One problem I have with the first graph from a purely technical point of view 
is 
that the number of horizontal data points far exceeds the resolution I used for 
the plot.  So, the data as shown has been filtered by the underlying plot 
routines.

Here is a plot where the data actually fits the resolution:

http://www.jsoftware.com/jwiki/Scripts/WeatherPlot?action=AttachFile&do=get&target=rochester2005temp.png

I'm not if either plot tells me much about a phenomenon that most likely is 
global and may be better analyzed on a scale of centuries.

--
David Mitchell

On 1/7/2010 16:14, Björn Helgason wrote:
> Well your first graph looks interesting and it gives a picture of big
> variation of temperatures.
> So if you want to present any trend out of the data it needs to be
> treated with seasonal adjustments.
>
> Series are made up of four components:
> St: The Seasonal Component
> Tt: The Trend Component
> Ct: The Cyclical Component
> It: The Error, or irregular component.
>
> One way of looking at such data is take each daily value and compare
> that value with the average value for that day
>
> One scary thing about the discussions about heat measurements and
> trends over time is that the researchers have been manipulating the
> data to fit their interests.
>
>
>
>
> 2010/1/7 David Mitchell<[email protected]>:
>> Yes, the second data set is the minimum high and minimum low temperatures for
>> yearly intervals.  It is an extract from the original data.
>>
>> --
>> David Mitchell
>>
>> On 1/7/2010 13:41, Björn Helgason wrote:
>>> The Y scale in one graph goes from -20 to +100 and so do the curves
>>> The Y scale on the other goes from -20 to +20 and the curves therefore
>>> not the same
>>>
>>>
>>> 2010/1/7 David Mitchell<[email protected]>:
>>>> It may depend on how one looks at the data:
>>>>
>>>> http://www.jsoftware.com/jwiki/Scripts/WeatherPlot?action=AttachFile&do=get&target=rochestermintemp.png
>>>>
>>>> ;)
>>>>
>>>> --
>>>> David Mitchell
>>>>
>>>> On 1/7/2010 9:23, Björn Helgason wrote:
>>>>> Looking at this data it is nothing that says there is any general
>>>>> warming going on.
>>>>>
>>>>> If anything it looks like it is getting cooler.
>>>>>
>>>>>
>>>>>
>>>>> 2010/1/6 David Mitchell<[email protected]>:
>>>>>>
>>>>>> Here is one example of what I find useful with J:
>>>>>>
>>>>>> http://www.jsoftware.com/jwiki/Scripts/WeatherPlot
>>>>>>
>>>>>> --
>>>>>> David Mitchell
----------------------------------------------------------------------
For information about J forums see http://www.jsoftware.com/forums.htm

Reply via email to