follow CCP

Recent blog entries
popular papers

What Is the "Science of Science Communication"?

Climate-Science Communication and the Measurement Problem

Ideology, Motivated Cognition, and Cognitive Reflection: An Experimental Study

'Ideology' or 'Situation Sense'? An Experimental Investigation of Motivated Reasoning and Professional Judgment

A Risky Science Communication Environment for Vaccines

Motivated Numeracy and Enlightened Self-Government

Ideology, Motivated Cognition, and Cognitive Reflection: An Experimental Study

Making Climate Science Communication Evidence-based—All the Way Down 

Neutral Principles, Motivated Cognition, and Some Problems for Constitutional Law 

Cultural Cognition of Scientific Consensus

The Tragedy of the Risk-Perception Commons: Science Literacy and Climate Change

"They Saw a Protest": Cognitive Illiberalism and the Speech-Conduct Distinction 

Geoengineering and the Science Communication Environment: a Cross-Cultural Experiment

Fixing the Communications Failure

Why We Are Poles Apart on Climate Change

The Cognitively Illiberal State 

Who Fears the HPV Vaccine, Who Doesn't, and Why? An Experimental Study

Cultural Cognition of the Risks and Benefits of Nanotechnology

Whose Eyes Are You Going to Believe? An Empirical Examination of Scott v. Harris

Cultural Cognition and Public Policy

Culture, Cognition, and Consent: Who Perceives What, and Why, in "Acquaintance Rape" Cases

Culture and Identity-Protective Cognition: Explaining the White Male Effect

Fear of Democracy: A Cultural Evaluation of Sunstein on Risk

Cultural Cognition as a Conception of the Cultural Theory of Risk

« The culturally polarizing effect of the "anti-science trope" on vaccine risk perceptions | Main | The logic of reciprocity--and the illogic of empirically uninformed vaccine risk communication »

How are climate skepticism, disbelief in evolution & vaccine hesitancy related?

The dominant theme of ad hoc risk vaccine risk communication warns of a “growing wave of public resentment and fear” that has induced a “large and growing number” of “otherwise mainstream parents” to refuse to vaccinate their children.

As discussed in the last post, this trope is not based on fact: there hasn't been an erosion in immunization rates”; on the contrary, coverage for all recommended childhood vaccines has held steady at 90% (the HHS "healthy person" target) or above for over a decade.

And while there's zero evidence of a " “growing crisis of public confidence in vaccines at present, emphatic assertions that there is one can be shown to induce misunderstandings and confusion inimical to the willingness of people to make voluntary contributions to public goods--like the herd immunity associated with universal immunization.

A secondary theme of ad hoc risk communication is the "anti-science" trope.  This claim links "growing" concern over vaccine safety to disbelief in evolution and skepticism toward climate change, all of which are depicted as evidence of a creeping hostility to science in the general public.

The CCP Vaccine Risk Perception study found this assertion, too, to be both contrary to fact and antithetical to maintaining the existing, broad-based public consensus in favor of universal immunization.

Below is a section of the Report that presents survey evidence on the relationship between vaccine risk perceptions, on the one hand, and climate change skepticism, disbelief in evolution, and science comprehension generally, on the other.  Tomorrow I'll post material relating to the Study's experimental component, which illustrates the potential of the "anti-science trope" to generate cultural conflict over vaccines.

A. Some benchmarks: evolution and climate change, science comprehension and religiosity.  

As emphasized, the aim of the survey component of the study was to evaluate the nature of the general public’s perception of childhood vaccine risks. Is there a shared or dominant affective orientation toward vaccine safety in the U.S. public? Or do childhood vaccines provoke mixed and opposing reactions—and if so, among whom?

Meaningful answers to these questions require an intelligible reference point with which to compare the survey responses. Dispute over universal vaccination laws—provisions that make immunization a condition of school enrollment, subject to medical or religious and in some states moral-objection “exemptions”—are frequently likened to conflicts over acceptance of mainstream science, including the teaching of evolution in public schools and the adoption of policies to mitigate the environmental impact of climate change. Associated with religious, cultural, and political divisions, the intensity and character of these conflicts can be used to help assess the intensity and character of any divisions of opinion observed on childhood vaccine risks.

