Myth: Global temperature data is inaccurate and/or too sparse to be able to establish a meaningful average temperature over the entire planet. Therefore, any claims of global warming are unfounded.

Fact: NASA has collected and acquired massive amounts of temperature data from various sources, including land-based, meteorological stations, sea surface temperature measurements from ships, and measurements taken from satellites. This data encompasses the entire planet, and is run through a method that is explained on NASA’s website, which results in a statistically significant global average temperature.

The first thing to note here is that there are not many who still make this argument, at least not among climate scientists. The IPCC, in its latest report, actually states that global warming is "unequivocal". Even skeptical scientists, such as Richard Lindzen and John Christy, will admit that we are indeed warming. Their only argument is against the cause of the warming, which is where most skeptics’ arguments have shifted. This should be a clue that there is no argument against warming, however some continue to insist that the planet is not warming.

It seems that the major impetus for the recent resurgence of this argument is a website, www.surfacestations.org, which attempts to question data collection equipment. This is actually a very nifty little trick. This site, launched in June of this year, has established a fairly large following. These devoted followers are commissioned to go out and take pictures of the US meteorological stations. Armed with these pictures, surfacestations.org scrutinizes them, looking for indications that they might be susceptible to a warm bias. This has filled many contrarians’ minds with the idea that the entire temperature data set is flawed, which is ultimately the point. Not surprisingly, there is no mention on the site of existing methods for removing biases from temperature measurements. First, the thermometers are now protected by Stevenson screens (emphasis added):

A Stevenson screen or Instrument shelter is a meterological screen to shield instruments against precipitation and direct heat radiation from outside sources, while still allowing air to circulate freely around them. It forms part of a standard weather station. The screen creates, as near possible, a uniform environment in relation to the air outside. - Wikipedia

Second, NASA’s GISTEMP compares urban stations to rural stations, in an attempt to further remove any potential biases:

We modify the GHCN/USHCN/SCAR data in two stages to get to the station data on which all our tables, graphs, and maps are based: in stage 1 we try to combine at each location the time records of the various sources; in stage 2 we adjust the non-rural stations in such a way that their longterm trend of annual means is as close as possible to that of the mean of the neighboring rural stations. Non-rural stations that cannot be adjusted are dropped. - NASA GISS

Another common argument is that we simply don’t have enough temperature data to be able to compute a global average temperature. This argument usually comes with a map of the world, showing the locations of existing surface meteorological stations. Obviously, on such a map, there are very large areas that are not covered (oceans, deserts, mountain ranges, etc.). However, NASA states that they have sufficient data, dating as far back as 1880:

The NASA GISS Surface Temperature Analysis (GISTEMP) provides a measure of the changing global surface temperature with monthly resolution for the period since 1880, when a reasonably global distribution of meteorological stations was established…We limit our analysis to the period since 1880 because of the poor spatial coverage of stations prior to that time and the reduced possibility of checking records against those of nearby neighbors. - NASA GISS

A major problem for both of these arguments is that they only focus on land-based temperature readings. This is because there is a preponderance of evidence in favor of global warming outside of those temperature measurements, which are completely ignored by these objections. In order to truly call global warming into question, one would also have to prove satellite data, borehole analysis, glacial melt, sea ice melt, sea level rise, proxy data, and rising ocean temperature to be flawed.

UPDATE: A new instance of this questioning of temperature data occurred when NASA made some small corrections to data at the turn of the millenium, thanks to a tip from Stephen McIntyre from Climate Audit. This was a good tip, and NASA’s data is now more accurate for it, but some skeptics have tried to misrepresent it as proof that NASA’s temperature data is faulty. Recently, Fox News provided an excellent example of this misrepresentation:

On Special Report, Jim Angle reported that NASA was forced "to admit it was wrong when it said that 1998 was the hottest year on record" and that NASA "now says 1934 was the hottest year, followed by 1998, then 1921." But Angle did not inform viewers that NASA’s revision affected annual temperature rankings for the United States only; it had no effect on the annual global temperature rankings. - Media Matters

As the fine folks at Media Matters pointed out, while the change did result in 1934 topping 1998 as the hottest year in the US, it had literally no effect on global temperature trends, and actually even a very miniscule effect on US trends. Looking at the global temperature graph below, one can see that the global warming trend is still very much intact: