Browsing by Author "Özdemir, T."

Now showing 1 - 3 of 3

Calculation of Power in Chi-Square and Likelihood Ratio Chi-Square Statistics by a Special Sas Macro
(2006) Özdemir, T.; Keskin, S.; Çak, B.
The goal of this study was relatively analyzed as to power in Chi-Square and Likelihood Ratio ChiSquare Statistics by using SAS special macro which is presented in Appendix. For the aim, data sets regarding questionnaire responses of 107 refugees were utilized. Contrary to other data sets (had power values with high-level), sample size for only data set 3 having power values with low-moderate level for both statistics were artificially increased from backward to forward and optimum samples sizes for Ch-Square and other were determined as 280 and 170, respectively. As a result, it was concluded that power of Chi-Square and Likelihood Ratio Chi-Square Statistics changed to some factors: the size of sample and combinations of all cells' frequencies of contingency table. Besides, it is possible that researchers can determine sample size which is suitable for each data set by means of special SAS macro in appendix. Moreover, ones should not forget that power concept in any statistic technique means reliability. © 2006 Asian Network for Scientific Information.
Comparison of Some Raspberry Cultivars' Herbal Features by Repeated Random Complete Design Statistic Technique
(Asian Network for Scientific Information, 2007) Eyduran, S.P.; Aǧaoǧlu, Y.S.; Eyduran, E.; Özdemir, T.
The aim of this study was comparatively to examine herbal traits of the cultivars such as Rubin, Summit, Holland Dwarf, Heritage, Tulameen, Aksu Red, Nuburg, Canby and Willamette red raspberries cultivated at Ankara Condition, in the capital of Turkey between 2002 and 2005. According to Repeated Random Complete Design (RRCD) (which was composed of four random plot design experiments) used in the experiment, the effects of cultivar, year and cultivar by year interaction on herbal traits such as the height of shoot, diameter of shoot, number of shoot, fruitfulness of shoot and weight of fruit were further more significant (p<0.0001). Besides, determination coefficients of RRCD for traits ranged from 95.60 to 99.94% (very-high). As a result, we concluded in Ankara condition that as to herbal traits such as the height of shoot, diameter of shoot, number of shoot, fruitfulness of shoot and weight of fruit, Willamette cultivar were more superior to others. In addition, we can suggest that researchers should analyze using RRCD because Determination Coefficients of RRCD for all traits were much more found. © 2007 Asian Network for Scientific Information.
A Study on Power of Chi-Square and G Statistics in Biology Sciences
(2006) Eyduran, E.; Özdemir, T.; Kazim Kara, M.; Keskin, S.; Çak, B.
The objective of this study was to examined Chi-Square and G test statistics in place of enough sample size, contingency coefficient and power of test for different four contingency tables (data set) regarding biology sciences. Besides, this study was to determine whether sample sizes of various four samples in biology sciences were sufficient. The reliability of two statistics related to Sample size, contingency coefficient and power of test. Power analysis for Chi-Square and G test statistics were performed using a special SAS macro According to results of power analysis, sample sizes of other sets of data except the third data set were determined to be sufficient because power values for both statistics were more than 88%. With respect to power analysis, G statistics for the initial two data sets were more advantageous than other as power value of G statistics were larger than that of other. In the last data set, as sample size were 1607 and power values for both statistics were 100%, both were asymptotically equivalent each other. As power values of the third data set for Chi-Square and G test statistics were approximately 46.77 and 58.16%, respectively, sample size with 20 for both were determined to be insufficient. When we artificially increased 30 to 200 by 10, sufficient sample size for third data should be 50 so as to provide power values of 80% with respect to results of SAS special macro. As a result, this study emphasized that researchers should have taken into sample sizes and power of test account except for probability of Type Error I in contingency tables in order to determine the best one of both statistics. © 2006 Asian Network for Scientific Information.