For my third year experiment I'm authenticating whiskey and other spirit based drinks using gas chromatography. From the chromatograms, I get the retention time and peak area but have no way of knowing what chemical those peaks refer to (e.g peak 1: Retention time 5.36mins with an area of 10.9186 Pa/min) each analysis gives me about 10-20 peaks like this. Using SPSS, I need to determine whether its possible to differentiate between the different spirit drinks from the data from the graphs (so that if an unknown spirit was to come in I could identify it). Whats the best way to input this data (the retention time, peak area, spirit type and brand) in SPSS for the LDA, PCA and cluster analysis methods to discriminate the data by spirit type. Its quite clear just by looking at the results which spirit is which as whiskys tend to share the same peaks with each other and those peaks tend to have a similar peak area, indicating they contain similar compounds, which makes sense as they come from the same raw materials while vodkas and gins tend to have only a couple of peaks the same as whiskey. Any help is much appreciated.
OS: Windows 10
SPSS version: 25