# Comparing percentiles of datasets of varying sizes

I am trying to build a simple anomaly detection solution.

I have a dataset with normal observations. It has about a 100 values. I calculate the np.percentile(dataset1) of this dataset.

I have another dataset of new observations which contains about 10 values. I calculate the np.percentile(dataset2) of this dataset as well.

Is it fair to say if the 25th, 50th and 75th percentile of dataset2 are 25%(can be any number based on the level of sensitivity you desire) or more different than dataset1, then the observations in dataset2 are anomalous since dataset1 is suppose to be a dataset of normal observations?