This morning’s Populus poll had topline figures of CON 32%, LAB 37%, LDEM 9%, UKIP 13%. The five point Labour lead is up from Friday’s poll which had the two parties equal on 35%… but both polls are inline with the average lead of 3 points or so which Populus have been showing lately.

I’ve seen it suggested lately that there’s a pattern of Populus producing better figures for Labour in their Monday polls, better figures for the Conservatives in Friday polls. Such a pattern is possible in theory – one can imagine that you might get slightly different respondents from weekend fieldwork than weekday fieldwork – and on the face of it looks like there could have been a bit of a pattern last month. Crunching the data properly though any difference appears to be minimal – the average figures this year for Populus’s Friday polls are CON 33.4%, LAB 36.5%; for Monday polls they are CON 33.1%, LAB 36.9%. Populus’s Monday polls give a Labour lead that’s 0.7% bigger than Friday polls, less than a percentage point.

Meanwhile Lord Ashcroft’s poll shows another big change in Tory support from last week. Toplines are CON 27%(-5), LAB 36%(nc), LDEM 7%(nc), UKIP 17%(+3), GRN 7%(+1). I wrote about the volatility in Lord Ashcroft’s polling a couple of weeks ago here: essentially, there’s no methodological reason for it, nor are the figures actually particularly volatile given the standard levels of variation you’d expect to find. As ever, it’s the underlying trend that counts rather than the individual bits of data that make it up.

A week ago co-incidence spat out three polls with seven point Labour leads within 2 days. This weeks little clump of Monday polls has produced rather more typical polls from Ashcroft and Populus, and a more unusual one from ICM.

Lord Ashcroft‘s weekly telephone poll has topline figures of CON 32%(+5), LAB 36%(+2), LDEM 7%(-4), UKIP 14%(-1). The Conservatives are up five, but it looks like something of a reversion to the mean after last week’s unusual poll that had that the Tories down 6. Full tabs are here.

Secondly is the twice-weekly Populus poll, which has topline figures of CON 34%, LAB 37%, LDEM 9%, UKIP 12%. Tabs for that are here.

Finally there is the monthly ICM poll for the Guardian here, which has topline figures of CON 34%(+3), LAB 33%(+1), LDEM 12%(+2), UKIP 9%(-7!). The narrow Conservative lead looks unusual, but is actually pretty typical of ICM’s recent polls – their last three monthly polls have now shown the Conservatives and Labour effectively neck and neck (a two point Tory lead, a point point Lab lead, now a one point Tory lead). More startling is that sharp drop in UKIP support, down 7 points and into single figures.

The drop in this particular poll is unusually large but it does fit into a broader trend. The expected pattern of UKIP polling around the European elections was for their support to peak after the inevitable burst of publicity following the European elections and then decline again. That’s pretty much happened. Lord Ashcroft’s polls had them peak at 19% just after the Euros, and they’ve now drifted down to 15%. YouGov had them peaking at 17%, now they’ve fallen back to 12%. ICM had them up to 16% after the Euros, now down to 9%. Populus they didn’t really have much of a post-Euro boost for UKIP anyway, only going to up 15%, but in their last couple have had them at 12%. ComRes, Survation and MORI haven’t shown UKIP coming down from their post Euro high yet, but none have polled in July yet… time will tell if they follow the trend.

Two new polls out today, both good for Labour. Populus this morning had toplines of CON 31%, LAB 38%, LDEM 9%, UKIP 14% (tabs here). Lord Ashcroft’s weekly poll has topline figures of CON 27%, LAB 34%, LDEM 11%, UKIP 15% (tabs here).

The Ashcroft poll comes after a poll last week that showed the Conservatives 2 points ahead, and has naturally provoked some comment about volatility. In one sense it’s fair comment – Ashcroft polling has been volatile. In another sense it’s not – Ashcroft’s polling hasn’t necessarily been any more volatile than you should expect, it’s just that we sometimes have slightly unrealistic expectations of how accurate a poll of 1000 people should be!

The standard margin of error on a poll of 1000 people is plus or minus 3 points. However, voting intention figures aren’t based on the whole sample, only on those who give a voting intention – in a phone sample of 1000 that’s typically 500 or so people, giving a margin of error of plus or minus 4 points. I should add that the margin of error is based upon what the margin would be in a pure random sample. This is very much a polite fiction – no voting intention polls are actual pure random samples. Many are from internet panels, even quasi-random phone polls aren’t actually random because of low response rates. Weighting effects would also change the actual margin of error.

Looking at Ashcroft’s nine regular polls to date, the average level of Labour support has been 33%, and all nine polls have been within 2 points of this. The average Lib Dem support has been 8.5%, and all nine polls have been within 2.5% of this. What’s made them look erratic is the level of Tory support, which has averaged 29%, but has varied between 25% and 34% – two of Ashcroft’s Tory scores have differed from the average by 4 points, one by 5 points. This assumes that there hasn’t been any genuine movement in Tory support, when it’s possible there has. Ashcroft’s highest Tory score came in his first poll in mid-May, at a time when ICM also showed a Tory lead and YouGov a neck-and-neck. Ashcroft’s lowest Tory score came just after the European results when UKIP had a post-European election boost.

Bottom line is that while Ashcroft’s polls look erratic, they probably aren’t much more erratic than we should expect from topline figures based on 500 people. There isn’t anything strange about their methodology, nothing odd going on, it’s just the normal limits of how precise polling with a given sample size can be. And it’s a useful reminder of why we shouldn’t read too much into individual polls, and it’s the underlying trend and average that count.