Epi info version 7

The collected data were checked for errors and completeness on daily basis. Data were entered into EPI- Info version 7 and exported to SPSS version 20 for analysis.
Frequencies and percentages were done to see the magnitude of events in the study. Bivariate logistic regression analysis was computed to test whether there is an association between Iodine content of salt and selected independent variables.
Independent variables with a significance level less than or equal to 0.20 in the bivariate logistic regression analysis were entered to the multivariable logistic regression analysis. The multivariable logistic regression model was built with backward elimination.

Data were coded and entered in to a computer using epi-info version 7 and exported to SPSS version 21 software for analyses. Any logical and consistency error identified during data entry was corrected after revision of the original completed questionnaire. Descriptive statistics was employed using frequencies and percentages. Both bivariable and multivariable logistic regression models were used to determine factors associated with essential neonatal care utilization. Model of fitness was checked by Hosmer and Lemeshow test and its p-value was 0.807. To identify factors associated with essential new born care utilization, variables with p-value < 0.2 in the bivariable analyses were entered into multivariable logistic regression model and those with p-value <0.05 in the multivariable logistic regression model were considered as independent factors. Crude and adjusted Odds ratios were computed for each explanatory variable to determine the strength of association at 95% Confidence Interval (CI).

The data collected from the respondents were entered into Epi Info version 7 and imported to SPSS-20. First, descriptive statistics of the generalized psychological distress were generated with the aim of assessing the prevalence of generalized psychological distress in the study population using cutoffs ≥19. Logistic regression models were used to assess univariate associations between the dependent variable generalized psychological distress and independent variables, grouped into sets of demographic, psychosocial, and HIV-related clinical risk factors, with unadjusted and adjusted odds ratio (adjusted for sex and age group) reported. After adjusting within each set of risk factors, those associated with generalized psychological distress at a level of significance of 0.1 were entered into a multivariable model using forward stepwise methods to determine their independent effect on psychological distress. A confidence interval of 95% was used to see the precision of the study, and the level of significance was taken at α<0.05.

The data were entered using Epi info version 7 and exported to SPSS version 20 for analysis. Descriptive statistics were used for organizing, describing and summarizing the data. Both bivariable and multivariable logistic regression was run to determine the association between explanatory variables, and response variables. Initially, bivariable logistic regression was used to identify factors independently associated with the outcome variable at a p-value of less than 0.25 based on previous evidence. David W. Hosmer and Stanley Lemeshow in their second edition book entitled “Applied Logistic Regression” recommended using a P-value of less than 0.25 as a screening criterion for variable selection for the multivariable analysis [39 ]. Other published articles used a p-value of 0.2 as a cut-off point to select variables for the multivariable analysis [40 (link)–43 (link)]. Therefore, in this study, variables having P-value ≤0.25 in the bivariate analysis were considered for multivariable analysis. Besides, analysis of multicollinearity was performed (Supplementary file 2). Then multivariable logistic regression was used to control the effect of confounding factors. Statistical significance was determined using a 5% level of significance and odds ratio with 95% CI.

Data were entered, edited, and cleaned using Epi-info version 7 and exported to SPSS version 20 for further statistical analysis. The descriptive analysis such as proportions, percentages, frequency distribution, and measure of central tendency was carried out.
Next to this, the bivariate analysis was done to identify whether there was an association between the dependent and independent variables to select the candidate variable for the multivariable analysis. Accordingly, variables found to have an association with the dependent variable less than 0.2 p-values were entered into multivariable binary logistic regression using the enter method for controlling the possible effects of confounders. Finally, the variables which had a significant association with p-value < 0.05 were identified as significant variables based on the odds ratio (OR), with 95% CI. The goodness of fit test was also checked.