Spss statistic version 26

A two-step cluster analysis (with Schwarz’s Bayesian criterion) was chosen to identify clusters based on BMI, COVID-related stress, and body dissatisfaction. This analysis is appropriate for samples larger than 200 and for both categorical and continuous variables [44 (link)]. One-way analysis of variance (ANOVA) with Bonferroni multiple comparison tests was used to assess differences between the clusters with regard to emotional overeating, eating motives (health, weight control, affect regulation), and mindful eating (recognition, awareness). The significance level was defined as p  <  0.05. All analyses were conducted using IBM SPSS Statistic version 26 (IBM, Armonk, New York, United States).

The Kolmogorov-Smirnov test demonstrated that some of the parameters were not normally distributed, whereby we adopted a non-parametrical statistical approach. To test whether the cows preferred to interact before with the owner or the stranger we used a two-tailed binomial test with a test value of 0.5. The variables, cows’ age, cortisol levels, OXT levels, caregiver-directed behaviors, stranger-directed behaviors, and apparatus-directed behaviors were used for analysis by Spearman’s correlation, both for the duration and the latency. We have considered multiple comparisons adjusting significant p values according to Bonferroni correction. All statistical tests were performed by IBM SPSS statistic, version 26 (IBM Corp., Armonk, NY, USA).

Our analyses were conducted using IBM SPSS Statistic version 26 (IBM, Armonk, NY, USA) (correlations and regression models) with PROCESS macro (moderation).

IBM SPSS Statistic version 26 was used for data analysis. Statistical tests were as follows: Cronbach Alpha test, Pearson Correlation test and t-test. The standard level of significance was 5%, or stated as 0.05 in the p-value.

Analysis of variance (ANOVA) was carried out for all the analytical results determined in wines with the IBM^® SPSS^® Statistic version 26 (Armonk, New York, USA). Significant differences were established by using the Tukey post hoc test (p < 0.05–0.01).

The subjects’ characteristics were summarized depending on the variables of interest: as frequencies and percentages, as appropriate for categorical variables, as means (±SD) or medians (±IQR), as appropriate for continuous variables. The Pearson’s Chi-squared test, ANOVA or Kruskal Wallis, t-test, or Mann-Whitney tests were used to assess the differences among groups, depending on the type and the distribution of the variables. The associations between greenness exposure and respiratory symptoms were assessed through Odds Ratios (ORs), calculated through logistic regression models using respiratory symptoms (0 = not present; 1 = present) as dependent variables and NDVI, divided into tertiles, as the main independent variable. Logistic regression models were adjusted for age, sex, body mass index (BMI) and urinary cotinine levels. Furthermore, Generalised Linear Models were used to test the association between the respiratory flows measured by spirometry and greenness.
The significance level was set ≤5%. Statistical analyses were performed using IBM SPSS® statistic version 26 integrated with R (3.6.1).