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 -
No PageRank Update...Why So Slow?
I've got 100s of new pages over a year old, all with quality content, yet they're all still at PR0. The main index page has a PR score of 4, yet all the other pages of the site are still at 0. They're are all unique and highly relevant pages. Anybody else notice Google's taking longer to rank pages? Why is Google taking so long to update PageRank?
Reporting & Analytics | | alrockn1 -
Can you use an advance segment as a metric or dimension for another advance segment in GA?
I have 3 advanced segments set up: Branded keywords Non-branded keywords (all) irrelevant non-branded keywords. irrelevant non-branded keywords are keywords where the visitor is not ready to purchase. for example keywords including terms such as "ideas" or "how to".. these have generated 0 conversions for us, and I want to track these separately from keywords that have a chance in converting, since the conversion rate between the two groups vary a lot. for the advanced segment "branded" - i listed a listed of keywords pertaining to the company name - using includes, Matching regexp and | (pipe) between keywords for advanced segment "non-branded keywords" - i took the same list and excluded matching regexp | between keywords. **for advanced segments "irrelevant keywords" ** - i took one word as the keyword and used includes, contains, and the keywords.. using OR statement between keywords. pipe doesn't seem to work with the "contains", and only seems to work with "matching regexp". **What i want to do is excluded all items from "Irrelevant keywords" in advanced segment "Non-branded keywords". but i can't seem to exclude based on another custom segment. **nor can I list - [X statement OR (statement y OR statement Z OR statement AB)] any thoughts on handling this logic?
Reporting & Analytics | | S.S.N0 -
Are Click-Through rates & Bounce Rates as Ranking Metrics ?
There are lots of articles around but I would prefer to see what everyone here has to say about it. Are they ranking metrics ( directly or In-directly )? If they are then how to get it right? Can i depend on Google In-page analytic? What is an acceptable Bounce rate for a home page ? What is an average click through rate for your landing page ? thanks
Reporting & Analytics | | conversiontactics0 -
Metrics for guest posting
I have couple blogs willing to publish an article with a backlink to my site. I want to compare them. What SEO metric is the best to use for comparison: Domain Authority or Domain Domain Mozrank or DomainTrust? I want to choose a blog that will give me the most linkjuice
Reporting & Analytics | | Alexey_mindvalley0 -
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 -
Do links with tracking codes pass PageRank?
I have a client that has acquired a link from an influential partner but the partner has set the link up to have clicks tracked within their analytics. Do links like this pass PageRank: Anchor Text
Reporting & Analytics | | SearchEngineRescue0 -
Why is this website with worse metrics performing better on serps?
Hi! I would like to ask if anyone has any ideas on why the second website in this analysis is getting position 2 on google and website 1 is getting position 5: http://www.opensiteexplorer.org/comparisons?site=bonobetfair.info&comparisons[0]=www.bonobetfair.com&=Compare The metrics indicate that the first website is clearly superior in (almost) all metrics. Why could this be?
Reporting & Analytics | | inmonova0