Facebook and Mortality: A Look at the First Figure

I was going to make this the fourth post on the Facebook/mortality study (“Online Social Integration is Associated with Reduced Mortality Risk“) but am instead making it the third. (See Part One, Part Two, and Interlude.) After this, I will look at the relation (according to the study) between Facebook activities and specific causes of death.

I question the implications of the patterns in the two graphs of Figure 1. The first graph illustrates the association between Facebook friend requests and relative mortality risk; the other, between Facebook friend acceptances and relative mortality risk.

f1-medium

There’s a slight similarity between the two graphs. They both dip downward, hover a little in the middle, dip down some more, and then dip a little upward again. This is no coincidence; the authors acknowledge that they estimated the two friendship categories separately “due to high collinearity between them.”

The first graph (of friend requests) seems to show no significant relation between the activity and mortality risk; the other (of friend acceptances), a possible relation. But Facebook friend acceptances are fewer than requests, almost by definition. (Not all request get accepted, and one can only accept a request that has been made.) Couldn’t this magnify their effects? In any case, I see a lot in common between the two figures; the main difference is in the range of y-values.

But what is going on here, anyway? Both figures show relative mortality risk in relation to the reference category (the mean for each activity, I presume). The second figure has the wider range (between 1.383 and 0.852 times the reference category); to determine whether the differences have meaning, we would need to see the original numbers. In terms of visual effect, the range looks dramatic; in terms of actual numbers, it may be tiny.

I was hoping to get to the bottom of the Cox proportional hazards model, from which these figures are derived; but even the appendix doesn’t reveal the initial numbers or the specific application of the model. The numbers in the two graphs are “adjusted for age, gender, device use, and length of time on Facebook.” Just how does this work? I don’t know, but the adjustments seem somewhat arbitrary. An adjustment for education level or income might be more illuminating. (Update: Actually, they did control for “type of device used,” which was supposed to correlate with socioeconomic status. They also tried controlling for “highest education levels listed by friends on Facebook” but found that this did not substantially alter the results.)

There’s no adjustment, apparently, for length of time between activity and death. In the appendix, the authors state: “To be clear: we are testing associations between 1) social media usage over a six month period and 2) mortality over a subsequent 24 month period, with a 6 month gap between these two measurement periods.” So there’s no distinction between people who were already ill, people who became ill after that period of Facebook usage, and people who died suddenly, with no intervening illness.

Given the “high collinearity” between the two activities and their relation to mortality risk, I also wonder why there isn’t an adjustment for the presence of the collinear activity. It doesn’t seem quite right to separate the two activities when they are so closely related. I suspect that the apparent difference between them is deceptive.

Why does this matter? I take this time with the study because I see in it a combination of good intentions and profound nonsense. Facebook activity isn’t necessarily meaningful or positive; it has a good deal of banality and meanness. Is this the right place to look for insight on the relation between social activity and mortality? Is it the right way? I doubt it. But even if I put aside my initial doubts, I find problems in the logic of the study.

Recently some interesting articles about friendship have appeared; while imperfect, they seem more promising to me than studies of Facebook activity. I will write one more post about the Facebook/mortality study and then proceed to friendship.


Note: I made minor revisions to the fourth paragraph after posting this piece.

Leave a comment

4 Comments

  1. They must have adjusted by doing a multiple regression. The effects are tiny (look at the y-axis) and are probably not meaningful. Also, note the important point that non-significance in one and significance in the other does not imply an interaction. This is a stats 101 error that psychologists, psycholinguists, medical people and many others make all the time. Gelman calls it (somewhat confusingly) “the difference between significant and non-significant is itself not significant” (this is confusing because people think he is talking about a significance test between p0.05 using the p-values, and some people have interpreted his comment as license to treat p=0.10 as indistinguishable from 0.05). There’s an article in Nature by Wagenmakers on this. See also our articles for an intro to these and other issues.

    http://vasishth-statistics.blogspot.de/2016/08/two-papers-with-code-statistical.html

    The basic problem is that these authors don’t understand frequentist statistics, and are misusing it, and are doing the usual thing of using the p-value as their guide to making decisions.

    Reply
    • Thank you for your comment and for the link to your articles. I read the first one (rather quickly) this morning and found it helpful and clear. What the researchers have done in these two figures seems pertinent to what you bring up on p. 29: “multiple measures which are highly correlated (first fixation duration, single fixation duration, gaze time, etc.) are routinely analyzed as if they were separate sources of information (von der Malsburg & Angele, 2015).” This seems to be a problem throughout the study. There’s also the issue of power; while on the surface this may seem a high-powered study, I suspect it wouldn’t hold up under repeated sampling. The sample sizes for the specific investigations (relation between specific Facebook activities and specific causes of mortality) are far smaller than the aggregate sample size, and there’s probably much more noise than we see.

      I agree with you about the need for transparency. Here the researchers seem to walk a fine line: they present the results as “observational” but also represent them in seemingly dramatic graphs and read unwarranted meaning into them. An egregious example is in their hypothetical explanation of the difference between the two graphs in Figure 1:

      “These results replicate the classic relationship between reduced mortality and number of social contacts in a large scale online setting, but they suggest that what matters is not the tendency to seek out friends—it is the willingness of others to seek out and establish these friendships. To the extent that these results might be explained by some causal relationship between social support and health, the results suggest that merely seeking additional support may be ineffective. ”

      To call that overreach is to understate the problem.

      Reply
      • The problem is the same one that plagues psychologists, psycholinguists, medical researchers etc. etc. It’s so easy to ascribe a pattern to noise. It feels right, especially when it conforms to theory.

        Just try running a first order markov process many times, with the current observation dependent on the last one but otherwise randomly sampled, and watch the trend emerge:

        ## R code:
        nsim<-500
        x<-rep(NA,nsim)
        y<-rep(NA,nsim)
        x[1]<-rnorm(1) ## initialize x
        for(i in 2:nsim){
        ## draw i-th value based on i-1-th value:
        y[i]<-rnorm(1,mean=x[i-1],sd=1)
        x[i]<-y[i]
        }
        plot(1:nsim,y,type="l")

        When one looks at such "trends" and one has a deep theory behind a prediction that the trend will go this way or that, it's going to feel really compelling.

  1. Facebook and Mortality: Final Post | Take Away the Takeaway

Leave a Reply

Fill in your details below or click an icon to log in:

WordPress.com Logo

You are commenting using your WordPress.com account. Log Out / Change )

Twitter picture

You are commenting using your Twitter account. Log Out / Change )

Facebook photo

You are commenting using your Facebook account. Log Out / Change )

Google+ photo

You are commenting using your Google+ account. Log Out / Change )

Connecting to %s

%d bloggers like this: