Early-onset scoliosis (EOS) can have negative effects on the developing thorax, lungs, and quality of life in general. Children with EOS can face various health problems and require recurring hospitalization and surgeries. Radiographic parameters are insufficient to evaluate the severity and efficacy of treatment in EOS. Early-onset Scoliosis Questionnaire (EOSQ)-24 questionnaire is a new instrument developed for this specific age group. To date, reliability of this questionnaire has not yet been interrogated in wide patient groups from different cultures. The aim of this study was to evaluate the validity and reliability of culturally adapted Turkish version of the EOSQ-24.Forward translation and back translation of the English version of the EOSQ-24 was done, and all steps for cross-cultural adaptation process were performed properly by an expert committee. Turkish version of the EOSQ-24 and Child Health Questionnaire-Parent Form-50 (CHQ-PF-50) were applied to 61 (24 male, 37 female) EOS patients. The average age of these patients was 9.1 ± 3.1 years (0.4 to 14.3 y), and 50 of them had undergone surgical treatment. Data quality was assessed by mean, median, percentage of missing data, and extent of ceiling and floor effects. Reliability was assessed by internal consistency using Cronbach's α and item-total correlations. The construct validity was evaluated by comparing the results of the EOSQ-24 with the Turkish version of the CHQ-PF-50. Subgroup analyses were applied for sex, diagnosis, treated/untreated, mobilization ability, and complications.The item response to the EOSQ-24 was high with a small number of missing answers (1.6% to 3.3%). Of the 24 items, 22 were evenly distributed. This resulted in a floor effect in 0% to 21.7% of patients, and a ceiling effect in 1.6% to 68.3%. The calculated Cronbach's α for the 24-item scale was 0.909, indicating excellent reliability. Construct validity showed that high correlations between the EOSQ and the CHQ by means of similar domains. Correlation coefficient was between 0.348 and 0.688 (P=0.0001). Subgroup analyses also showed significant difference in treated/untreated patients (P=0.032) and mobilization ability (P=0.001).The Turkish adaptation of the EOSQ-24 exhibits favorable psychometric properties and excellent reliability, validating its use in this population.
Bu calismada kategorik veri analizinde onemli yeri olan hiyerarsik log-linear analiz yontemi incelenmistir. Genel bilgiler bolumunde iki ve uc boyutlu tablolar icin bagimsizlik modelleri ve bunlarin odds oranlari ile iliskileri uzerinde durulmustur. Parametreler, carpimsal modeller icin geometrik ortalama yardimiyla yorumlanmistir. Model seciminde ileriye ve geriye donuk secim yontemleri ile birlikte w, R2, 8 ve AIC gibi kriterlerden de yararlanilmistir. Bulgular ve tartisma bolumunde cinsiyet, lokalizasyon, atopi ve nikel degiskenleri arasindaki iliski yapisi uc ayri log-linear analiz yapilarak incelenmistir. Ilk olarak cinsiyet ve nikel degiskenleri arasindaki iliskiyi bulmak amaciyla iki boyutlu tablolar icin log-linear analiz yontemi kullanilmis ve sonuclar odds orani ile yorumlanmistir. Lokalizasyon, nikel, atopi ve cinsiyet, lokalizasyon, nikel degiskenleri arasindaki iliskiler ise uc boyutlu tablolar icin log-linear analiz yontemiyle incelenmistir. AbstractIn this study, hierarchical log-liner analysis which has an important role in categorical data analysis is examined. In general knowledge section, independent models and their relations between odds ratios are explained. Parameters are explained by using geometric mean for product models. In model selection, forward and backward selection methods are used together with w, R2, 8, and AIC criteria. In findings and discussions section, relation structure between sex, localization, atopy and nickel is examined by using three different log-linear analysis. First of all, in order to find relation between sex and nickel variables, log- linear analysis method for two-dimensional contingency table is used and results are interpreted by odds ratio. Relations between localization, nickel, atopy and localization, nickel, sex variables are examined by using two different log-linear analysis methods for three-dimensional contingency tables.
