Compute PageRank yourself - Which OSE metrics as input
-
Hi,
we're running a project here where we try to optimize our internal link structure by computing the PageRank ourselves given your existing link graph. Right now we weight all pages the same, which is kind of incorrect given that quite a number of our pages have external links, hence have more LinkJuice.
We'd now like to include a weight that respects the external link power to a page. Anyone got suggestions OSE metric would be good? I was thinking of Page Authority, but I assume this is computed by taking both external and internal links into consideration.
Alternatively I could use sum all PageAuthority values of inlinks to a certain page, but as Page Authority seems exponential, this seems to be the wrong thing.
Anyone out there you who tried the same before?
Cheers,
schuon -
So you'd say the best approximation of a page's link power is page authority?
I would say Page Authority is a more meaningful metric and it is readily available for you. PA is extremely useful for competitive analysis when you are comparing your client's web pages with other ranking pages.
A discussion I would recommend reading: http://www.seomoz.org/blog/what-is-pagerank-good-for-anyway-statistics-galore
-
Hi Ryan,
thanks for your reply! First off, I am aware I won't be able to compute the PageRank, rather my little own approximation of it. Basically OSE does the same (I guess they also tweaked the algorithm quite heavily).
Purpose being to optimize internal linking / link juice distribution. With Page Authority I can't preview the effects of changing internal links.
So you'd say the best approximation of a page's link power is page authority?
-
May I ask why would you go to such incredible effort?
You can use Page Authority along with other metrics which are computed for you.
Even if you perfectly computer PR for your page, it is a meaningless number. The PR you compute for a page will not match the PR Google computes for the same page. Google makes determinations as to whether a link should be considered, discounted entirely (such as link farms), or partially weighted based on their internal guidelines. Google also sees many links that OSE does not, so you would need to use Google's data for the page, preferably from WMT.
The PR formula is copyrighted by Stanford, licensed by Google and then tweaked. There are competing theories on numerous aspects of how PR is actually computed. Does PR drain for each sub-folder encountered and if so by how much? Do sites in Dmoz get a PR boost? Do brands get a boost? etc.
If you compute PR for a page, you can call is "Schuon's PR". It will be a number that will exist for you and you alone based on which links you used, how you counted those links, and how you adjusted for other factors.
There are numerous pages discussing the topic but here is one: http://michaelnielsen.org/blog/lectures-on-the-google-technology-stack-1-introduction-to-pagerank/
Got a burning SEO question?
Subscribe to Moz Pro to gain full access to Q&A, answer questions, and ask your own.
Browse Questions
Explore more categories
-
Moz Tools
Chat with the community about the Moz tools.
-
SEO Tactics
Discuss the SEO process with fellow marketers
-
Community
Discuss industry events, jobs, and news!
-
Digital Marketing
Chat about tactics outside of SEO
-
Research & Trends
Dive into research and trends in the search industry.
-
Support
Connect on product support and feature requests.
Related Questions
-
Is there a way to filter all computers on a specific IPv6 network in Google Analytics?
Is there a quick way of filtering the IP addresses for all the computers on a network that's using IPv6? I want to filter out visits to our websites from the devices on our office network, but each computer (and phone and tablet) seems to have a different address. It _looks _like they all start the same way, though. One computer is xxxx:xxxx:xxxx:xxxx:aaaa:aaaa:aaaa:aaaa, another is xxxx:xxxx:xxxx:xxxx:bbbb:bbbb:bbbb:bbbb, my phone is xxxx:xxxx:xxxx:xxxx:cccc:cccc:cccc:cccc, etc. Does this mean that xxxx:xxxx:xxxx:xxxx is the address for our network as a whole, and I can just set up a Google Analytics filter for "IP addresses starting with..."? Or would doing that also filter out hits from, like, every visitor within a 20 mile radius of our office? If I need to simply put in the individual addresses for each and every device, I will. I'm just hoping it doesn't come to that. Thanks!
Reporting & Analytics | | BrianAlpert780 -
Google Analytics Page Metrics and Redirects
Hi All- Context: A site has been redesigned. Pages were renamed in the process. Problem: It's very hard to compare before and after metrics because the page URLs are not the same. Question: Anyone know how to do this in Google Analytics? I'm hoping there's some simple trick I just don't know about. D
Reporting & Analytics | | DonnaDuncan0 -
How to track link building? What metrics?
