Central hub for data assembly, collaboration, and communication. These tools help you organize datasets, coordinate with team members, and maintain documentation throughout the SNT process.
1
DATA ASSEMBLY AND COMMUNICATION PLATFORM
Central hub for data assembly, collaboration, and communication.
2
DATA COLLECTION (ICF COLLECT)
Design data collection forms, collect data offline, and submit when data is available.
Section 1 of 25
2DATA EXTRACTION
Extract raw data from DHIS2 and external sources.
1
EXTRACT DHIS2 ROUTINE DATA
Extract epi, intervention and stock data from DHIS2
2
POPULATION DATA
Extract population datasets from World Population
3
RAINFALL DATA
Extract rainfall and climate data from CHIRPS
Section 2 of 25
3DATA TRANSFORMATION
Transform and reshape your datasets.
1
ADMIN LEVEL HIERARCHY
Verify unique identifiers across admin hierarchy levels
2
WIDE TO LONG FORMAT
Convert wide format data to long format structure
3
LONG TO WIDE FORMAT
Convert long format data to wide format structure
4
FUZZY MATCH: POPULATION & ROUTINE
Match population data to routine data using fuzzy logic
5
FUZZY MATCH: SHAPEFILE & ROUTINE
Match shapefile data to routine data using fuzzy logic
6
FUZZY MATCH: MFL & DHIS2
Match Master Facility List to DHIS2 facility data
7
HF COORDINATE CLEANING
Clean and validate health facility coordinate columns
8
COORDINATE CONVERSION
Convert any coordinate format to Longitude/Latitude
9
COLUMN GROUPING TOOL
Group and organize columns by category or type
10
JSON TO SHAPEFILE
Convert GeoJSON files to Shapefile format
11
SHAPEFILE TO JSON
Convert Shapefile format to GeoJSON files
12
SHAPEFILE BOUNDARY OVERLAY
Create or overlay higher admin unit boundaries
13
ADMIN-UNIT-SHAPEFILES
Generate admin unit shapefiles from boundaries
Section 3 of 25
4DATA PREPROCESSING OF ROUTINE EPI DATA
Prepare and clean routine epidemiological data.
1
COMBINE EPI FILES
Merge multiple EPI data files into consolidated dataset
2
RENAME EPI VARIABLES
Standardize EPI column names and conventions
3
RENAME FROM DATA DICTIONARY
Rename variables using data dictionary mapping
4
CREATE EPI INDICATORS
Compute derived EPI variables and indicators
5
COMPUTE NEW VARIABLE FROM DATA DICTIONARY
Create new variables using data dictionary formulas
6
SORT EPI COLUMNS
Reorder EPI columns by category or custom order
7
SPLIT PERIOD COLUMN
Split period into separate year and month fields
8
CREATE FACILITY UID
Generate unique Health Facility identifiers
9
CREATE REPORT COLUMN
Add reporting period and status columns
10
CREATE YEAR-MONTH COLUMN
Combine year and month into formatted column
11
DIAGNOSTIC CHECK
Run diagnostic checks on EPI data columns
12
COLUMN CONSISTENCY CHECK
Verify column consistency across datasets
13
OUTLIER DETECTION
Identify and handle statistical outliers
14
DATA QUALITY ASSESSMENT
Merge EPI files based on common key columns
15
MERGE WITH POPULATION & SHAPEFILE
Combine EPI data with population and shapefile
16
HF TYPE
Convert column data types appropriately
17
FINAL EPI DATABASE
Generate final consolidated EPI database
Section 4 of 25
5ANALYSIS ON REPORTING
Analyze reporting completeness and patterns.
1
REPORTING MATRIX
Generate reporting matrix by facility and period
2
HF REPORTING STATUS
Track health facility reporting status
3
REPORTING RATE BY ADMIN LEVEL
Calculate reporting rates at admin levels
Section 5 of 25
6ACTIVE & INACTIVE STATUS OF HEALTH FACILITIES
Determine operational status of health facilities.
1
HF ACTIVE/INACTIVE STATUS
Classify facilities as active or inactive
Section 6 of 25
7COHERENCY CHECK & STRIPPLOTS
Validate data coherency and visualize distributions.
1
COHERENCY CHECK & STRIPPLOTS
Run coherency validation and stripplots
Section 7 of 25
8CASE MANAGEMENT
Analyze malaria case management indicators.
1
CASE MANAGEMENT ANALYSIS
Analyze testing and treatment indicators
Section 8 of 25
9EPI STRATIFICATION
Stratify and classify epidemiological data.
1
POPULATION GEOSPATIAL
Geospatial analysis of population
2
TEST POSITIVITY RATE
Calculate test positivity rates
3
CRUDE INCIDENCE
Calculate crude incidence rates
4
ADJUSTED INCIDENCE (LEVEL 1)
First level adjusted incidence
5
ADJUSTED INCIDENCE (LEVEL 2)
Second level adjusted incidence
6
ADJUSTED INCIDENCE (LEVEL 3)
Third level adjusted incidence
7
RISK CLASSIFICATION
Classify areas by risk levels
Section 9 of 25
10STRATIFICATION OF OTHER DETERMINANTS
Analyze additional factors influencing malaria.
1
SEASONALITY ANALYSIS
Identify seasonal patterns
2
SMC ELIGIBILITY
Determine SMC eligibility
3
POINT COORDINATES
Manage facility coordinates
4
ACCESS TO CARE
Analyze healthcare access
Section 10 of 25
11DATA PREPROCESSING OF ROUTINE INTERVENTION DATA
Prepare and clean routine intervention data.
1
COMBINE INTERVENTION FILES
Merge intervention files
2
RENAME INTERVENTION VARIABLES
Standardize column names
3
CREATE INTERVENTION INDICATORS
Compute derived variables
4
SORT INTERVENTION COLUMNS
Reorder columns
5
SPLIT PERIOD COLUMN
Split year and month
6
CREATE FACILITY UID
Generate unique IDs
7
CREATE REPORT COLUMN
Add report columns
8
CREATE YEAR-MONTH COLUMN
Combine year-month
9
DIAGNOSTIC CHECK
Run diagnostics
10
COLUMN CONSISTENCY CHECK
Verify consistency
11
OUTLIER DETECTION
Detect outliers
12
MERGE INTERVENTION FILES
Merge files
13
MERGE WITH POPULATION & SHAPEFILE
Combine datasets
14
DATA TYPE CONVERSION
Convert data types
15
FINAL INTERVENTION DATABASE
Generate final database
Section 11 of 25
12COHERENCY CHECK & STRIPPLOTS (INTERVENTION)
Validate intervention data coherency.
1
INTERVENTION COHERENCY CHECK
Run coherency validation
Section 12 of 25
13GEOSPATIAL ANALYSIS OF ROUTINE INTERVENTION DATA
Perform geospatial analysis on intervention data.
1
INTERVENTION GEOSPATIAL ANALYSIS
Generate geospatial analysis
Section 13 of 25
14DATA PREPROCESSING OF ROUTINE STOCKOUT DATA
Prepare and clean routine stockout data.
1
COMBINE STOCKOUT FILES
Merge stockout files
2
RENAME STOCKOUT VARIABLES
Standardize column names
3
CREATE STOCKOUT INDICATORS
Compute derived variables
4
SORT STOCKOUT COLUMNS
Reorder columns
5
SPLIT PERIOD COLUMN
Split year and month
6
CREATE FACILITY UID
Generate unique IDs
7
CREATE REPORT COLUMN
Add report columns
8
CREATE YEAR-MONTH COLUMN
Combine year-month
9
DIAGNOSTIC CHECK
Run diagnostics
10
COLUMN CONSISTENCY CHECK
Verify consistency
11
OUTLIER DETECTION
Detect outliers
12
MERGE STOCKOUT FILES
Merge files
13
MERGE WITH POPULATION & SHAPEFILE
Combine datasets
14
DATA TYPE CONVERSION
Convert data types
15
FINAL STOCKOUT DATABASE
Generate final database
Section 14 of 25
15COHERENCY CHECK & STRIPPLOTS (STOCKOUT)
Validate stockout data coherency.
1
STOCKOUT COHERENCY CHECK
Run coherency validation
Section 15 of 25
16GEOSPATIAL ANALYSIS OF ROUTINE STOCKOUT DATA
Perform geospatial analysis on stockout data.
1
STOCKOUT GEOSPATIAL ANALYSIS
Generate geospatial analysis
Section 16 of 25
17GEOSPATIAL ANALYSIS OF OTHER INTERVENTIONS
Perform geospatial analysis on other interventions.