The study measured study participants’ beliefs about both evolution and global warming. On evolution, subjects responded to an item from the National Science Foundation (2012) “Science Indicators” battery, which is conventionally used to measure science literacy. That item instructs respondents to respond to the statement “Human beings, as we know them today, developed from earlier species of animals.” In line with many public opinion polls (e.g., Newport 2012), 56% of the survey respondents classified this statement as “true,” and 44% as “false.”

On climate change, 52% of the survey respondents indicated that they believe scientific evidence supports the proposition that the earth’s temperature has been increasing in “the last few decades” as a result “of human activity such as burning fossil fuels.” Thirty percent indicated that they did not believe there was “solid evidence” of increasing global temperatures over the “past few decades,” while another 18% indicated that they believed there was “solid evidence” of warming but that the cause was “mostly. . . natural patterns in the earth’s environment,” as opposed to “human activity.” These figures, too, are in line with recent national opinion surveys (Silver 2013).

Irrespective of their responses to these items, however, the overwhelming majority of survey respondents agreed with the proposition that the “health benefits of obtaining generally recommended childhood vaccinations outweigh the health risks” (BALANCE). Eighty percent of the respondents who believe in human-caused climate change agreed with this proposition. So did 81% of those who believe the earth’s temperature has increased as a result of “natural patterns,” and 73% of those who believe the earth’s temperature has not increased in recent decades. Eighty percent of the respondents who believe in evolution and 77% who do not  (a difference smaller than the survey margin of error) likewise indicated that they agree the benefits of childhood vaccinations outweigh their risks (Figure 5).

Study participants also responded to items measuring both their religiosity and their knowledge of and facility with scientific evidence. The former was assessed with a scale that aggregated self-reported church attendance, frequency of prayer, and “importance of God” in the respondents’ lives (α = 0.86). Subjects’ “science literacy” was assessed with 11 items from the NSF’s Science Indicator battery, which is conventionally used to study public understanding of science in the U.S. and abroad (NSF 2012). In addition, subjects completed a ten-item version of the Cognitive Reflection Test (Frederick 2005; Toplak, West & Stanovich 2013), which assesses the motivation and capacity to consciously interrogate one’s views on the basis of available information, a critical-reasoning disposition integral to forming evidence-based beliefs (Toplak, West & Stanovich 2011).

The NSF and CRT items formed a reliable scale (Cronbach’s α = 0.82), which can be interpreted as measuring a “science comprehension” aptitude (Kahan, Peters et al. 2012). Consistent with previous studies (Pennycook 2012, 2013; Shenhav, Green & Rand 2011; Gervais & Norenzayan 2012), there was a modest negative correlation between the religiosity and science comprehension (r = -0.26, p < 0.01).

Religiosity and science comprehension also were meaningfully—but not straightforwardly—associated with the study subjects’ positions on evolution and climate change. Science comprehension was modestly associated (r = 0.28, p < 0.01) with belief in evolution and weakly associated with belief in human-caused climate change (r = 0.10, p < 0.01) for the sample as a whole (including both survey and experiment subjects). But the impact was moderated by subjects’ religiosity: among those low in religiosity, higher science comprehension substantially increased belief in evolution and in human-caused global warming; among those high in religiosity, however, higher science comprehension had next to no impact on belief in evolution and substantially reduced belief in human-caused global warming (Figure 7).

The interaction between religiosity and science comprehension is not surprising. Science literacy and critical reasoning dispositions have been found to magnify cultural and ideological predispositions toward global warming (Kahan, Peters et al. 2012; Kahan 2013b). So it stands to reason that they would have the same impact on predispositions associated with religiosity, which plays a comparable role to shared cultural and political outlooks in the web of social relationships that orient individuals toward what is known by science. “Belief in evolution” is not a reliable indicator of either a scientifically literate understanding of evolutionary mechanisms (Schtulman 2006; Bishop & Anderson 1990) or the species of science literacy measured generally by the NSF Science Indicators. Rather, how one responds to the question “do you believe in human evolution” indicates a form of identity that features religiosity (Roos 2012). It is perfectly plausible that the significance of “disbelief” in evolution as an expression of personal identity would be unaffected by science knowledge—or possibly even reinforced by habits of mind associated with critical reasoning. Indeed, experimental evidence supports this inference (Lawson & Worsnop 2006).

