mkaranja/ACIAR-Project

ACIAR Project: Identifying potential biosecurity systems for Fusarium wilt TR4 with smallholder banana producers in Tanzania and Mozambique (TR4 Biosecurity project) # ACIAR-Project ACIAR Project: Identifying potential biosecurity systems for Fusarium wilt TR4 with smallholder banana producers in Tanzania and Mozambique (TR4 Biosecurity project) ## Data Cleaning Documentation: ACIAR Survey Data for Tanzania This documentation provides a clear and concise record of the data cleaning process, including the steps taken to export the data from ONA and the cleaning procedures performed using R. ### STEP 1. DATA EXPORT FROM ONA To export the ACIAR survey data from ONA, the following steps were taken: - Navigate to the project's "Overview" tab and click on the "Prepare Data Export" button in the "Data Exports" section. - In the subsequent window, select "CSV" as the file type and click on "Show advanced export options". - Ensure the following options are checked: - remove prefixed group names - include links of images - include labels - Export with choice labels - Uncheck all other options. Click "Export CSV file" to download the data. ### STEP 2: DATA CLEANING The data cleaning process was performed using R for statistical analysis. The following steps were taken: - Only data collected from Tanzania on or after "2023-10-20" was included in the analysis. - The data was cleaned and organized by sections, with each section saved in its own Excel worksheet. - Empty columns were dropped from all sections. - values were standardized eg. proper spelling, removed special characters (spaces) #### SECTION 1: DEMOGRAPHICS Questions with 'other specify' options, were standardized to ensure that the data was consistent. The following changes were made. For question 8(q8_education_level), 'other specify' values were recorded as follows: + ("secondary education (o level)","secondary school","secondary education ( form 4)","o level") = "high school education" For question 11(q11_land_acquisition_method), 'other specify' values were recorded as follows: + ("bought and inherited", "inherited and bought", "two acres were inherited but 5 …