• Journal of Veterinary Clinics
• /
• v.27 no.1
• /
• pp.71-78
• /
• 2010

Analysis of variance (ANOVA) is a method to analyze the data from the experimental designs comparing two or more groups or treatments at the same time, and is the most effective tool of analyzing more complex data sets with different source of variations. This article describes the logic of ANOVA, the application of the method to the analysis of a simple data set, and the methods available for performing planned or post hoc multiple comparisons between the treatments means. In addition, the common misuse of the techniques is also discussed to emphasize that an inappropriate statistical analysis is potentially far more harmful than poorly conducted research. Lastly, an example is given for illustration purposes.

• The Journal of Dong Guk Oriental Medicine
• /
• v.2 no.1
• /
• pp.55-71
• /
• 1993

In order to investigate the effect of Cervus elaphus aqua-acupuncture on the hypogonadism in male rats, hydrocortisone acetate was adminsterd per mouse to induce hypogonadism and a series of Cervus elaphus aqua-acupuncture and normal saline aqua-acupuncture treatments were done into the loci corresponding to Shinsu($BL_{23}$) for 10 days. The level of urinary 17-ketosteroids. serum FSH, prolactin, LH, testosterone and body weight were measured. The obtained results are summarized as follows. 1. The level of urinary 17-ketosteroids was increased by Cervus elaphus aqua-acupuncture with the statistical significance as compared with the control group. 2. The level of serum FSH was increased by Cervus elaphus aqua-acupuncture with the statistical significance as compared with the control group. 3. The level of serum prolactin was increased by Cervus elaphus aqua-acupuncture with the statistical significance as compared with the control group. 4. The level of serum LH was increased by Cervus elaphus aqua-acupuncture with the statistical significance as compared with the control group. 5. The level of serum testosterone was decreased by Cervus elaphus aqua-acupuncture with the statistical significance as compared with the control group. 6. Body weight change was increased by 3rd, 6th and 9th day after the Cervus elaphus aqua-acupuncture and 3rd,6th day after normal saline aqua-acupuncture with the statistical significance as compared with the control group.

• Journal of Hospice and Palliative Care
• /
• v.13 no.1
• /
• pp.1-6
• /
• 2010

The purpose of clinical trials is to find evidences for the effects of experimental new drugs or treatments on human. For the successful clinical trials, it is not sufficient to use statistics only for the analyses of collected data, but it is necessary to extend the usage of statistics in various ways. At the beginning of the study, one needs to use statistics for systematically and concretly planning the study. For this, we discussed the usage of statistics in defining the effect, determining the sample size, statistical analyses, and so on.

• Communications for Statistical Applications and Methods
• /
• v.15 no.1
• /
• pp.13-26
• /
• 2008

Inference on the present data will be more reliable when the data arising from previous similar studies are available. The data arising from previous studies are referred as historical data. The power prior is defined by the likelihood function based on the historical data to the power $a_0$, where $0\;{\le}\;a_0\;{\le}\;1$. The power prior is a useful informative prior for Bayesian inference such as model selection and model comparison. We utilize the historical data to perform multiple comparison in the one-way ANOVA model. We demonstrate our results with some simulated datasets under a simple order restriction between the treatments.

• The Korean Journal of Applied Statistics
• /
• v.17 no.3
• /
• pp.419-430
• /
• 2004

Since cDNA microarray experiments can monitor expression levels for thousands of genes simultaneously, the experimental designs and their analyzing methods are very important for successful analysis of microarray data. The loop design is discussed for selecting differentially expressed genes among several treatments and the analysis of variance method is introduced to normalize microarray data and provide estimates of the interesting quantities. MA-ANOVA is used to illustrate this method on a recently collected loop designed microarray data at Cancer Metastasis Research Center, Yonsei University.

• Communications for Statistical Applications and Methods
• /
• v.19 no.5
• /
• pp.721-729
• /
• 2012

Various methods control the influence of a covariate on a response variable. These methods are analysis of covariance(ANCOVA), RANK ANCOVA, ANOVA of (covariate-adjusted) residuals, and Kruskal-Wallis tests on residuals. Covariate-adjusted residuals are obtained from the overall regression line fit to the entire data set that ignore the treatment levels or factors. It is demonstrated that the methods on covariate-adjusted residuals are only appropriate when the regression lines are parallel and covariate means are equal for all treatments. In this paper, we proposed the new nonparametric method on the ANCOVA model, as applying joint placement in a one-way layout on residuals as described in Chung and Kim (2007). A Monte Carlo simulation study is adapted to compare the power of the proposed procedure with those of the previous procedure.

