“close to the margin of statistical significance”

In the full model (model 3), further adjusted fo the number of excisional haemorrhoids, the association between depression and postoperative pain was close to the margin of statistical significance ( β : 0.61; 95% CI: 0.01 to 1.21; p = 0.05).

There was a statistically significant decrease of the NAA/Cr ratios in HT patients in groups with different disease length in comparison to the healthy controls, except from the group 1 (duration of the disease 2–5 years) in the PWM region, however the p value was close to the margin of statistical significance ( p = 0.05).

Combined effect of hyperoxia and E 2 depletion with subsequent administration of E 2 lowered Nrf-2 nuclear level close to the margin of statistical significance, most probably due to small sample size ( p =0.065, hsham vs. hovxe) ( Fig. 6 A).

ESR was associated only with TST90, but close to the margin of statistical significance ( p = 0.076).

In addition to those mentioned above, other metabolites, such as succinate, dimethylamine, creatinine, and an unknown signal in the region of 3.5–3.7 ppm, were close to the margin of statistical significance.

Nevertheless, the numerical differences between active smokers and never smokers were close to the margin of statistical significance and are consistent with a culprit effect of active smoking in downregulating miR-27b compared with prior smokers and, likely, never smokers as well.

However, in these regression analyses, the OR associated with baseline platelet levels was close to the margin of statistical significance, so another multivariate model was calculated.

The difference among the scores of the participants for the PLNS subscale of “medications” was not statistically significant according to gender, but was close to the margin of statistical significance.

However, although there was a significant difference in study 1 ( p = 0.040), it was close to the margin of statistical significance.

Furthermore, the confidence intervals for some pooled results were close to the margin of statistical significance, which implies that the pooled results may vary in the case of a change in the study selection or in certain conditions.

Univariate proportional hazards regression analyses were performed to identify factors associated with first-line regimen discontinuation, and multivariable proportional hazards regression analysis was performed that included all factors for which the results of univariate analysis were statistically significant (P<0.05) or close to the margin of statistical significance.