These relationships—which are integral to making sense of the salience and ferocity of societal conflict over climate change and over evolution—were absent from the views of the survey respondents toward childhood vaccines (Figure 7). Both science comprehension (r = 0.12, p < 0.01) and religiosity (r = -0.14, p < 0.01) displayed only weak relationships with the battery of items that formed the PUBLIC_HEALTH scale. There was an interaction between religiosity and science comprehension in the survey respondents’ scores on the scale, but it was small in size and, more importantly, moderated only the intensity of the positive orientation that subjects of varying levels of religiosity expressed toward childhood vaccines (App. 1, Table 1).

A more detailed examination of the participants’ responses to the various survey items follows. Unsurprisingly, there is unanimity on none. Nevertheless, understood in relation to contested societal issues that feature conflict among large and readily identifiable societal groups, the uniform and uniformly supportive margins of agreement reflected in survey responses is of fundamental interpretive significance. As will become even more apparent, in probing the nature of opposition to universal childhood immunization, one is necessarily assessing the attitudes of a segment of the population that is small in size and that defies identification by the sorts of characteristics associated with recognizable cultural styles in American society.


To download Vaccine Risk Perceptions and Ad Hoc Risk Communication: An Empirical Assessment, click here.

PrintView Printer Friendly Version

EmailEmail Article to Friend

Reader Comments (22)

So there's no link between climate opinion and vaccine opinion, or between evolution opinion and vaccine opinion.

That sounds like bad news for the "everything's determined by your cultural worldview" team.

January 30, 2014 | Unregistered CommenterPaul Matthews


who is on that team? I'm sure there are some, but I'm pretty sure I'm not.

There are many influences *besides* "cultural worldviews" that play a role in shaping risk perception.

But even more importantly -- to me, at least! -- the influence that interactions among persons w/ shared outlooks exerts on how they come to know what is known by science by no means implies that people w/ different outlooks should disagree!

January 30, 2014 | Registered CommenterDan Kahan

I hope this isn’t too random of a question since it isn’t specific to this particular post (though it at least relates to the topics in question) but I’ve noticed that “disbelief in evolution” and “global warming skepticism” are often mentioned together and I wanted to ask why that is. Is this association due to greater overlap in the populations that subscribe to both these positions as opposed to their counterparts (i.e. they just happen to both correlate with one tribe), or is it because both can be categorized as “skeptical” in some way? I ask because if it is the latter, it seems like the “opposite” association (creationism/intelligent design and belief in [anthropogenic] global warming) would be more analogous in the sense that both positions posit the intervention of an intelligent/powerful being (Gods? Aliens? Humans?) to account for an otherwise natural phenomenon (whether right or wrong). Is this is alternative framing ever used, or is it simply a mirror image of the other and makes no difference?

January 30, 2014 | Unregistered CommenterBrian E

I noticed this study invites "proposals for supplementary analyses of the data." Is the data available so people can look at it in order to come up with such proposals?

January 30, 2014 | Unregistered CommenterBrandon Shollenberger


That's an intersting & difficult question!

Easy answer would be that both reflect resistance to "scientific consensus."

But that's not satisfying: so do the views that deep geologic isolation of nuclear wastes is unsafe & that allowing people to carry guns in public causes violent crime to increase, yet those beliefs never find themselves mentioned in the same sentence w/ disbelief in evolution (these two "skeptical" views correlate positively w/ belief in it) or climate-change skepticsism (the nuclear-safety & gun-control indeterminacy skepticisms correlate positively w/ belief in climate change).

Another common assertion: climate skepticism and belief in evolution--both of which represent views of about 50% of US population--are signs of science illiteracy. Not true in the case of climate-change skepticism. And come to think of it, not true in case of disbelief in evoluition either.

They are also both presented as signs of hostility to or rejection of the authority of science. But that's also false.

Well, as I said, why those two beliefs get paired in popular discourse is a hard question!

Maybe others will offer additional hypotheses. I hope they also have either evidence to support them or ideas about how to test them.

January 30, 2014 | Registered CommenterDan Kahan


You are referring to the prefatory note in the Report, correct?

All the vaccine-related items used in both the survey and experiment are reproduced in Appendix 3. The Appendix also indicates how survey participants responded to the items.

You can get a sense of what other data were collected from the discussion of the various analyses.

The experimental stimulus is also reproduced (Appendix 2).

If you have conjectures, and ideas about how to test them with the data set--fire away, and your proposal will be considered for inclusion in this site's wildly popular feature, "WSMD? JA!" (surely you've heard of it?)

You can also send me an email, as indicated in the prefatory note.

January 30, 2014 | Registered CommenterDan Kahan

Dan -

Did you really mean this: "Another common assertion: climate skepticism and belief in evolution--both of which represent views of about 50% of US population--are signs of science illiteracy. "

Or did you mean to say "Another common assertion: climate change skepticism and [DIS]-belief in evolution--both of which represent views of about 50% of the population--are signs of science illiteracy"

As for Brian's comment - is it not true that climate "skepticism" and believe in creationism (of the YEC-type) is somewhat associated - but that the evidence shows that cultural/political/social identification is probably a better explanation of causality than being "anti-" or "pro-" science?

January 30, 2014 | Unregistered CommenterJoshua

Dan -

As for your comment:

"Well, as I said, why those two beliefs get paired in popular discourse is a hard question! "

Doesn't seem to me that it's too hard a question to answer. It seems to me that one of the reasons they get paired (that is, climate change "skepticism" and disbelief in godless evolution, or YEC beliefs, or I would guess even ID), is because there is something of an association. It seems that another reason is that it fits nicely with an identity-protection narrative among those who disagree with those beliefs.

Perhaps the better question is not why they get paired, but why the explanation is, so often, a mistaken belief about scientific literacy. But even there, it seems to me, the answer to that question is fairly obvious also.

January 30, 2014 | Unregistered CommenterJoshua

I guess that should be ".....or I would guess even belief in ID)......

January 30, 2014 | Unregistered CommenterJoshua

@Joshua-- thanks, did mean "DISbelief in evolution . . ."

How would you test your hypotheses?

January 30, 2014 | Unregistered Commenterdmk38

1. The worldview story was on my mind because there's a new review paper on this from the Cardiff crowd.

2. There's a slight muddle in your 30% and 18% numbers. They are the wrong way round either in the graph or in the text.

3. Relating to Brian's question, I think there's a phenomenon of "enemy equating". Is there an official term for this in social science or psychology? The argument goes as follows:
"I hate Xs. I hate Ys. Therefore all Xs are Ys".

January 31, 2014 | Unregistered CommenterPaul Matthews


2. Thanks! Wrong in figure. I corrected it.

1. I've seen the Cardiff paper. But do you think they take position that (a) "worldviews" account for all systematic & practically important variance in risk perception or that (b) the test for the influence of worldviews is the existence of practically important variance among individuals who differ in them?

I don't believe either (a) or (b). But if I were going to be an extremist, I would jettison only (a).

Indeed, for preesnt purposes, I'm inclined to believe that the positions that members of the public in the U.S. form on the safety and efficacy of vaccines does reflect the set of influences for which we (or at least I) am using the impact of "worldviews" as a shorthand. That is, I believe that most individuals are forming their understandings of what's known to science about the risks and benefits of vaccines by exercising the rational faculties they exercise to recognize what is collectively known. People tend to exercise that faculty inside of affinity groups, because that is where they can do so most efficiently. There is no conflict on vaccine risks among individuals of different "worldviews" in the U.S. because the affinity groups that orient them in this fashion with respect to what is known to science are not in conflict. This is the rule; conflict of the sort we see on climate, nuclear, HPV vaccine & the like the exception.

3. Yes, I'm sure there either is "a" mechanism of that sort or a variety of ones that operate in that way -- that is, that operate to incline individuals to impute bad qualities to individuals whom they hold in low regard.

But then I think the question is-- what is Brian's question?

I understood him to be asking why, in popular discourse, the "disbelief in evolution" & "climate skepticsm" positions are so often juxtaposed in one or another sort of commentary about public understandings of and conflicts over science. This strikes me as one of those questions that is profound and perplexing and important precisely b/c the practice it is asking about is so pervasive and natural that we barely notice it and have an instinct to dismiss the question by asserting the answer is "obvious" -- when it really isn't!

I am, of course, inclined to accept Joshua's answer or something like it. I think I've asserted something pretty close to that -- that the selectivity with which people pick out the science-consensus divergent beliefs of different groups is a form of group-identity defense, or -identity aggression.

But I recognize that as an answer that I'm drawn to precisely because it "fits" so well with other views I hold. Fitting well is fine; beliefs are supposed to fit with each other, and that's a criterion, I guess, of those beliefs being correct. But precisely for that reason, we are drawn to fit observation to belief--and the prospect that one might be donig that should disturb anyone who would like to understand what's really going on in the world.

