Prevalence ; Proportional Hazards Models ; Regression Analysis

OBJECTIVE: To realize batch processing of univariate Cox regression analysis for great database by SAS marco program. METHODS: We wrote a SAS macro program, which can filter, integrate, and export P values to Excel by SAS9.2. The program was used for screening survival correlated RNA molecules of ovarian cancer. RESULTS: A SAS marco program could finish the batch processing of univariate Cox regression analysis, the selection and export of the results. CONCLUSION The SAS macro program has potential applications in reducing the workload of statistical analysis and providing a basis for batch processing of univariate Cox regression analysis.
Proportional Hazards Models ; Regression Analysis ; Software

Distortion product otoacoustic emission (DPOAE) signal can be used for diagnosis of hearing loss so that it has an important clinical value. Continuously using sweeping primaries to measure DPOAE provides an efficient tool to record DPOAE data rapidly when DPOAE is measured in a large frequency range. In this paper, locally weighted least squares estimation (LWLSE) of 2f1-f2 DPOAE is presented based on least-squares-fit (LSF) algorithm, in which DPOAE is evoked by continuously sweeping tones. In our study, we used a weighted error function as the loss function and the weighting matrixes in the local sense to obtain a smaller estimated variance. Firstly, ordinary least squares estimation of the DPOAE parameters was obtained. Then the error vectors were grouped and the different local weighting matrixes were calculated in each group. And finally, the parameters of the DPOAE signal were estimated based on least squares estimation principle using the local weighting matrixes. The simulation results showed that the estimate variance and fluctuation errors were reduced, so the method estimates DPOAE and stimuli more accurately and stably, which facilitates extraction of clearer DPOAE fine structure.
Algorithms ; Hearing Loss ; diagnosis ; Humans ; Least-Squares Analysis ; Otoacoustic Emissions, Spontaneous ; Regression Analysis

Detecting plant health conditions plays a key role in farm pest management and crop protection. In this study, measurement of hyperspectral leaf reflectance in rice crop (Oryzasativa L.) was conducted on groups of healthy and infected leaves by the fungus Bipolaris oryzae (Helminthosporium oryzae Breda. de Hann) through the wavelength range from 350 to 2,500 nm. The percentage of leaf surface lesions was estimated and defined as the disease severity. Statistical methods like multiple stepwise regression, principal component analysis and partial least-square regression were utilized to calculate and estimate the disease severity of rice brown spot at the leaf level. Our results revealed that multiple stepwise linear regressions could efficiently estimate disease severity with three wavebands in seven steps. The root mean square errors (RMSEs) for training (n=210) and testing (n=53) dataset were 6.5% and 5.8%, respectively. Principal component analysis showed that the first principal component could explain approximately 80% of the variance of the original hyperspectral reflectance. The regression model with the first two principal components predicted a disease severity with RMSEs of 16.3% and 13.9% for the training and testing dataset, respectively. Partial least-square regression with seven extracted factors could most effectively predict disease severity compared with other statistical methods with RMSEs of 4.1% and 2.0% for the training and testing dataset, respectively. Our research demonstrates that it is feasible to estimate the disease severity of rice brown spot using hyperspectral reflectance data at the leaf level.
Data Interpretation, Statistical ; Least-Squares Analysis ; Oryza ; classification ; microbiology ; Plant Diseases ; classification ; microbiology ; Plant Leaves ; classification ; microbiology ; Principal Component Analysis ; Regression Analysis ; Severity of Illness Index ; Spectrum Analysis ; methods

This study involved direct observation of the differences in prevalence of disease and utilization of medical care by smokers, non-smokers, and ex-smokers. The data was collected from the 1989 Korean National Health Survey (1989 KNHS). A total of 5,201 individuals ages 20 to 59 were randomly selected from the whole Korean population using the three-stage stratified random sampling. Based on the logistic regression, the following results were obtained. Compared with the non-smokers, the relative risks for an acute disease were 1.9 and 1.7 for male ex-smokers and female current smokers, respectively. Smoking behavior significantly increased utilization of health services such as admissions (RR = 2.5 for current smokers) among females, outpatient visits (RR = 2.1 for ex-smokers, RR = 2.3 for age began to smoke was less than 18 years) among males and (RR = 1.5 for current smokers) among females. Furthermore, the utilization of outpatient services for ex-smokers who were self-concerned about their health was 3.4 times higher than the non-smokers. Based on the weighted least square regression model the days of medication for male current smokers and ex-smokers were significantly longer than non-smokers. These effects persisted after controlling for major identified confounding factors. Thus, the results of this study confirmed that smoking is an important cause of diseases and a major contributing factor to the use of health services.
Adult ; Female ; Health Services/*utilization ; Human ; Korea/epidemiology ; Least-Squares Analysis ; Male ; Middle Age ; Prevalence ; Regression Analysis ; Smoking/*adverse effects/epidemiology

