felixwainaina/Effect-of-Shamiri-Intervention-on-Adolescent-Mental-Health

Mental health problems are prevalent among African adolescents, but professional treatment capacity is limited. Shamiri, an efficient lay provider-delivered intervention, has significantly reduced depression and anxiety symptoms in previous randomized controlled trials (RCTs). # 1\. Brief Background This report examines the impact of the Shamiri Intervention on adolescent mental health, focusing on depressive symptoms as measured by the Patient Health Questionnaire-8 (PHQ-8). The PHQ-8 is a widely used, validated tool for assessing depression severity. This analysis aims to determine if the Shamiri Intervention leads to a significant change in PHQ-8 scores compared to a control condition. The dataset includes baseline and endpoint PHQ-8 scores, along with demographic information, allowing for a comparison of changes in depressive symptoms over time between the intervention and control groups. # 2\. Data Analysis Methods The analysis was conducted using R. The following steps were performed: 1. Data Cleaning: * The data was loaded from an Excel file. * Columns were renamed for clarity. * Text responses for PHQ and GAD questions were converted to numerical scores (0-3). * Data types were adjusted (e.g., Time and Condition to factors, Age to numeric). * Missing values were imputed using the median for each column. * Duplicate rows were removed. * Total PHQ-8 and GAD-7 scores were calculated for each participant. 2. Data Preparation for Analysis: * The data was reshaped from long to wide format, with baseline and endpoint PHQ-8 scores in separate columns. * A change score was calculated by subtracting the baseline PHQ-8 score from the endpoint PHQ-8 score (Endpoint \- Baseline). 3. Statistical Analysis: * Descriptive statistics (mean and standard deviation) of the change scores were calculated for both the intervention and control conditions. * An independent samples t-test was performed to compare the mean change scores between the two conditions. * A boxplot was generated to visualize the distribution of change scores for each condition. # 3\. Findings ### Descriptive Statistics | Condition | Mean Change | SD Change | | ----- | ----- | ----- | | **Control** | 0.1698113 | 6.17917 | | **Intervention** | \-2.0800000 | 6.33049 | This t …