Stata

Because of the small losses to follow-up and the low percentage of SARS-CoV-2 infected [10 , 11 ], cumulative incidence was used. The association between the use of public transport before and after the initial lockdown period and subsequent contraction of SARS-CoV-2 was investigated using logistic regression. All individuals who had not contracted SARS-CoV-2 by January 27, 2021, were included as controls. We estimated odds ratios (ORs) with 95% confidence intervals (CIs) adjusting for age, calendar time, gender, municipality, smoking habits, income level, fitness and underlying medical conditions. Trend test was performed by fitting ordinal values corresponding to exposure categories and testing whether the slope coefficient differed from zero. All analyses were performed using Stata (Stata Statistical Software, release 16, Stata Corp., College Station, TX) and R (version 3.6.2). A two-sided p-value of less than 0.05 was considered statistically significant. Sensitivity analyses were performed in health care workers and in non-health care workers, and by sex.

Risk ratios/relative risks (RRs) of adverse pregnancy outcomes by multiple micronutrient supplementation were analyzed using logistic regression. Potential confounding of significant associations by dietary intakes were investigated by adjusting these models for food frequency intakes. Continuous variables were analyzed in statistical models using linear regression, adjusted for confounders where appropriate. Where the dependent variable residuals were skewed, the models were analyzed with prior transformation of the data so that the residuals were normally distributed. Other categorical variables were analyzed using a χ²-test, Fisher’s exact test (as appropriate), or logistic regression. RRs were calculated using the Stata binreg function. Missing data were dealt with using case or listwise deletions, and p < 0.05 was considered statistically significant throughout. The statistical analyses were performed using either Stata (version 13.1; Stata Corp., from Timberlake Consultants Ltd., Richmond, Surrey, UK) or R (version 3.6.1; The R Foundation for Statistical Computing, Vienna, Austria).

We analyzed pooled studies in a random-effects model using the statistical method of Inverse Variance with Review Manager, and calculated the weighted mean difference (WMD) or standard mean difference (SMD) with 95% confidence interval (CI). Heterogeneity was quantified with Review Manager using the I² statistic; I² values of 25%, 50%, and 75% represented low, moderate, and high heterogeneity, respectively. Sensitivity analyses were performed using the statistical method of meta-based Influence Analysis with STATA to assess the general effects after specific studies were omitted. A descriptive statistics analysis of TET, which included normality tests, percentiles distribution and frequency histogram, was conducted with SPSS for dividing groups of studies into “short time”, “medium time” and “long time”. Subgroup analyses of the TET and disease categories (HFrEF and HFpEF) were performed with Review Manager to assess part of potential source of heterogeneity. A funnel plot and contour-enhanced funnel plot were made with STATA to identify publication bias. A two-tailed P value lower than 0.05 was considered statistically significant. Review Manager (Version 5.4), SPSS (Version 21.0) and STATA (Version 16.0) were the software used in the analyses.

We used Visual Basic 6.0/ASP.net and Oracle 8i to manage the data, with stringent range, consistency, and logical checks. To ensure data quality and accuracy, real time data entry was done using netbook. Data were analyzed separately for the hospital and community births using Statistical Package of Social Sciences (SPSS Inc., Chicago, Illinois, USA, SPSS, Version 19.0 for Windows) and Stata (Stata Corp., College Station, Texas, USA, Intercooled Stata 12.0 Version), P ≤ 0.05 was considered statistically significant for all analyses. Descriptive statistics (frequencies, percentages, means and standard deviation) were calculated. We examined the characteristics of newborns and mothers across the allocated groups on a range of variables to determine the degree of balance achieved by the randomization. We analyzed colonization positivity data by intervention groups and follow-up time. Among those that were positive, we further estimated distribution of colony counts by intervention groups and follow-up time. A paired analysis comparing the baseline positivity/colony count of the child with his 2- and 48-hours post intervention positivity/counts was performed to study any group differences as well as changes over follow-up time within group. The chi square, t- test and OR with 95 % CI were used to estimate statistics and significance.

The definition of high myopia was spherical equivalent (SE) -6.00 D or less. SE was calculated as sum of sphere and 1/2 cylinder. Quantile regression, a type of regression model estimating conditional quantile functions, was adopted to construct the reference centile curves on the RESC cross-sectional data.
To validate the accuracy of the age-specific severity estimation in predicting high myopia, baseline centiles and refraction at age 15 years of first-born twins were used as test and outcome variables to conduct diagnostic test. The sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV) and Mathew’s correlation coefficient (MCC) were calculated. Predictions were made by locating a subject into regions between the quantile curves based on his/her age and SE, to identify if he/she would develop high myopia by the age of 15. All the statistical analysis was performed with Stata (Stata version 12.0, Stata Corp., College Station, TX)[21 ].

Logistic regression with robust standard errors was used to evaluate relationships between metrics on purchase of vegetables in the last 7 days (binary outcome). These results are presented as odds ratio (OR) with 95% confidence interval (CI). Multiple regression with robust standard errors was used for analysis of FE with vegetable purchase diversity, energy intake (kcal), WHR, and BMI. Two sensitivity analyses were conducted: (1) Different buffer sizes for clusters under the dispersion metrics; (2) FE metrics on energy intake adjusted for bodyweight (Kg). Descriptive statistics are presented as median and interquartile ranges (IQR). Statistical analyses were conducted in Stata, visualized in R Studio and Stata, and mapped in Geoda and QGIS.