Spss statistics program

The evaluation of the cost differences was performed by analyzing the total cost of each system during the period studied. In addition, the cost per device and day was estimated, as it was the way that external companies invoiced. To estimate the potential savings in a larger area, after evaluating the cost differences between the two systems, the cost differences if the results were applied to our entire healthcare area until 2019 were estimated.
Finally, the possible impact of an increase in the price of CPAP was estimated through a sensitivity analysis, with the price of the devices increased by 25 and 50% and the differences until 2019 estimated. Differences in the satisfaction questionnaire were studied by Chi-square or Fisher’s exact test, with a significance level of 0.05, using the IBM SPSS Statistics program (IBM Corporation, Armonk, NY) version 26.0.

The results of the experiments are indicated as mean values ± standard deviation. In a first step the distribution of the values was tested. The normality test was performed graphically and by means of the Kolmogorov-Smirnov test. The Mann-Whitney U-test was used to compare two independent groups. The following variables of the examined samples were included:-

Time of data collection (3, 7, 14, 21 days or 24, 48, 72 h)

-

Ceramic component (TCP, HA, GB14, bioglass, titanium)

-

Metal doping (Cu, Ag, Bi, no doping)

The abovementioned testing as well as the graphical representations and the statistical significance calculation were carried out with SPSS statistics program (version 22.0, IBM, Armonk, NY, USA). Results showing a significance level of p < 0.05 results were considered to be significant.

Descriptive statistics (mean and standard deviations) and other statistical analyses were made using the IBM SPSS Statistics program version 22. Independent t test for equality of means was used to compare the groups, and in case of obvious nonnormality, Mann–Whitney U test was used. The statistical significance was set at 0.05, two‐tailed. Bonferroni corrections for multiple comparisons were used. A logistic regression analysis with a backwards likelihood ratio method to eliminate insignificant variables was conducted, with a dichotomized measure of MMP‐13 in saliva as the dependent variable (a cutting value was more than 50% of the cumulative percentage) and all periodontal markers (BOP, CAL, gingival index, calculus index, plaque index, and probing depth) as explanatory variables and controlled for age, gender, and smoking habits. No test of normality or calculation of the sample size was made.

Participants who completed the finger-tapping frequency test were included in the data analyses. All data were checked for normality using the Shapiro–Wilk test. Descriptive statistics were used to show the characteristics of the participants and their mean age with SD for three groups. The differences of mean finger-tapping frequency among three groups were compared by post hoc analysis with Bonferroni-corrected Student’s t-tests. Since the finger-tapping frequency was influenced by gender and age, the analysis was separated by gender groups and age was added as a covariate. All of the analyses were conducted using the IBM SPSS Statistics program (formerly SPSS) with version 20.0 software. An alpha P value <0.05 was considered statistically significant.

Results of the experiments described in Section 2.1, Section 2.3 and Section 2.4 are presented as means (±standard deviations) of three replicate trials. The effects of EOs on the reduction of ERG, ZEA, and DON were examined by one-way analysis of variance (ANOVA). The homogeneity of variance was tested by a Levene’s test. Based on the results, an appropriate post-hoc test was selected. For homogeneous samples, Tukey’s test with a p-value < 0.05 was used, while, for nonhomogeneous samples, the Games–Howell test with a p-value < 0.05 was applied. Analyses were conducted using the IBM SPSS Statistics program.