• Journal of Korean Society of Occupational and Environmental Hygiene
• /
• v.3 no.1
• /
• pp.54-61
• /
• 1993

Principles and advantages of neutron actiation analysis which is one of widely using nuclear techniques are introduced. The importance of neutron activation analysis in occupational health study is discussed. The indusrial hygienic study of the samples like human hair, blood, urine, organs, tissues and airborne contamination of the working environment can be enhanced by the technique. Statistical treatments of the acquired data are also emphasized.

• Journal of the military operations research society of Korea
• /
• v.13 no.1
• /
• pp.45-64
• /
• 1987

Power algorithms for analysis of variance tests are presented. In experimental design of operational tests and evaluations the selection of design parameters so as to attain an experiment with desired power is a difficult and important problem. An interactive computer program is presented which uses the power algorithms for ANOVA tests and creates graphical presentations which can be used to assist decision makers in statistical design. ANOVA tests and associated parameters (such as sample size, types and levels of treatments, and alpha-level)are examined.

• Journal of Acupuncture Research
• /
• v.33 no.2
• /
• pp.61-76
• /
• 2016

Objectives : This study was designed to clarify population-social characteristics that influence the utilization patterns of hospitalized patients in a traditional korean hospital, thereby providing clinical data which would help further improvements of traditional korean medical service in particular the Acupuncture and Moxibustion. Methods : We investigated population-social characteristics and annual utilization patterns of all patients who were hospitalized for more than 24 hours in a Korean Medical Hospital from January 2005 to December 2014. The obtained data were recorded in the EMR chart and statistical analysis was performed using SPSS 21.0. Additionally, data from the patients admitted to the department of Acupuncture and Moxibustion were analyzed separately. Results : 1. All inpatients had a significant annual difference in age, gender, hospitalized department, and disease code annually but not in re-hospitalization number. Inpatients of the department of Acupuncture and Moxibustion also varied in their age, gender, and disease code annually, but not in re-hospitalization number. 2. Pearson correlation analysis on all inpatients showed that the mean days of hospital treatments had a negative correlation with all variables except medical care insurance. Total cost, cost per day per person and recuperation cost had a positive correlation with all variables except medical care insurance. There was no meaningful relationship between nonrecuperation cost and the variables. 3. Stepwise multiple regression analysis on all inpatients showed that the mean days of hospital treatments had a negative correlation with all variables except automobile insurance. The total hospitalization costs had a positive correlation with both general insurance and medical care insurance. Cost per day per person and recuperation cost had a positive correlation with the females. There was no meaningful relationship between non-recuperation cost and the variables. 4. Pearson correlation analysis on inpatients of the department of Acupuncture and Moxibustion inpatients showed that the mean days of hospital treatments had a positive correlation with all variables except general insurance and automobile insurance. Total cost and recuperation cost had a positive correlation with all variables except medical care insurance, and cost per day per person had a positive correlation with females and general insurance. There was no meaningful relationship between non-recuperation cost and the variables. 5. Stepwise multiple regression analysis on inpatients of the department of Acupuncture and Moxibustion inpatients, the mean days of hospital treatments, total cost, cost per day per person and recuperation cost had a positive correlation with general insurance. There was no meaningful relationship between non-recuperation cost and the variables. Conclusion : Population-social characteristics of inpatients annually varies, and the change influences the utilization pattern.

• The Korean Journal of Applied Statistics
• /
• v.24 no.5
• /
• pp.847-859
• /
• 2011

cDNA microarray-based comparative genomic hybridization(CGH) data includes low-intensity spots and thus a statistical strategy is needed to detect subtle differences between different cancer classes. In this study, genes displaying a high frequency of alteration in one of the different classes were selected among the pre-selected genes that show relatively large variations between genes compared to total variations. Utilizing copy-number changes of the selected genes, this study suggests a statistical approach to predict patients' classes with increased performance by pre-classifying patients with similar genetic alteration scores. Two-stage logistic regression model(TLRM) was suggested to pre-classify homogeneous patients and predict patients' classes for cancer prediction; a decision tree(DT) was combined with logistic regression on the set of informative genes. TLRM was constructed in cDNA microarray-based CGH data from the Cancer Metastasis Research Center(CMRC) at Yonsei University; it predicted the patients' clinical diagnoses with perfect matches (except for one patient among the high-risk and low-risk classified patients where the performance of predictions is critical due to the high sensitivity and specificity requirements for clinical treatments. Accuracy validated by leave-one-out cross-validation(LOOCV) was 83.3% while other classification methods of CART and DT performed as comparisons showed worse performances than TLRM.