Discover XiTi 7.5

Web analytics
News | Contact |
Home > Internet users behaviour > 04/24/2008   

Website traffic: September 2008 is looking good…

The first quarter 2008 was more dynamic than the first quarter 2007 in terms of website traffic. According to our forecasts, this trend should continue in September 2008...
  • Study conducted from July 2000 to March 2008
  • Perimeter of 239,888 websites
The slowdown in growth observed in 2006 and 2007 seems to be over in early 2008

The table below shows the rates of evolution in website traffic for each first quarter (January to March) from 2002 to 2008.

On a like-for-like perimeter in terms of website numbers, we observe a rate of evolution in website traffic in the 1st quarter 2008 that is twice as high as the 1st quarter 2007 (but remains lower than the earlier first three quarters).

Evolution of website visits, after fluctuating between +15.7% and +28.1% in the period January-March in 2004, 2005 and 2006, fell to +4.8% in the first quarter 2007 and then increased to +9.6% in the first quarter 2008:


This progress in the rate of evolution of website visits measured during the 1st quarter 2008 compared to the 1st quarter 2007 can be observed each month:

  • Evolution January 2008: +9.3% (compared to +5% in January 2007), as we observed in our survey Website frequentation: a promising start of the year 2008…,

  • Evolution February 2008: +12.4% (compared to +5.3% in February 2007, knowing that this change should be looked at in perspective because February 2008 had 29 days, compared to 28 days in 2007),

  • Evolution March 2008: +7.5% (compared to +4.4% in March 2007).


According to our forecasts, visits should increase by around 13% in September 2008 compared to September 2007

The graph below shows the evolution of the website traffic index for visits recorded from September 2001 to March 2008, and our predictions for this index from April to September 2008.

According to our prediction model, for 100 visits recorded in September 2001, 254 visits should be recorded in September 2008.


Thus, the rate of evolution of website visits should be +12.7% between September 2007 and September 2008. This trend is clearly more positive than in September 2007, which experienced a noteworthy seasonal low (see our survey "Website Frequentation: prediction until January 2008"), or even than September 2006.


The slowdown in growth of website traffic observed in 2006 and 2007 seems to be over in this first part of 2008. Thus, the rate of evolution of visits in the 1st quarter 2008 is twice as high as in the 1st quarter 2007, even if the level of previous years has not yet been reached.

According to our forecasts, this trend should continue until September 2008…

Check out XiTi Monitor in the coming months to follow the evolution of website traffic.

These analyses are broken down by sector of activity: if you want to compare the performances of your website with your competitive environment, do not hesitate to go to the “Contact us” section to ask for a personalized study.


The indicator used for this study, measuring the number of visits recorded based on a constant perimeter of sites, reveals the evolution of website activity.

In the absence of official data regarding the number and composition of existing websites, it is not actually possible to present an indicator that reflects the evolution of Web users’ total Web consumption.

In this study, we looked at website traffic. This covers the evolution in audiences generated by a fixed number of websites. The series of data successively integrates daily rates of evolution, calculated on a like-for-like perimeter on all sites audited by XiTi. Thus, the evolution of this indicator does not reflect the evolution of the XiTi perimeter, but website arrivals and departures within this perimeter are integrated in the calculation of our indicator.

The audience registered on sites within the XiTi perimeter very quickly revealed the existence of seasonal effects that processing methods make it possible to extract.

Tools adapted* to processing chronological series enabled us to break down this monthly series. The components are:

- The trend of the series which represents long-term evolution of the series.

- The seasonal component representing yearly or, in our case, monthly fluctuations that are repeated more or less regularly from year to year. It reveals phases of growth and recession.

A moving average provides an adjustment of the monthly audience; it corresponds to an estimation of the global trend. The moving average necessitates, at time t, measurements of the series at time t, as well as measures around t.

In our study, a moving average of 13 terms, symmetric centered on t, is adapted in order to measure the annual trend of a series of monthly data. To measure the moving average at month m, measurements from month m, month m-1 to m-6, and month m+1 to m+6 are required. This explains the necessity to estimate this moving average at the end of the period. Thus, for example, if we take the month of March 2008, when the months from April to September have passed, the calculated moving average that replaces the current estimation may bring about a rectification of the seasonal effect.

When data required for calculating the moving average are incomplete, the yearly trend is an estimation by successive linear regression, based on the hypothesis of almost stable evolution of the yearly trend in the short term.

Lastly, after estimating the long-term trend and extracting seasonal effects, two successive steps make it possible to make predictions through to September 2008:

- Estimation, for the period of prediction, of the yearly trend by successive linear regressions.

- Re-injection of monthly seasonal effects to estimate the series for the period of prediction.

*Non-parametric deseasonalization method.

En savoir plus :
© 1997-2019 AT Internet/XiTi - All rights reserved  | FR  | EN  | ES
deg_gauche deg_droit