Saylac
Spatial Analysis of Yearly, Longitudinal, and Areal Change
Provides the Saylac Shiny application for multidisciplinary analysis of global, national, and regional indicators observed across places and years. SAYLAC abbreviates Spatial Analysis of Yearly, Longitudinal, and Areal Change. The platform supports spatial diagnostics, longitudinal data exploration, time-series diagnostics, comparative forecasting, and automated reporting for development, health, education, economic, environmental, and social indicators. The application implements three connected modules: Spatial Analysis Workflow for exploratory spatial data analysis, Single Model Diagnostics for stationarity testing, trend diagnostics, and comparative forecasting, and Spatial Uncertainty and Reporting Analysis Dashboard for forecast mapping, spatial clustering, and reporting. The application supports choropleth mapping, Moran's I, Geary's C, Local Indicators of Spatial Association, Getis-Ord Gi star statistics, spatial correlograms, Theil-Sen trend estimation, Mann-Kendall testing, Autoregressive Integrated Moving Average models, Exponential Smoothing State Space models, neural network autoregression, BATS, TBATS, theta forecasting, symmetric mean absolute percentage error model comparison, and report generation. The platform was first applied in Touryare and Mohamud (2026) <doi:10.1007/s43621-026-04022-x> for integrated spatial-temporal forecasting of educational attainment in Eastern Africa toward Sustainable Development Goal 4.
README
# Saylac
**Saylac** is an R/Shiny application for multidisciplinary spatial, longitudinal, time-series, forecasting, and diagnostic analysis of global, national, and regional indicators.
**SAYLAC** abbreviates **Spatial Analysis of Yearly, Longitudinal, and Areal Change**.
The package keeps the earlier SAW-SIMODI-SURAD analytical engine but presents it through a clearer and more memorable CRAN-facing name. It can be used for indicators from education, health, poverty, economy, environment, demography, infrastructure, governance, and other development fields.
## Main features
- Spatial diagnostics for country-level and regional indicators.
- Longitudinal exploration of indicators observed across years.
- Time-series diagnostics using stationarity and trend tests.
- Comparative forecasting using ARIMA, ETS, BATS, TBATS, Theta, NNAR, MLP, and random-walk drift models.
- Spatial mapping of forecast outputs.
- Automated HTML, Word, and PDF reporting.
- Example data for quick testing.
## Published application
The live application is available at:
<https://muse252.shinyapps.io/Saylac_Shiny_App_Ready/>
## Installation
After CRAN acceptance, install with:
```r
install.packages("Saylac")
```
For GitHub development installation, use the repository once it is public:
```r
remotes::install_github("Abdisalammuse/Saylac", dependencies = TRUE)
```
## Launch the app
```r
library(Saylac)
run_saylac()
```
Backward-compatible launch command:
```r
run_saw_simodi_surad()
```
## Example data
```r
saylac_example_data()
```
The app accepts country-year data in CSV format. A common structure is:
```text
Country,Year,Value
Kenya,2020,7.9
Uganda,2020,6.1
```
## Applied reference
The platform was first applied in:
Touryare, M. S. M., & Mohamud, M. A. (2026). Mapping the path to SDG 4 through integrated spatiotemporal forecasting of educational attainment in Eastern Africa from 1990 to 2030. *Discover Sustainability*. https://doi.org/10.1007/s43621-026-04022-x
## Citation
```r
citation("Saylac")
```
## License
GPL (>= 3)
Versions across snapshots
| Version | Repository | File | Size |
|---|---|---|---|
0.1.3 |
rolling linux/jammy R-4.5 | Saylac_0.1.3.tar.gz |
28.9 KiB |
0.1.3 |
rolling linux/noble R-4.5 | Saylac_0.1.3.tar.gz |
50.4 KiB |
0.1.3 |
rolling source/ R- | Saylac_0.1.3.tar.gz |
28.9 KiB |
0.1.3 |
latest linux/jammy R-4.5 | Saylac_0.1.3.tar.gz |
28.9 KiB |
0.1.3 |
latest linux/noble R-4.5 | Saylac_0.1.3.tar.gz |
50.4 KiB |
0.1.3 |
latest source/ R- | Saylac_0.1.3.tar.gz |
28.9 KiB |
0.1.3 |
2026-04-23 source/ R- | Saylac_0.1.3.tar.gz |
0 B |