Bu calismanin amaci, ikili yanit degiskenleri icin cok merkezli klinik denemelerin incelenmesi ve arastirmacilara analiz yontemleri konusunda onsel bir bilgi saglamaktir.Cok Merkezli Klinik Denemeler, klinik bir denemenin, ayni anda birden cok klinikte yurutulmesine verilen isimdir. Cok merkezli klinik denemeler, 1940’larda ve 1950’lerde Brandford Hill’in klasik kontrollu coklu klinik denemeleri tasarlamasindan bu yana giderek populerligini arttirmis ve gunumuzde yaygin olarak kullanilmaya baslanmistir.Calismanin ilk bolumunde, ikili yanit degiskeni icin cok merkezli klinik denemelerin tasarlanmasi, orneklem buyuklugunun hesaplanmasi, merkezlerin belirlenmesi gibi bilgiler verilmistir. Denemelerde kullanilan analiz yontemleri olan Sabit Etkili Model, Rastgele Etkili Model ve Mantel-Haenszel Yaklasimi tanitilmistir. Bunun yaninda, yontemlerin zayif yonleri hakkinda da bilgi verilmistir. Ikinci bolumde ise SAS programi kullanilarak, tanitilan yontemlerin uygulamasi yapilmistir.Sizofreni hastalari uzerine yapilmis olan calismanin verileri kullanilarak, her uc analiz yonteminden elde edilen sonuclar incelenmis ve yorumlanmistir. Sonuc olarak, tedavi yontemleri arasinda istatistiksel olarak anlamli bir farkin olmadigi gorulmustur.AbstractThe purpose of this study was to investigate of multi-centre clinical trials for binary response and provide a priori information for investigators.Multi-centre clinical trials is the name of a clinical trial which is conducted at multiple clinics. Multi-centre clinical trials increased their populariyt from 1940’s and 1950’s with design of classical controlled clinical trials by Brandford Hill and today, they have wide spread using.In the first part of this study, information about desing, sapmle size calculation, determination of centers etc. for multi-centre clinical trials for binary response had given. Fixed effect model, random effect model an Mantel-Heanszel approach which are analysis methods used in trials had introduced. As well as, informations have given about weak side of the methods. In the second part of the study, applied of methods which are introducedbefore using SAS software.Results from all of the three analysis methods which are obtained from data set of the study about schizophrenia patients, investigated and interpreted.
The main purpose in all experimental designs is to take into account the factors that are considered likely to have an effect on the response variable emphasized, and to minimize the error of experiment in this way.Bread, which is the staple human food, cannot have any negative effect on human beings as long as it is produced by using suitable materials under appropriate conditions.However, when inappropriate amounts of raw materials are used (e.g.non-optimal amounts of bran, yeast or other additives), bread threatens health.In this study, Box-BehnkenDesign (BBD) and Central Composite Design (CCD), the two different designs of the response surface method, were applied to a single dataset.Two designs were evaluated in terms of the results obtained.The purpose in the second-order factorial experiments is to identify the optimum levels of independent variables for the dependent variable.In this study, the implementation of second-order response surface model and interpretation of the results were based on 2 k CCD (Central Composite Design) and BBD (Box-Behnken Design) with one replicate.In the CCD, the amount of bran added, flour type, the ratio of yeast added, furnace temperature, the duration of remaining in the furnace, and fermentation time were accepted to be significant factors that affected volume yield.In addition, R 2 = 80.7% shows that the regression equation explains variables by 80.7%.In the BBD, the ratio of bran added, the type of flour, the ratio of yeast added, furnace temperature (only in quadratic form), the duration of remaining in the furnace (only in quadratic form), and fermentation time (only in quadratic form) were accepted to be significant factors that affected volume yield.Furthermore, R 2 = 89.64%shows that the regression equation explains variables by %89.64.This method provides savings in terms of time and the amount of material by limiting the area at particular levels.Researcher may use the results of either CCD or BBD (whichever s/he deems suitable) according to the volume s/he wants to obtain.
