I'm fairly new to statistics in general and R specifically and am taking a biophysics course which uses both. My project is to determine trends in temperature and precipitation for my region, using daily measurements from a single monitoring station. I have daily values for Ave. Temp, min, and max, as well as precipitation. From what I have found in my research it seems like ARIMA may be the most effective option available (RHtestV4, etc. don't seem to be available to the public). Would you recommend using ARIMA modeling or is there another option available?
I've tried linear regression but even going to yearly means, there is still too much variance to obtain a decent trend line. Any information or tips would be immensely appreciated.
Thank you.
Notice a very small value at period 126 (11/2011). The ARIMA model that was automatically developed for the output series (taking into account the effect of the two X's AND the effect of Pulses and Seasonal Pulses ) was (1,0,0)(1,0,0) 
. Note that if one doesn't or didn't take into account both of these possibly needed components the automatic arima simply may not be useful. Automatic arima that assumes no Pulses, no Level Shifts, no Seasonal Pulses and no Local Time Trends and subsequently develops very poor model suggestions ( as in your case ! ) . The actual/fit/forecast graph yields very good fitted values and very reasonable forecasts. 
A comparison of the actual and cleansed values further clarifies the need for anomaly detection. 
. The forecasts for the next 12 period is quite reasonable. 
I believe that the prime culprit in your bad forecasts is the naivety in believing rather than challenging observations. Accountants believe the observed data while statisticians challenge the data for homogeneity/consistency. The spurious values in your output series ( unaccounted for by the two X's AND/OR the auto-correlative structure within the data led to a bad ARIMA model identification and subsequently bad forecasts premised on using the actual data. The anomaly at 11/2011 leads directly to a bad forecast as the observation at 11/2011 is not part of the normal process and needs to be investigated. It is important to investigate the possible causes for the anomalies to suggest "newly found/discovered cause variables BUT at a minimum unusual values need to be neutralized so that other parameters are robustly estimated . AUTOBOX ( as a default ) uses the adjusted value for 11/2011 and other anomalies in the early part of 2012 as the basis for the forecasts. This assumption is easily reversible via a user-selected menu option which would then use the actual rather than the adjusted value . The spurious high forecasts are probably based on the unusually high (untreated !) values in the early part of 2012 (Jan and Feb ). Hope this helps !
Best Answer
I think it can. Campbell & Diebold (2005) use an ARX-GARCHX model for point and density forecasting of daily average temperature in Atlanta, Chicago, Las Vegas, and Philadelphia.
They compare their forecasts with a few competitors, the best among which is the forecasts from Earth Satellite (EarthSat) corporation which are used to settle temperature-related weather derivative products traded on the CME. In the end, ARX-GARCHX never beats EarthStat, but still looks quite well considering that the model is rather simple (conceptually -- and especially computationally) as compared to models used by professional weather forecasters.
Point forecasts: ARX-GARCHX does worse than EarthSat forecasts in 1-4 day horizons, but already in 5-8 day horizons the difference in forecast accuracy between the methods is not statistically significant. Beyond 8 days, ARX-GARCH does roughly as well as the EarthSat forecast.
Density forecasts: No comparison between EarthSat and ARX-GARCH (?).
References: