Skepticism is warranted here. What standards are the study's authors using to determine liberalism and conservatism? If someone votes to place restrictions on the Patriot Act, does that indicate a liberal opposition to the empowerment of intelligence agencies viewed as conservative or even fascist? Or does it indicate a traditionally conservative, constitutional constructivist opposition to increasing the powers of centralized government? Is a vote to allow states to legalize marijuana a liberal vote for countercultural values? Or is it a conservative vote for states' rights?
The link provided by parados is well worth reading. Here's the key takeaway:
"The Martin-Quinn method keeps track of only one thing: whether a Justice voted to affirm or reverse in a case. The method does not pay attention to what the case was about; the method itself has nothing to do with politics or ideology (or, for that matter, law). All it knows are things like this: in the first case decided last year, Justices A, B, C, and D voted to affirm and Justices E, F, G, H, and I voted to reverse. In the second case last year, Justice A voted to affirm and all the others voted to reverse. And so forth for every case fed into the model, nothing more. The authors’ findings are all derived from analysis of that data."
This is enough in my mind to invalidate the political inferences (liberal, conservative) made from non-political data using apolitical statistical methods.
All of the sensationalism of the study is tacked on at the end by means of logically unwarranted (or at least unjustified) assumptions, the nature of which are disguised by using graphs and measurements that lend a false air of objectivity while camouflaging weak reasoning with obscure and impenetrable technicalities.
Another point, which I didn't see discussed in parados's link article, is that shifting voting alliances are fundamentally ambiguous: if known conservatives begin voting more often with known liberals, does that indicate that the former are becoming more liberal, or that the latter are becoming more conservative?
The link does, however, point out that if the court moves to the right as new members replace retired ones, while preexisting justices remain ideologically unchanged, they end up being relatively "more liberal" by comparison.
All of this shows how important it is to look behind conclusions and to independently evaluate both data and methodology.