1
OTHER INTERVENTIONS GEOSPATIAL
Analyze other interventions
Section 17 of 25
18DATA PREPROCESSING FOR INTERVENTION TARGETING
Prepare data for intervention targeting analysis.
1
TARGETING DATA PREPARATION
Prepare targeting dataset
Section 18 of 25
19DECISION TREES, INTERVENTION TARGETING & MIXES
Design intervention packages and targeting strategies.
1
INTERVENTION TARGETING & MIXES
Design decision trees and mixes
Section 19 of 25
20DECISION TREE FOR PRIORITIZATION
Prioritize areas for intervention implementation.
1
PRIORITIZATION DECISION TREE
Apply decision tree logic
Section 20 of 25
21SNT COSTING TOOL
Calculate costs for intervention packages.
1
SNT COSTING CALCULATOR
Calculate intervention costs
Section 21 of 25
22DESCRIPTIVE STATISTICS & DATA VISUALIZATION
Summarize and visualize data distributions using a complete suite of descriptive tables and chart types.
1
FREQUENCY TABLES
Generate one-way and two-way frequency tables with counts, percentages, and cumulative totals
Create cross-tabs with row, column, and cell percentages for two or more categorical variables
4
BAR CHART
Simple, grouped, and stacked bar charts for categorical comparisons
5
HISTOGRAM
Distribution histogram with adjustable bin width, density overlay, and normal curve
6
PIE & DONUT CHART
Pie and donut charts showing proportional composition of categorical data
7
LINE CHART
Trend lines for time series data with multi-series overlay and confidence bands
8
BOX PLOT
Box-and-whisker plots showing median, IQR, and outliers across groups
9
SCATTER PLOT
Bivariate scatter plots with regression line, R-squared, and grouping by category
10
HEATMAP
Correlation matrix heatmap and cross-tabulation heatmap with color intensity mapping
11
VIOLIN PLOT
Violin plots combining density estimation with box plot for distributional shape
12
BUBBLE CHART
Three-variable scatter plot where bubble size encodes a third numeric dimension
13
AREA CHART
Stacked and filled area charts for cumulative or proportional time-series data
14
WATERFALL CHART
Waterfall/bridge charts showing sequential contributions to a cumulative total
15
RADAR / SPIDER CHART
Multi-dimensional radar charts for comparing profiles across multiple variables
16
TREEMAP
Hierarchical treemaps for visualizing nested proportional data by category
17
FUNNEL CHART
Funnel charts for pipeline stages, health cascade analysis, and dropout rates
18
DOT PLOT
Cleveland dot plots and strip plots for comparing values across categories clearly
19
DENSITY PLOT
Kernel density estimation plots for continuous distributions by group
20
CUMULATIVE DISTRIBUTION PLOT
Empirical CDF and ECDF plots for comparing distributions across groups
Section 22 of 25
23INFERENTIAL STATISTICS & ANALYTICAL METHODS
Comprehensive suite of inferential tests, regression models, and advanced analytical methods for hypothesis testing, causal inference, and predictive modelling of public health data.
1
CHI-SQUARE GOODNESS OF FIT
Test whether observed frequencies match an expected distribution for one categorical variable
2
CHI-SQUARE TEST OF INDEPENDENCE
Test association between two categorical variables in a contingency table
3
FISHER'S EXACT TEST
Exact test of independence for small sample 2x2 contingency tables
4
FISHER'S GOODNESS OF FIT
Freeman-Tukey (Fisher) goodness-of-fit test for sparse or small-sample frequency data
5
McNEMAR'S TEST
Paired nominal data test for before-after or matched-pair binary outcomes
6
MANN-WHITNEY U TEST
Non-parametric test comparing distributions of two independent groups
7
WILCOXON SIGNED-RANK TEST
Non-parametric test for paired or one-sample comparison against a median
8
KRUSKAL-WALLIS TEST
Non-parametric one-way ANOVA equivalent for three or more independent groups
9
ONE-SAMPLE T-TEST
Test whether the sample mean differs significantly from a known reference value
10
INDEPENDENT TWO-SAMPLE T-TEST
Compare means of two independent groups with equal or unequal variance options
11
PAIRED SAMPLES T-TEST
Compare means of matched or repeated measures on the same subjects
12
ONE-WAY ANOVA
Test mean differences across three or more groups with post-hoc comparisons (Tukey, Bonferroni)
13
TWO-WAY ANOVA
Two-factor ANOVA with main effects and interaction term
14
THREE-WAY ANOVA
Three-factor ANOVA examining main effects and all two-way and three-way interactions
15
REPEATED MEASURES ANOVA
Within-subjects ANOVA for time-series or repeated measurement designs
16
MANOVA
Multivariate ANOVA for simultaneous testing of multiple continuous outcome variables
17
ANCOVA
Analysis of covariance adjusting for continuous confounders in group comparisons
18
SIMPLE LINEAR REGRESSION
Model the linear relationship between one predictor and a continuous outcome
19
MULTIPLE LINEAR REGRESSION
Multivariable linear model with diagnostics: residuals, VIF, leverage, and heteroscedasticity tests
20
SIMPLE LOGISTIC REGRESSION
Binary outcome model with odds ratios, confidence intervals, and ROC-AUC
21
MULTIPLE LOGISTIC REGRESSION
Multivariable logistic model with adjusted odds ratios, Hosmer-Lemeshow test
22
LASSO LOGISTIC REGRESSION
Penalized logistic regression with L1 regularization and cross-validated lambda selection
23
RIDGE & ELASTIC NET REGRESSION
L2 and combined L1/L2 penalized regression for high-dimensional and collinear data
24
MIXED EFFECTS LOGISTIC REGRESSION
Random effects logistic model accounting for clustering at facility or district level
25
MULTINOMIAL LOGISTIC REGRESSION
Model for nominal outcomes with more than two categories and relative risk ratios
26
ORDINAL LOGISTIC REGRESSION
Proportional odds model for ordered categorical outcomes
27
POISSON REGRESSION
Count data model with incidence rate ratios; offset for population exposure
28
NEGATIVE BINOMIAL REGRESSION
Overdispersed count model handling excess variance beyond Poisson assumptions
29
KAPLAN-MEIER SURVIVAL ANALYSIS
Estimate and plot survival functions with log-rank test for group comparisons
30
LOG-RANK TEST
Non-parametric comparison of survival curves between two or more groups
31
COX PROPORTIONAL HAZARDS
Semi-parametric survival regression with hazard ratios and PH assumption check
32
ODDS RATIO & RISK RATIO
Calculate OR, RR, ARR, NNT with 95% CI from 2x2 tables; stratified Mantel-Haenszel estimates
33
INTERRUPTED TIME SERIES (ITS)
Segmented regression for evaluating the effect of a policy or intervention on a time-series outcome
34
DIFFERENCE-IN-DIFFERENCES (DiD)
Quasi-experimental DiD estimator with parallel trends test and heterogeneity analysis
35
PROPENSITY SCORE MATCHING
Balance covariates between treatment groups using propensity score matching and weighting
36
INSTRUMENTAL VARIABLE (IV)
Two-stage least squares estimation for addressing endogeneity in observational studies
37
MIXED EFFECTS LINEAR MODEL
Linear mixed model with random intercepts and slopes for repeated or clustered data
38
MULTILEVEL (HIERARCHICAL) MODEL
Multilevel modelling for nested data structures (patients within facilities within districts)
39
PEARSON & SPEARMAN CORRELATION
Parametric and non-parametric correlation coefficients with significance testing
40
PARTIAL CORRELATION
Correlation between two variables controlling for the effect of one or more covariates
41
NORMALITY TESTS
Shapiro-Wilk, Kolmogorov-Smirnov, Anderson-Darling, and QQ-plot normality diagnostics
42
LEVENE'S & BARTLETT'S TEST
Test homogeneity of variances assumption prior to ANOVA or t-tests
43
POWER & SAMPLE SIZE CALCULATOR
Calculate required sample size or achieved power for t-tests, ANOVA, proportions, and regression
44
META-ANALYSIS
Fixed and random effects meta-analysis with forest plots, funnel plots, and heterogeneity statistics
Section 23 of 25
24MATHEMATICAL MODELING & COMPARTMENTAL MODELS
Build, simulate, and analyse compartmental epidemiological models for malaria and other infectious diseases. From classic SIR dynamics to vector-host transmission, parameter estimation, and reproduction number calculation.
1
SIR MODEL
Classic Susceptible-Infectious-Recovered model with phase-plane, time-series, and R₀ output
2
SIRS MODEL
SIR with waning immunity; susceptibles re-enter the pool after loss of protection
3
SIS MODEL
Susceptible-Infectious-Susceptible model for diseases conferring no lasting immunity
4
SEIR MODEL
Includes exposed/latent compartment before infectious stage; tracks epidemic dynamics
5
SEIRS MODEL
SEIR with waning immunity allowing re-entry to susceptible pool after recovery
6
SIRD MODEL
SIR extended with disease-induced mortality; tracks fatality dynamics separately
7
SEIRD MODEL
SEIR extended with mortality compartment for modelling case fatality rate dynamics
8
ROSS-MACDONALD MODEL
Classic vector-host malaria model with mosquito biting rate, EIR, and vectorial capacity
9
VECTOR-HOST (VBD) MODEL
General vector-borne disease compartmental model for human and vector populations
10
AGE-STRUCTURED MODEL
Age-stratified SEIR with WAIFW contact matrix
11
MULTI-PATCH SPATIAL MODEL
Metapopulation model linking patches via mobility matrix; spatial spread analysis
12
STOCHASTIC SIR MODEL
Gillespie stochastic simulation of SIR with extinction probability and ensemble plots
13
BASIC REPRODUCTION NUMBER (R₀)
Next-generation matrix method for R₀ calculation with sensitivity to parameter changes
14
SENSITIVITY ANALYSIS (PRCC)
Partial Rank Correlation Coefficient and tornado plots for model parameter sensitivity
15
PARAMETER ESTIMATION & FITTING
Least-squares and MCMC Bayesian fitting of model parameters to observed epidemic data
16
EPIDEMIC THRESHOLD ANALYSIS
Bifurcation diagrams, endemic equilibrium, and herd immunity threshold computation
Section 24 of 25
25MACHINE LEARNING & PREDICTIVE ANALYTICS
Apply supervised, unsupervised, and deep learning methods to health and epidemiological data. From risk prediction and disease classification to clustering, anomaly detection, and time-series forecasting for malaria and public health programmes.
1
DECISION TREE CLASSIFIER
Interpretable tree-based classification with Gini/entropy split, pruning, and confusion matrix
2
RANDOM FOREST CLASSIFICATION
Ensemble of decision trees for binary and multi-class outcomes with OOB error and variable importance
3
RANDOM FOREST REGRESSION
Ensemble regression for continuous outcomes with partial dependence plots and RMSE diagnostics
4
GRADIENT BOOSTING (XGBoost)
XGBoost/LightGBM boosted trees for classification and regression with SHAP value explanations
5
SUPPORT VECTOR MACHINE (SVM)
SVM classifier and regressor with kernel selection, hyperplane visualization, and ROC-AUC
6
K-NEAREST NEIGHBORS (KNN)
Instance-based classification and regression with optimal k selection via cross-validation
7
NAIVE BAYES CLASSIFIER
Probabilistic classifier for binary and multi-class health outcomes with prior and posterior display
8
K-MEANS CLUSTERING
Partition-based clustering with elbow method, silhouette scores, and cluster profile summaries
9
HIERARCHICAL CLUSTERING
Agglomerative clustering with dendrogram, linkage methods, and district/facility grouping
10
PRINCIPAL COMPONENT ANALYSIS (PCA)
Dimensionality reduction with scree plot, biplot, and explained variance decomposition
11
NEURAL NETWORK (MLP)
Multi-layer perceptron for classification and regression with layer configuration and loss curves
12
TIME SERIES FORECASTING (Prophet)
Facebook Prophet and ARIMA for forecasting malaria cases, incidence trends, and seasonality decomposition
13
LSTM / DEEP TIME SERIES
Long Short-Term Memory recurrent network for multi-step health indicator forecasting
14
ANOMALY DETECTION
Isolation Forest and Autoencoder-based anomaly detection for surveillance data outliers
15
FEATURE IMPORTANCE & SELECTION
Permutation importance, SHAP, Boruta, and RFE methods for identifying key predictors
16
MODEL EVALUATION & CROSS-VALIDATION
K-fold CV, ROC-AUC, precision-recall, calibration curves, and confusion matrix reporting
Section 25 of 25
1TOOL NAME
Loading content...
External Application
This content requires opening in a new browser tab.
