With new information, it is evident that there is a need for new methodologies for precision dairy (PD) data analysis. Dairy producers have a variety of PD technologies available to them, which creates the need for investment analyses. This study serves as early work in data valuation of new information streams that these technologies collect. Academics need experience with these new data sets and potential methodologies to contribute to producer-targeted recommendations. The objective of this case study is to investigate the complexities of these data intensive herd records. This initial work has provided early evidence that new PD technology can inform herd management decisions at the individual cow level. This data starts in June of 2014 and extends through July 2015, where daily and hourly data were collected from wearable technology on the herd at Coldstream, the University of Kentucky research farm. A quantile regression technique was applied to the unbalanced panel data set, where the functional form was: Daily Milk Yield = β₀ + β₁ Days in Milk + β₂ Body Weight + β₃ SCC + β₄ Eating Time + β₅ Steps + β₆ Resting Bouts + β₇ THI This analysis separates the herd into 3 quantiles: the 25th, 50th, and 75th percentiles. Sorting the data by lactation stage and lactation number isolates the effects of the production variables for each category. The results indicate that production variables have different effects on high performing cows as compared with the same variables’ effects on low performing cows. Body weight for example, is 0.02 and 0.04 lbs higher than the 25th percentile in the 50th and 75th quantile respectively, at the 1% significance level. Days in milk findings reveal that cows in the 75th percentile have coefficient magnitudes 0.03 and 0.05 lbs/day higher than cows in the 25th percentile. This small but significant(all at the 5% significance level) finding reiterates what the literature has documented about days in milk, but reveals marginal effects in more specific cow groups.The coefficient sign (±) of variables such as steps taken, resting bouts, and THI, were also found to change across stage of lactation. The successful application of this technique will allow finer detail to be taken with the model specification, and thus better herd management based off this precision data.