Stata data analysis

Chi-squared, logistic regression and correlation (Pearson and Spearman) analyses were completed using Stata data analysis and statistical software (Version 12). Prior to statistical analysis an initial model was created with ‘sometimes’ response options excluded. This allowed direct comparison between those answering definitively ‘yes’ or ‘no’ (Model 1). In the interest of completeness, survey response options were also dichotomised yielding two further datasets for analysis i.e. Model 2 = Y + S versus N and Model 3 = Y versus S + N. A total of five herd classification independent variables (i.e. region, calving-season, enterprise type, herd size, bioexclusion status) were used to examine key influences on JD risk variables. As a first step, a univariable (Pearson’s Chi-squared) analysis was completed. Independent variables recording P ≤ 0.15 were included in logistic regression models (1, 2 and 3). A manual backwards elimination with a forward step was applied to each model with significant variables (P ≤ 0.05 chosen as accepted significance level) retained in the final model. Pearson’s correlation was used to check for co-linearity across independent variables. Spearman’s rank correlation (r_s) was performed to examine relationships between dependent variables (JD survey questions) with r_s values of >0.3 reported. Biosecurity variables were not statistically analysed.

Statistical analyses were performed using the SPSS® software (Version 21). Data were analysed by Fisher’s exact test (nominally scaled) or the Mann–Whitney U-test (ordinally scaled). Differences with a probability of p < 0.05 were defined as significant. To identify independent predictors for severe TBE and functional outcome, a binary logistic regression model was performed for all items except for age, where an ordered logistic regression with the Stata® Data Analysis was conducted (Version 12, StataCorp LP, Texas, U.S.A.).

Results obtained before and after attending the ETA and results of the satisfaction questionnaire were analyzed. A descriptive statistical analysis was performed. Since variables were found to be normally distributed after have been tested through the Kolmogorov-Smirnov test, categorical data were reported as number and percentages and compared through the Chi-square test, while continuous data were reported as mean and standard deviation (SD), and compared with the Student’s t-test. Student’s t-test for paired data was performed in order to compare the total score obtained before and after attending the ETA. Results were considered statistically significant with a p-value of 0.05. All data were analyzed with STATA data analysis and statistical software version 17.0 (Copyright 1996–2022; Stata-Corp LP, College Station, TX, USA).

Data were analyzed using One-way or Two-way analysis of variance (ANOVA). Post-hoc comparisons were conducted only when the main effect was statistically significant. P-values for multiple comparisons were adjusted using Bonferroni's correction. All of the analyses were conducted using STATA data analysis and statistical software (StataCorp LP, College Station, TX). Fisher's exact probability test was used for the retrieval experiments, as previously described (Liang et al., 2014 (link)).

Data were analyzed using one-way or two-way analysis of variance (ANOVA). Post hoc comparisons were conducted only when the main effect was statistically significant. P-values for multiple comparisons were adjusted using Bonferroni’s correction. All analyses were conducted using STATA data analysis and statistical software (StataCorp LP, College Station, TX, USA).

The primary data analyses were descriptive statistics of the cohort including geographical practice location, years of experience, qualifications held and practice sector. Nominal logistic regression was performed and relative risk ratios calculated for possible factors affecting clinical indications to perform vascular assessment and the type of vascular testing that was performed. These clinical indicators included combinations of the type of referral received, clinical signs and symptoms of PAD and patient medical history. Vascular assessment performed included combinations of clinical observations, Doppler use and pressure measurements. The fit of the data to the final nominal logistic regression model was assessed using the Homser-Lemeshow test with a p value >0.05 indicating an adequate fit. All data analysis was conducted using Stata data analysis and statistical software version 13. Missing data were excluded case wise.

All statistical analyses were completed by using Stata data analysis and statistical software version 11.1 (Stata Corp., College Station, TX, USA) [34 ]. Baseline and change data are reported as either mean ± standard deviation (SD) for normally distributed variables or median (interquartile range (IQR)) for non-normally distributed variables. An independent t-test or non-parametric equivalent (rank sum) was used to determine any differences in demographic and dietary data between intervention groups at baseline. Wilcoxon rank rum was used to compare differences in migraine frequency, severity and duration between intervention groups. The level of significance was set at p < 0.05. As migraine data (frequency, duration and severity) were not collected at each of the four time-points (only collected if they occurred during the intervention), we were unable to perform any imputation or linear mixed models for an intension-to-treat analysis. Results presented are for those who completed all measurement sessions and the AES at each of the four time-points. For these completers, it was assumed that no migraine data meant no incidence of migraine during the intervention.