methods, our proposed stacked ensemble system does recognize facial expression more accurately with less standard deviation. It overcomes the individual classifier's bias and achieves more reliable recognition results.

• Journal of Information Processing Systems
• /
• v.10 no.2
• /
• pp.314-333
• /
• 2014

When analyzing default predictions in real estate companies, the number of non-defaulted cases always greatly exceeds the defaulted ones, which creates the two-class imbalance problem. This lowers the ability of prediction models to distinguish the default sample. In order to avoid this sample selection bias and to improve the prediction model, this paper applies a minority sample generation approach to create new minority samples. The logistic regression, support vector machine (SVM) classification, and neural network (NN) classification use an imbalanced dataset. They were used as benchmarks with a single prediction model that used a balanced dataset corrected by the minority samples generation approach. Instead of using prediction-oriented tests and the overall accuracy, the true positive rate (TPR), the true negative rate (TNR), G-mean, and F-score are used to measure the performance of default prediction models for imbalanced dataset. In this paper, we describe an empirical experiment that used a sampling of 14 default and 315 non-default listed real estate companies in China and report that most results using single prediction models with a balanced dataset generated better results than an imbalanced dataset.

• The Mathematical Education
• /
• v.57 no.4
• /
• pp.413-431
• /
• 2018

In this study, I developed an activity oriented lesson to support the understanding of probabilistic and quantitative estimating population ratios according to the standard statistical principles and discussed its implications in didactical respects. The developed activity lesson, as an efficient physical simulation activity by sampling with replacement, simulates unknown populations and real problem situations through completely closed 'Closed Box' in which we can not see nor take out the inside balls, and provides teaching and learning devices which highlight the representativeness of sample ratios and the sampling variability. I applied this activity lesson to the gifted students who did not learn estimating population ratios and collected the research data such as the activity sheets and recording and transcribing data of students' presenting, and analyzed them by Qualitative Content Analysis. As a result of an application, this activity lesson was effective in recognizing and reflecting on the representativeness of sample ratios and recognizing the random sampling variability. On the other hand, in order to show the sampling variability clearer, I discussed appropriately increasing the total number of the inside balls put in 'Closed Box' and the active involvement of the teachers to make students pay attention to controlling possible selection bias in sampling processes.

• Journal of Information Science Theory and Practice
• /
• v.7 no.2
• /
• pp.23-31
• /
• 2019

We report results of selection-bias-free approaches to the analysis of the impact of open access (OA) models on citation metrics. We studied reference groups of Gold and Green OA articles and the group of non-OA (Paywall) articles with the new functionality of the Web of Science Core Collection database, the InCites platform of Clarivate Analytics, and the Dimensions database of Digital Science. For each reference group we obtained the values of the percent of cited articles and citation impact and their dependence on the depth of the citation period. Different research fields were analyzed in two schemas of the InCites platform. We report the higher values and growth rates of the citation metrics: citation impact and %Cited, in the OA reference groups over the Paywall group. The Green OA articles demonstrate the highest values of citation metrics among all the OA models. Dependence of the value of citation impact on citation period follows linear law with R2 values close to 0.9-1.0. The overall annual growth rates of citation impact of the Green OA, Gold OA, and the Paywall articles, k equal, respectively, 3.6, 2.4, and 1.4 in Dimensions and 4.6, 3.6, and 2.3 in the Web of Science Core Collection. We suppose that earlier results reported for the articles in pure OA journals vs. articles in Paywall journals were affected by the high citation impact of the Green and Hybrid OA articles that could not be elucidated in the Paywall journals at that time.

• The Journal of Internal Korean Medicine
• /
• v.42 no.3
• /
• pp.259-278
• /
• 2021

Objectives: This study examines the effect of Sagunja-tang on functional dyspepsia (FD) through a systematic review and meta-analysis of a randomized controlled trial (RCT). Methods: A search for RCTs that tested the effect of Sagunja-tang on functional dyspepsia was conducted in Medline, Embase, PubMed, CENTRAL, CiNii, CNKI, NDSL, RISS, OASIS, and KISS databases on November 8, 2020, with no limit on the year of publication. A meta-analysis was performed by synthesizing the findings, including total efficiency, clinical symptom score, myosin light-chain kinase (MLCK) level (pg/mL, and gastric half-emptying time (min). RevMan 5.4.1 software was used for data analysis. The quality of the literature was evaluated using Cochrane's risk of bias (RoB) tool. Results: A total of 14 RCTs met the selection criteria. As a result of the meta-analysis, the treatment group had higher total efficacy and MLCK levels (gastric antrum, jejunum) than the control group, and the clinical symptom score and gastric half-emptying time were lower. However, due to the low quality of the included RCT and the small sample size, the results may be slightly biased.