I'm an SEO newbie (my main roles are front-end designer and content manager).
Reporting & Analytics | | RSGregC
I've been managing our company's effort to generate links. In the past, trying to develop relationships has gone nowhere. As a result, we're currently mostly creating good content ourselves and posting it on Web2.0 sites (weebly, etc.) and linking back to our site, and then using UAW (unique article wizard) to create a second tier of links to those links. We've been doing this for a while, and our traffic from SEO is going up - but we don't really know how to track our work. Can you please
a) give your opinion about our approach, and
b) tell me which metrics we should be using, and which tools for these metrics? Thank you so much
Greg0 -
Distribution of SEOMOZ Ranking Metrics across all Monitored Websites
Hi, I'm looking into building a tool which would incorporate SEOMOZ ranking metrics and I have a few questions with regard to the ranking data which will help me develop it correctly. I have done a few searches, for the information but haven't found an answer to these questions on seomoz - if they exist somewhere then I would be grateful if you could point me in the right direction. 1/. When looking at the values of metrics such as MozRank and DA, is there any information on how this values are distributed amongst the ranked website - EG The mean / median values of DA and MozRank etc of all websites monitored is X & Y . If there were any distribution graphs for these values then even better. 2/. Along the lines of the above - are there any online resources showing similar information for google PR? 3/. What is the calcuation used in the scale of MozRank and DA - ie We have a scale of 1-10 for these values - be we also know the scale in not linear but logrithmic - ie Double the Links of a DA 5 website and you would not end up with a DA 10 website - so what is the calculation which defines the scale. A WBF about google PR by Rand indicated that a value of between 8-9 is used in Google PR - but what about the values used for DA and MozRank etc? Many thanks for your help
Reporting & Analytics | | James770 -
Google Search Results inconsistent from different computers
Recently after some optimization activities - I do not see much movement in search rankings - my client is seeing the results on page 1 position 3 and I see page 2 for the same keyword. How does Google change ranking based on past searches and how can I get an accurate picture of what the actual rank is?
Reporting & Analytics | | devonkrusich0 -
Social Shares Metrics?
I notice in the OSE Link Metrics the reporting of Social Shares. The total shares do not include the Facebook Likes. What I'm wondering is what does this mean? Do Shares count more than Likes? Are Likes not counted by Google. What about LinkedIn Shares, why are they not being reported on? If Google is now putting more emphasis on Social where is the best use of effort? Getting Likes, Getting Shares only Twitter and Facebook and Google+?
Reporting & Analytics | | underthesun8080 -
RE: Google Analytics keywords metric and appropriate keywords
Greetings, When running Google Analytics' keyword report, I see that the over 85% of the top 100 keywords used to find us include a word in our name (Eagle's Nest Foundation and Camp -- with "eagle" or "eagle's nest" being the most frequent) or the name of one of our programs. Does this mean that most folks searching for summer camps in North Carolina already know about us and that we therefore need to optimize for broader keywords, to cast a wider net for folks who don't already know about us? Thanks, Dave
Reporting & Analytics | | DMoff0 -
GA custom reports involving pages and goals - what are the metrics saying?
Hi, All! I would like to create a custom report that will enable me to see which of my pages are contributing to goal completion on my site (so I can then optimize the pages that are contributing the most, with maximal ROI for the optimization investment). If I make the dimension "page/page title" and the metric "goal X completions" - which would make sense - what exactly are the numbers that I am seeing telling me? Is it how many times a person started the goal funnel from that pages (meaning every goal would appear only once and there be no overlap)? That doesn't appear to be the case with the numbers, because the headline in the main "Goals" section tells me I have 30 goal completions for that goal, for example, but the headline in the custom report (which is adding up all the numbers) is, say, 100. Or does it mean the number of times that this page was ever in the navigation path of someone who ended up completing a goal? Then the same goal would be counted multiple times, for each page in the path. Additionally, I see this strange thing on some of my reports where the actual funnel pages appear as contributing towards goals, which I guess makes sense, but again the numbers don't match up. If the goal was to get to page B, and the funnel was A->B, and there were supposedly 30 goal completions, my custom report says that A gave 28 goal completions and B gave 25. Anyone know for sure - or through testing - what the case is with all these things? Any explanations will be much appreciated!
Reporting & Analytics | | debi_zyx0