**Matt's Stats n stuff » R**, and kindly contributed to R-bloggers)

Following on from some of my earlier posts, this is purely about, hopefully, saving some other people some time in putting this together. Height z-scores are required to then calculate the blood pressure z-scores. The CDC (Center for Disease Control and Prevention) have (growth) charts available for using an LMS Box Cox transformation to calculate age and sex specific z-scores. These are available here. Blood pressure z-scores are calculated by a different method which is published by NIH (National Institute of Health). A pdf (307KB) containing the method is available here.

These scripts have information in the first few rows which explain a bit about how the variables are required to be set up. These scripts could be made a lot more efficient, however I’ve tried to keep them clean so those using them can (very) easily follow what is going on, and efficiency for something straight forward like this shouldn’t be an issue no matter how large the dataset.

http://www.fileden.com/files/2010/9/21/2974895//child_height_zscore_v0.9.r

http://www.fileden.com/files/2010/9/21/2974895//child_bp_zscore_v0.92.r

NOTE: Age is rounded down, as in the charts are every month on the half month (24.5, 25.5, 26.5 etc) so a 3 year old is 36 months, half way between 35.5 and 36.5. In that instance the values for 35.5 are used in the calculation.

I do aim to one day, hopefully soon, put all these functions together into 1, including BMI (indicator and z-score), height (percentile and z-score), waist circumference (percentile and z-score) and blood pressure (percentile and z-score), with options for rounding and what not.

**leave a comment**for the author, please follow the link and comment on his blog:

**Matt's Stats n stuff » R**.

R-bloggers.com offers

**daily e-mail updates**about R news and tutorials on topics such as: visualization (ggplot2, Boxplots, maps, animation), programming (RStudio, Sweave, LaTeX, SQL, Eclipse, git, hadoop, Web Scraping) statistics (regression, PCA, time series, trading) and more...