Gallup's Jeff Jones responds to my post yesterday suggesting a possible day-of-week effect in the Gallup Daily tracking of the Obama-Clinton race:
We appreciate the interest people have in Gallup Daily tracking data. Your hypothesis of possible day-of-week effects in Gallup’s tracking poll is based on suggestive evidence from Gallup’s published three-day rolling averages. However, looking precisely at the results for each individual day of the week, we find no such day-of-week effect.
The table below shows the results by day of week, consisting of over 36,000 interviews with Democratic voters conducted from Jan. 2 through March 31.
Over the course of tracking, the average levels of support are 45% Clinton, 42% Obama. For any given day of the week, the average is within one point of the overall average for each candidate.
One poster to your site suggested a day-of-the week effect may have been a more recent phenomenon. But even when you look at the data on a monthly basis, where each day of the week occurs only 4-5 times, the same general pattern appears – the average for a candidate on any specific day of the week is within 2 percentage points of the average for the entire month. There is one exception to that, Clinton has had some good Mondays in March, basically every other one, but even with that her Monday average is only 3 points higher than her overall March average.
The possibility of a day of the week effect has come up in relation to prior Gallup tracking data, such as for the 1996 and 2000 elections. We carefully examined those data for evidence of such an effect, and did not find anything to suggest a systematic effect.