# Regression and ANOVA for multiple site comparison of weather data?

I have already asked a similar question in the past and received the advice to ask more specific in the 'ANOVA community'.

My experimental design looks like this:

Temperature is measured at several sites over a period of six month each year. Each site consists of two plots (farmland) which are treated differently (Plot1=Control and Plot2=Treatment applied). Data is logged by three loggers every 15 minutes and averaged to daily mean values for data analysis.

So let's say I have n sites with two treatments each and I want to see if there is a difference in temperature (min, max, mean) independently from the site. Additionally the sites can be grouped (within-site compared plots are always in the same group).

My two-tailed H0 is, that regardless of the site or year Control shows different temperatures than the Treatment.

More detailed: for group x Control shows higher temperatures, regardless of site or year effects, than the treatment (one-tailed) & for group y Treatment shows higher temperatures regardless of site or year effects.

Which approach would I have to choose?

Here is a dummy data set of three sites with data for a few days in the month of june. Data structure equals my original data:

Edit: here's the dummy data table Password: CfCWQq67

• Can you please show your data as text, so it can be easily copied into some program, and NOT as an image? Oct 20 '20 at 1:40
• The data has the form of panel (repeated measurements) data. You can start with plotting the data as such (against time on x-axis). Show small panels for each site, with the two treatment groups with different colors. Oct 20 '20 at 3:14
• Thanks Kjetil B Halvorsen, I have added a link to the .csv-file below the image. I have already plotted the daily mean values, the differences in mean values, the min and max values (and their differences), looked for extreme values, etc. But I want to go a further step (away from descriptive) to stochastic analysis.
– Timo
Oct 20 '20 at 7:26