Amaç: Kovaryans analizi (ANCOVA), bir çalışmada etkisi incelenen faktör dışında bağımlı değişken ile ilişkisi bulunan sürekli bir veya birden fazla değişkenin etkisinin istatistiksel olarak kontrol edilmesini sağlayan bir yöntemdir. Bu çalışmada randomize olan araştırmalarda ortak değişken ile sonuç değişkeni arasında korelasyon bulunan modellerde ortak değişkenin etkisinin göz ardı edildiği varyans analizi (ANOVA) ile ortak değişken etkisinin arıtıldığı ANCOVA'nın korelasyon düzeyine bağlı olarak gücünün değişimi karşılaştırılmıştır. Gereç ve Yöntemler: Araştırmamızda Cohen'in küçük, orta ve büyük f etki büyüklüklerine bağlı 3 farklı senaryo kullanılarak n=30, 50 ve 100 örneklem büyüklükleri için benzetim çalışması yapılmıştır. Her bir benzetimde bağımlı değişken ile ortak değişken arasında 0'dan 1'e kadar 0,1 birimlik artış ile 11 farklı korelasyon bulunacak şekilde veri seti üretilerek her senaryoda 5000 benzetim yapılmıştır. Benzetim uygulamaları için R paket programı kullanılmıştır. R paketinde veri üretmek için 'MBESS' ve güç hesaplamaları için 'pwr' açık kaynak kodlu kütüphaneler kullanılmıştır. Bulgular: Küçük ve orta etki büyüklüklerine sahip benzetim sonuçlarında sonuç değişkeni ile ortak değişken arasında 0,20 korelasyon bulunduğunda ANOVA ile ANCOVA arasındaki güç değerinin ayrışmaya başladığı ve korelasyon değeri 0,50 ve sonrasında ANCOVA'nın ANOVA'ya göre çok daha fazla güce ulaştığı görülmüştür. Sonuç: Ortak değişken ile sonuç değişkeni arasında 0,2 ve üzeri korelasyon bulunduğunda ANOVA yerine ANCOVA kullanılarak daha az sayıda örneklem büyüklüğü ile araştırmada yeterli güce ulaşılacaktır.
The aim of this study was to evaluate the additional diagnostic value of "inversion recovery" single-shot fast-spin echo (IR-SSFSE) sequence using the inversion time at the null point for hepatic hemangiomas as a supplement to standard T2-weighted (T2W) magnetic resonance imaging for the distinction of hemangiomas and cysts.A total of 228 lesions in 56 patients were evaluated in this retrospective study. In addition to routine hepatic magnetic resonance imaging, IR-SSFSE imaging using inversion time value of 600 milliseconds (null point for hepatic hemangiomas) was obtained. Two radiologists independently reviewed T2W images at first and T2W images plus IR-SSFSE sequence 4 weeks afterward and used a 5-point scale to indicate the possibility of detected hyperintense lesion is a cyst or a hemangioma. A receiver operating characteristic analysis and κ statistics were used to evaluate the diagnostic additive value of IR-SSFSE sequence for differentiation of hepatic hemangiomas and cysts, and to determine interobserver agreement, respectively.Among 228 lesions, diameters of which ranges from 2 to 125 mm (mean, 13.84 ± 16.24 mm), 56.14% of them (n = 128) were hemangiomas, and 43.86% of them were cysts (n = 100). In the receiver operating characteristic analysis for the differentiation of hepatic hemangiomas from cysts, the calculated area under the curve (AUC) for standard T2W images alone was 0.889 (95% confidence interval [CI], 0.825-0.953) for the first observer and 0.913 (95% CI, 0.861-0.965) for the second observer. When IR-SSFSE sequence was combined to T2W images, AUC was calculated as 0.958 (95% CI, 0.920-0.996) for the first observer and 0.980 (95% CI, 0.956-1.0) for the second observer. The AUC values obtained from standard T2W images and standard T2W plus IR-SSFSE images were significantly different for both observers (P < 0.01). Both observers demonstrate better performance in differentiating hemangiomas and cysts with a combination of IR-SSFSE sequence and T2W imaging than with T2W imaging alone. Adding IR-SSFSE sequence as a supplement to standard T2W images improved the sensitivity and the κ values.Inversion recovery single-shot fast-spin echo sequence using the inversion time to null signal from the hepatic hemangiomas as a supplement to standard T2W images is useful for distinguishing hemangiomas from hepatic cysts without the need for intravenous gadolinium chelate administration.
The use of joint models that are capable of handling different data types is becoming increasingly popular in biopharmaceutical practice. Evaluation of various statistical techniques that have been developed for mixed data in simulated environments requires joint generation of multiple variables. In this article, we propose a unified framework for concurrently simulating ordinal and normal data given the marginal characteristics and correlation structure. We illustrate our technique in two simulation settings where we use artificial data as well as real depression score data from psychiatric research, demonstrating negligibly small deviations between the specified and empirically computed quantities.
'/%3e%3cuse xlink:href='%23a' transform='rotate(60)'/%3e%3ccircle r='17' fill='%23000095'/%3e%3ccircle r='15' fill='%23fff'/%3e%3c/svg%3e)