The phrase "ad hoc correlation" is correct and usable in written English.
It can be used in contexts where a correlation is established for a specific purpose or situation, often without a broader application.
Example: "The researchers found an ad hoc correlation between the two variables during the study, but further analysis is needed to confirm its validity."
Alternatives: "temporary correlation" or "specific correlation".
We remark that it is easy to be misled by ad hoc correlations with small databases.
During feature ranking using the ROC FS method, we applied an ad hoc cross correlation technique that incorporates correlation information into the ranking procedure so as to avoid the existence of correlated features into the best subset.
After a preliminary filtering procedure, mainly devoted to remove all the influences due to meteo-climatic parameters and/or cultural electrical noise, a software developed ad hoc to study the possible correlation between anomalous patterns in electrical signals and local microseismic activity was employed.
Using IHFST, the relevant features are selected according to the distance evaluation criterion of DET, and the redundant features are then further suppressed based on the Pearson's correlation analysis and ad hoc technique.
Finally, the ad hoc technique associated with the mean correlation coefficient is applied to reevaluate the distance evaluation criteria α j, and a feature that is highly correlated with the top informative features will be suppressed or removed.
To compare two AUC measurements with unequal sample size, we used an ad hoc z-test assuming that the correlation between them was 0.5.
In this paper, an improved hybrid feature selection technique (IHFST) that combines a distance evaluation technique (DET), Pearson's correlation analysis, and an ad hoc technique is proposed.
To address this problem, an improved hybrid feature selection technique (IHFST) combining DET, Pearson's correlation analysis, and an ad hoc technique is proposed.
Comparisons with empirical correlations and formulas based on ad hoc models are provided.
It was able to produce a visualization layout with a high correlation to the ARWU score without the need for "ad hoc" weighting of individual attributes.