So I wish there were more evidence of about how this aspect of public discourse works. It's interesting to reflect on what sorts of evidence one could adduce. I accept what essentially amounts to testimonials -- how it appears to me-- of people who I think are making the effort to form relatively complete and balanced observations.

But at that point, I'd like to do something more controlled in the nature of an experiment, or maybe an observational study in which the relationships being observed (or found not to exist) generate inferences that give us more reason or less to believe one or another competing account of the phenomenon.

Indeed, I think we had better be able to form at least one good counter-hypothesis of why the phenomenon Brian asks about exists, or we will have a hard time testing the one that Joshua advances.

January 31, 2014 | Registered CommenterDan Kahan

Dan -

> "But I recognize that as an answer that I'm drawn to precisely because it "fits" so well with other views I hold."

Eye - there's the rub, eh? Your question asking for a way to test my hypothesis has me uncharacteristically silent. It's a great question - and it's the important question. I need some time to think about it.

January 31, 2014 | Unregistered CommenterJoshua

"Eight percent of the respondents who believe in evolution and 77% who do not (...)"

I guess there is an "-y" lacking in the first of these number, or there is a very ecompassing margin of error...

January 31, 2014 | Unregistered CommenterMartin

Dan, thanks. I don't think the cardiff paper really takes a position, it just reviews the literature, a bit uncritically IMHO, and it reeks of the "how-can-we-get-people-to-do-what-we-want" trope that permeates everything Corner touches.

I know nothing about the worldviews of US vaccine sceptics, but I do know that the worldview story is oversold as far as UK climate sceptics are concerned. The Cardiff team found that in another recent paper, but buried it in the SI in the appendix.

January 31, 2014 | Unregistered CommenterPaul Matthews

@Martin: indeed! thank you

January 31, 2014 | Registered CommenterDan Kahan

@Paul ... did you say trope?! Well, don't worry; I won't tell your twitter pals!

January 31, 2014 | Registered CommenterDan Kahan

Hi Dan.. perhaps you still haven't got this communication thing worked out yet.. everything you say is visible to anybody

Paul's 'twitter pals' are also perfectly capable of reading your last comment, and having their perceptions' of patronizing academic fulfilled... I think you made that as a joke, as I've been hanging around here long enough by the way, (having witnessed the whole twitter conversation) but it may have come across badly..

One element is for why their are linkages talked about, is deliberate human behavior (not unconscious choices) deliberate tactics to persuade an audience not to listen to an opponent, or not thought to be that 'label' the listener would not want put on themselves, if they keep asking questions, think bigot, racist, denier, etc..

in the UK for example, the immigration debate was put back (or just ignored) for decades less anyone be thought racist or a bigot from left of centre politicians. Gordon Brown's prime time 'error calling a Labour voter a bigot (he thought the mike turned off later, whilst in a car) when she asked him questions about it on camera, went a long way to bursting that taboo.

Typical rhetoric tricks, used by activists and politicians alike, on all and any issues.... make it up! ie a nice little analogy or metaphor (without any evidence) X group of people are as bad, mad, sad, crazy, evil, etc as Y group of people... and you, listener don't want to be thought of like that do you..... if you keep asking me questions.. do you..

and of course the negative Y comparison, just gets changed for whatever is the flavour of the cultural times, or will tick the most boxes of the audience you are speaking to, or the most evil or stupid

so for some USA audiences 'climate sceptics' are painted as stupid as creationists (works in USA, but very few creationist in UK, so public in UK go huh?) and of course rhetoric gets hyped up the more some ask questions, or speakers thinks is losing the argument, until we get to 'en par with holocaust deniers' or 'conspiracy theorists' (evil or nutty - and no one want to be thought of, as that, or labelled publicly as that)

I agree with Paul, the Cardiff team just want to find reason to ignore people, to explain them away, to find ways to counter them, not communicate.. they would NEVER actually talk to 'sceptics', happy to just find generalizations from surveying a disinterested public largely oblivious to any of the issues..

one paper, found the most influence group from a set of generated headlines for a research paper, towards scepticism, was young welsh green student activists (something Geoff Chambers gently chided Adam Corner, for not commenting on) because counter to the narrative?

That said Amelia Sharman LSE, has been interviewing sceptics, I've got the signed paperwork to proof it, and even bought her lunch.. (she even knows where I live) ;-)

January 31, 2014 | Unregistered CommenterBarry Woods

oops 'Prove' it, not proof it, kids bedtime, so rushing as usual.

