Halifax -1.9% MoM, -17.5% YoY -21.3% from peak.

Sir_Humphrey

Really2 wrote: »

The only problem is where they take the figures from.
There are more than 1000 towns in england alone so demographic can have a big bearing and a low sample could easily skew the figures.
(not a professional statistician but I have to work out a lot of anomalous data and what can spike things in my job to provide accurate reporting )

1000-1500 is not a small sample. Sample sizes above that number add little to accuracy. Most opinion polls have a sample of about 1100. Non-random variations are taken care by weighting (such as mix-adjustment).

EDIT: I should point out that all these MoM figures have confidence intervals (roughly meaning margins of error).

Really2

lostinrates wrote: »

I'm neither fish nor fowl, bull nor bear.:o

Not again, you have got to stop this chicken.:D

lostinrates

Really2 wrote: »

Not again, you have got to stop this chicken.:D

I threw in the chicken reference for you. I know you like a nice chicken.

Thrugelmir

Really2 wrote: »

The only problem is where they take the figures from.
There are more than 1000 towns in england alone so demographic can have a big bearing and a low sample could easily skew the figures.
(not a professional statistician but I have to work out a lot of anomalous data and what can spike things in my job to provide accurate reporting )

Llloyds\HBOs have around 30% of the mortgage market currently. So the Halifax price index is probably a fair representation of market movement.

As has been mentioned before this is based purely on mortgage advances so auction sales and cash sales would have effect of pushing overall prices lower.

The Nationwide index is based on a different methology and is weighted to type of property.

neas

mitchaa wrote: »

You should be using Q1 2007 so i'll let you off;)

I would've bought Dec 2007 ... had i not 'thought straight' :P.

I tried to make it like your sbut couldnt open the Q1 2007 one.

Really2

Sir_Humphrey wrote: »

1000-1500 is not a small sample. Sample sizes above that number add little to accuracy. Most opinion polls have a sample of about 1100. Non-random variations are taken care by weighting (such as mix-adjustment).

As I said this is not an opinion pole you could ask a 1000 people in two cities there political allegiance and get a close figure of the population.

If you did the same on houses it would be wildly inaccurate.

you cant use opinion method on financial reporting.
The bigger the sample the more accurate.

Put in simple terms.

To work out a companies turnover I could use 10% of there invoices and X them by 10 to get the company turnover.

Would I? no way I would be a dead man.

Financial data analysis is allways the most accurate when you have the most figures to hand.

Especially looking on a national level 1000 would only cover the price of 0.0004% of accommodations in the UK. (not to mention the different types flats, terace, semi, detached etc)

In financial terms it is like picking out 1 invoice of 25,000 to determine a companies turnover.;)

Really2

Thrugelmir wrote: »

Llloyds\HBOs have around 30% of the mortgage market currently. So the Halifax price index is probably a fair representation of market movement.

As has been mentioned before this is based purely on mortgage advances so auction sales and cash sales would have effect of pushing overall prices lower.

The Nationwide index is based on a different methology and is weighted to type of property.

That was not what I was debating it was if 1000 sales would be acurate of the UK market.

Sir_Humphrey

Really2 wrote: »

As I said this is not an opinion pole you could ask a 1000 people in two cities there political allegiance and get a close figure of the population.

If you did the same on houses it would be wildly inaccurate.

you cant use opinion method on financial reporting.
The bigger the sample the more accurate.

Put in simple terms.

To work out a companies turnover I could use 10% of there invoices and X them by 10 to get the company turnover.

Would I? no way I would be a dead man.

Financial data analysis is allways the most accurate when you have the most figures to hand.

Especially looking on a national level 1000 would only cover the price of 0.0004% of accommodations in the UK.

In financial terms it is like picking out 1 invoice of 25,000 to determine a companies turnover.;)

For a nationwide picture, 1000-1500 is a large enough sample to get an accurate measure. You are incorrect about opinion polling, if those cities were Glasgow and Manchester you would not get an accurate picture, but a sample of 1000-1500 is enough to smooth out those issues (to about 95% confidence).

stephen163

A sample size of 1000 is too small but they compensate for this by stratifying and weighting. Statistically, it is true that the more samples you get the more accurate your data will be, however, once you pass a certain sample size, the gains get smaller and smaller so in practice, a sample size of a small fraction of your population is all that is required to satisfy a certain confidence interval.

neas

I have to laugh at SKY news broadcasting:

House prices in the UK fall by 1.9% during March, showing signs that the market may soon stablise.

Riiiiight... so they fall at almost 2% (higher than the average drop month on month)... and the logic is its showing signs of stopping? Wouldny signs of stopping be a 0.9% then a 0.5% then a 0.2% then a 0.1% fall etc etc?

Not just a constant fall. Seriously these guys are full of doo doo..