Introduction:
The study explores the relationship between chess practice and mathematical skills. The research, focused on the Colegio Comunal Orquídeas in Bogotá, seeks to establish whether chess can be an effective tool for improving mathematics achievement. Several previous studies support the idea that chess can benefit cognitive and mathematical development, as shown by research by Paniagua (2017) and Figueroa et al. (2023).

Objectives:
The main objective is to analyze the correlation between chess practice and the development of mathematical skills, using eleven-year historical data.

Methods:
The Vector Autoregressive (VAR) model was employed to analyze the relationship between chess practice and mathematics performance. Chess, mathematics and reading comprehension data were collected from Colegio Comunal Orquídeas. The VAR model allows us to examine the joint dynamics of these variables.

Data and Analysis:
Data spanned eleven years and included chess, mathematics, and reading comprehension scores. Descriptive statistics were evaluated and time series were tested for stationarity using the Augmented Dickey-Fuller (ADF) test. The results showed that the math and chess series are stationary, while the reading series is not.

Correlation:
A very strong correlation (0.917) was found between chess scores and math scores, and a strong correlation (0.768) between math and reading scores. The relationship between chess and reading comprehension was also significant (0.807).

VAR model:
The selected VAR model (with 2 lags) for the variables chess and mathematics explained 96.19% and 97.12% of the variability in these variables, respectively. Instantaneous causality was observed between chess score and math grades, indicating an immediate effect of chess on math.

Projections and Results:
The model projections suggest that chess scores and math grades will increase in the future. The confidence interval for the chess score is 3.71 to 3.88, and for the math grades, 4.72 to 4.87.

Normality and Homoscedasticity Tests:
Tests were applied to evaluate the normality and homoscedasticity of the model residuals. The results indicated that the residuals could follow a normal distribution and show homoscedasticity.

Conclusion:
The study confirms that chess practice is strongly correlated with mathematics and reading achievement. Although no evidence of Granger causality was found, instantaneous causality was detected. Projections suggest future improvements in both chess and mathematics.

Keywords: Chess, correlation, mathematics, education and time series.