Nondestructive method of measuring soluble solids content (SSC) of citrus fruits was developed using Fourier transform near infrared reflectance (FT-NIR) measurements collected through optics fiber. The models describing the relationship between SSC and the NIR spectra of citrus fruits were developed and evaluated. Different spectra correction algorithms (standard normal variate (SNV), multiplicative signal correction (MSC)) were used in this study. The relationship between laboratory SSC and FT-NIR spectra of citrus fruits was analyzed via principle component regression (PCR) and partial least squares (PLS) regression method. Models based on the different spectral ranges were compared in this research. The first derivative and second derivative were applied to all spectra to reduce the effects of sample size, light scattering, instrument noise, etc. Different baseline correction methods were applied to improve the spectral data quality. Among them the second derivative method after baseline correction produced best noise removing capability and yielded optimal calibration models. A total of 170 NIR spectra were acquired; 135 NIR spectra were used to develop the calibration model; the remaining spectra were used to validate the model. The developed PLS model describing the relationship between SSC and NIR reflectance spectra could predict SSC of 35 samples with correlation coefficient of 0.995 and RMSEP of 0.79 degrees Brix.
Biochemistry ; methods ; Calibration ; Citrus ; metabolism ; Least-Squares Analysis ; Light ; Models, Statistical ; Regression Analysis ; Reproducibility of Results ; Scattering, Radiation ; Spectroscopy, Fourier Transform Infrared ; methods ; Spectroscopy, Near-Infrared

No abstract available.
Regression Analysis*

The purposes of this study were to a) measure the service quality attributes of foodservice type such as school foodservice, hospital foodservice and business & industry(B&I) foodservice, managed by contract management company(CMC), b) compare with service quality attributes by CMC scale, c) analyze overall customer satisfaction(CS) by the foodservice type and the CMC scale, and d) identify the effect of service quality attributes on an overall CS by the foodservice type and the CMC scale. The questionnaires were handed out to 6,620 customers of 207 school, 38 hospital, and 86 B&I foodservices in 108 CMCs. The statistical data analysis was completed using SPSS Win(ver 12.0) for descriptive analysis, t-test, reliability analysis, and multiple linear regression analysis. From an analysis on service quality attributes, 'proper arrangement of table and chair at hall distribution(3.53)', 'operation of nutrition education(3.50)' were highly perceived to student, 'correctable serving(4.08)', 'serve at fixed distribution time(4.08)', 'kindness of serving employee(4.04)' were highly perceived to patient, 'employee's kindness(3.84)' were highly perceived to customer of B&I. In comparison of service quality attributes by CMC scale, most scores of large enterprise(LE) were significantly higher than small and medium sized enterprise(SME) in school foodservice, hospital foodservice and B&I foodservice. Overall CS levels were 3.53 out of a maximum 5 on B&I, 3.46 on school, and 3.44 on hospital and were evaluated differently CS score by CMC scale. Finally, regression results for the effects of service quality attributes on overall CS by each of foodservice type were identified significantly different service quality attributes by foodservice type such as school, hospital, B&I(p<.001) and by CMC scale. For considering the goal of enterprise on profit-making through CS and the needs of customer on CS at moment of truth(MOT), the findings should be applied to the CMC and the foodservice industry.
Commerce ; Data Interpretation, Statistical ; Hand ; Humans ; Linear Models ; Surveys and Questionnaires ; Regression Analysis

Adequate organ growth is an important aspect of growth evaluation in children. Renal size is an important indicator of adequate renal growth; computed tomography (CT) can closely estimate actual kidney size. However, insufficient data are available on normal renal size as measured by CT. This study aimed to evaluate the relationships of anthropometric indices with renal length and volume measured by CT in Korean pediatric patients. Renal length and volume were measured using CT images in 272 pediatric patients (age < 18 years) without renal disease. Data for anthropometric indices—including height, weight, and body surface area (BSA)—were obtained using medical records. Using the equation for an ellipsoid, renal volume was calculated in cubic centimeters. Height showed greatest correlation with renal length on stepwise multiple linear regression analysis; BSA showed the strongest significant correlation with renal volume. The mean renal size for each age group and height group was determined; it showed a tendency to increase with age and height. This is the first Korean study to report the relationship between body indices and renal size measured by CT. These results can serve as normative standards for assessing adequate renal growth.
Body Surface Area ; Child* ; Humans ; Kidney ; Linear Models ; Medical Records ; Regression Analysis

BACKGROUND AND OBJECTIVES: According to the correlation between hearing injury and McBride disability rating presented by previous studies, there are over/underestimated cases particularly in the 40 dB hearing range compared to other ranges. In this study, we reviewed the overestimated and underestimated data and propose a complementation scheme for a disability rating system by using the linear regression analysis. SUBJECTS AND METHOD: For the past 14 years, we have provided legal advisory for 121 cases of hearing injury, for which disability had to be rated. We reviewed all but excluded 11 cases for the aggravation of disability. A regression equation was produced from a linear regression analysis that used the percent of hearing handicap (AAO-HNS/AMA-1979 formula) as an independent variable (x) and McBride disability rating (%) as a dependent variable (y), following the Pearson correlation test. Iterative calculation was performed for overestimated (18) and underestimated (8) cases. RESULTS: Appropriate disability ratings were 14% for the cases overestimated to 20% and 11% for those underestimated to 5%. Appropriate disability ratings for the 20% of overestimated cases were changed to 14%, and for the 5% of the underestimated cases, the disability ratinb 11%. Iterative calculation showed that the Pearson correlation index was improved from 0.8866 to 0.9065 and the determination coefficient of regression analysis (adjusted R-square) was improved from 0.784 to 0.8202. CONCLUSION: The common range of hearing injury, which falls between 30-40 dB corresponds to the percentage of hearing handicap of 7.5-22.5%. A fairer assessment of ability rating would be possible by complementing some parts of this hearing range.
Complement System Proteins* ; Disability Evaluation ; Hearing Loss ; Hearing* ; Jurisprudence ; Linear Models* ; Regression Analysis*