Objective: To determine the causal relationship between educational attainment and the risk of allergic rhinitis and (or) eczema using Mendelian randomization (MR) analyses. Methods: This study was a secondary data analysis based on the summary data of genome-wide association studies (GWAS), which involved 293 723 participants (educational attainment) from the Social Science Genetics Association Consortium and 462 013 participants [allergic rhinitis and (or) eczema] from the UK Biobank. Genetic variants that were closely related to educational attainment were identified as instrumental variables. Two-sample MR analyses, including inverse-variance weighted (IVW), MR-Egger regression, weighted median method and weighted model-based estimation, were performed to investigate the causal relationship between educational attainment and the risk of allergic rhinitis and (or) eczema, in which the odds ratio (OR) values were used as indicators. Results: A total of 70 single-nucleotide polymorphisms (SNPs) were chosen as instrumental variables. The MR-Egger regression results suggested that the genetic pleiotropy was unlikely to bias our results (P=0.107). In the univariable MR analyses, IVW regression showed that the risk of allergic rhinitis and (or) eczema was OR=1.044 (95%CI: 1.020-1.069, P<0.001) and OR=1.170 (95%CI: 1.074-1.256, P<0.001), respectively, for the increase in the duration of education by one year or one standard deviation (SD) (3.71 years). In the reverse MR analysis, IVW regression showed little evidence that allergic rhinitis and (or) eczema affected educational attainment (OR=1.020, 95%CI: 0.927-1.023, P=0.683). The results of the weighted median method and weighted mode-based estimation were consistent with the results of IVW. Conclusion: This study suggests that there is a positive causal relationship between educational attainment and the risk of allergic rhinitis and (or) eczema, which means that educational attainment can increase the occurrence of allergic rhinitis and (or) eczema.