January 31, 2014 | Unregistered CommenterBarry Woods

@Barry-- will consider the entire msg carefully but on who can see what: perhaps I have a tin ear. I didn't think I was saying anything, here or anyplace else, that would give offense to anybody. I got my ears pinned back by @Paul & others for using "trope"-- I took that in good humor & appreciated the feedback. I thought maybe too there might even be interesting things to talk about w/ my tutor/critics on whom Feynman, an outstanding scientist communicator, is actually accessible to, and what he himself thinks about his audience when he lectures... & now I am only amused to find @Paul using "trope" -- & do still have 1/2 a mind to bring this to the attention of the others, so that he too can be upbraided.

I do see that often someone who addresses me in "social medial" land starts w/ a presumption that I hold a particular view that it can be made obvious I don't hold, & harbor hostility that I am happy to demonstrate to them I don't have. No one is to be blamed for their presumptions; the only thing we can expect is updating in light of the evidence made available.

Beyond that, I can only be who I am. I don't have time for anything more than that & I doubt it would do any good

January 31, 2014 | Unregistered Commenterdmk38

Dan, that is what I was referring to. However, what I asked after is not "a sense of what" data was collected or general information about the data. I asked if the data itself is available. It is much easier to come up with ideas if one can look at the data, either to check thoughts or find inspiration.

For instance, the document reports a number of correlations. The issue of correlation scores being misused is one I've discussed recently in a series of posts (a rough draft of a document collecting them is available here). There are a number of things to check when calculating correlation scores, and it'd be easier to check them myself than try to make a list of the possibilities. Plus, it'd save you the trouble of doing work to resolve my concerns.

As a demonstration, Figure 7 shows a graph of a strong negative correlation between two variables. However, a visual examination of that graph suggests the residuals of the fit are not normally distributed. That would mean the assumptions underlying the correlation calculation are not met. The overall notion is likely correct despite this since the correlation is so strong, but it's still something to verify. Also, it raises a question about other correlation scores reported (especially ones so low as 0.10).

There are lots of ideas like that which may merit consideration. It'd be far more practical to let people look at the data and check for themselves than require them send such ideas. (Plus, it'd let people reassure themselves of your results.)

January 31, 2014 | Unregistered CommenterBrandon Shollenberger


I haven't made the data set publicly available at this point. I will after I submit for publication.

To promote engagement with the data in the meantime-- including by people who are doing me the favor of telling me they think I'm using an inappropriate statistical model or otherwise analyzing the data in a manner that doesn't support the inferences I myself am drawing -- I've tried to make things as transparent as I can: by showing the raw data (in toplines for all the survey items; in scatter plots or lowess regression where I've looked at the relationship of different items or analyzed responses for relevant source of variance); by reporting the outputs for the regression models; and by graphically reporting the results where I think the practical significance is not likely to be apparent in regression outputs & the like. Also, as I've indicated, I'm happy to run additional analyses that people propose. Beyond that, how much to discount -- maybe down to no weight at all -- b/c I haven't yet posted the entire data set is a judgment call, and I would certainly respect any one you or anyone else would make.

On Fig 7: here are the residuals. I think they look okay. Agree?

As you know, Fig. 7 is just an illustration of the raw data on the "vaccine risk/benefit" items -- a scatter plot that, as you note, shows a negative correlation so obvious that a bat would have no trouble discerning it, & that I plopped a regression line on just to supply even more information.

I don't regress the items in the PUB_HEALTH scale on one another; that would be ridiculous in my view, since there's every reason to think they are all just measuring the same thing.

What I do want to be confident about is that the items scale appropriately. I report the cronbach's alpha and the factor analysis used to assess unidmensionality (and factor loadings). See anything odd there?

On these "small" correlations -- I do report some just to make the point that they are trivial (one of my own peeves is how often researchers treat the bare statistical significance of a correlation as supporting any sort of practical inference).

If it isn't too much of a bother, I am eager to learn of any other questions or comments that occur to you along these lines (or any others).

January 31, 2014 | Registered CommenterDan Kahan

PostPost a New Comment

Enter your information below to add a new comment.

My response is on my own website »
Author Email (optional):
Author URL (optional):
Some HTML allowed: <a href="" title=""> <abbr title=""> <acronym title=""> <b> <blockquote cite=""> <code> <em> <i> <strike> <strong>