Statistical comments on “Homeopathy in paediatric atopic diseases: long-term results in children with atopic dermatitis”

To the Editor

We read with great interest a recent article on homeopathy in paediatric atopic diseases.[ ¹ ] The authors investigated the prescribed remedies and the outcome of atopic diseases in children treated with homeopathy at the Homeopathic Clinic of Lucca (Italy), and the long-term outcome of children suffering from atopic dermatitis (AD) after an approximate 8-year period (range 5–10 years).

A major concern is about the data presented in table 5. While no dependency between the complete remission of the symptoms and the Prick/RAST test at the time of the first homeopathic visit, was observed in the asthma patients (P = 0.175), authors indicate that dependency was observed in atopic dermatitis patients (P = 0.029) so patients negative at the RAST or Prick test have more frequently complete remissions compared to those positive at the time of the first homeopathic visit in the long term follow-up. It is questionable that data showed in table 5 supports such affirmation as based on the frequencies observed in the table an exact Fisher test seems to be more appropriate than a Chi-square test and then a non-significant P-value of 0.061 is obtained.

Additionally, the Wilcoxon test is appropriate for analyzing the data from a repeated-measures design with two conditions. Basically, it is designed to evaluate the difference between two treatments or conditions where the samples are correlated. There are at least two requirements that need to be reached to correctly use the test: matched data and the dependent variable should be continuous. It is intriguing how this test was used in table 3. What does exactly represent the provided P-value?

Many readers of the medical literature have neither the time, nor the training, to determine the validity of reported findings. Instead, they rely on the quality of the journal and its review and editorial processes, as surrogate markers of quality. In conclusion, the authors' valuable results concerning tables 3 and 5 could better be used as citable evidence if analyzed with suitable statistical analysis methods.

• References

• 1 Rossi E., Picchi M., Bartoli P., Panozzo M., Cervino C., Nurra L. Homepathic therapy in pediatric atopic diasease: short- and long-term results. Homeopathy 2016; 105: 217-224.