Skip to main content

Level-of-Effort Paradata and Nonresponse Adjustments

We recently finished the development of nonresponse adjustments for a large survey. We spent a lot of time modelling response probabilities and the key variables from the survey. One of our more interesting findings was that the number of calls (modeled in a number of different ways) was not predictive of key variables but was highly predictive of response. In the end, we decided not to include this predictor. It could only add noise.

But this raises a question in mind. Their might be (at least) three sources of the noise:

1) the number of calls it takes to reach someone (as a proxy of contactibility) is unrelated to the key variables. Maybe we could speculate that people who are more busy are not different from those who are less busy on the key statistics (health, income, wealth, etc.).

2) The number of calls it takes to reach someone is effectively random. Interviewers make all kinds of choices that aren't random. These choices create a mismatch between contactibility and the number of calls.

3) Interviewers measure the number of calls wrong (see the recent article by Biemer, et al.). Measurement error adds noise.

In the end, we didn't need to distinguish among these three potential sources. But understanding these potential sources of error is important. If option 3 were the problem, then we would need to understand how to improve reporting on the number of calls. My guess is that issue 1 only occurs for some variables, therefore, understanding 2 and 3 will be important.
Labels:

Comments

  1. UnknownFebruary 4, 2013 at 7:25 AM

    Interesting! Thanks, James.

    How did you measure the relationship between contactability and key variables? I presume you did this only for respondents, so there is some missing data. Isn't there a fourth option, that the relationship between contactability and key variables exists, but only for nonrespondents? Meaning that: some nonrespondents would have responded if they had had one additional attempt, others would have needed five additional attempts, others maybe 100. Perhaps there is a correlation between this number and your key variables. What do you think, would a strong relationship among the nonrespondents be likely? Could it be strong enough to change change your opinion on adjustment?

    ReplyDelete

Post a Comment

Popular posts from this blog

Assessment of Maching Learning Classifiers

I heard another interesting episode of the Data Skeptic podcast . They were discussing how a classifier could be assessed (episode 121). Many machine learning models are so complex that a human being can't really interpret the meaning of the model. This can lead to problems. They gave an example of a problem where they had a bunch of posts from two discussion boards. One was atheist and the other board was composed of Christians. They tried to classify each post as being from one or the other board. There was one poster who posted heavily on the Christian board. His name was Keith. Sadly, the model learned that if the person who was posting was named Keith, then they were Christian. The problem is that this isn't very useful for prediction. It's an artifact of the input data. Even cross-validation would eliminate this problem. A human being can see the issue, but a model can't. In any event, the proposed solution was to build interpretable models in local areas of t
3 comments
Read more

Tailoring vs. Targeting

One of the chapters in a recent book on surveying hard-to-reach populations looks at "targeting and tailoring" survey designs. The chapter references this paper on the use of the terms among those who design health communication. I thought the article was an interesting one. They start by saying that "one way to classify message strategies like tailoring is by the level of specificity with which characteristics of the target audience are reflected in the the communication." That made sense. There is likely a continuum of specificity ranging from complete non-differentiation across units to nearly individualized. But then the authors break that continuum and try to define a "fundamental" difference between tailoring and targeting. They say targeting is for some subgroup while tailoring is to the characteristics of the individual. That sounds good, but at least for surveys, I'm not sure the distinction holds. In survey design, what would constitute
36 comments
Read more

What is Data Quality, and How to Enhance it in Research

  We often talk about “data quality” or “data integrity” when we are discussing the collection or analysis of one type of data or another. Yet, the definition of these terms might be unclear, or they may vary across different contexts. In any event, the terms are somewhat abstract -- which can make it difficult, in practice, to improve. That is, we need to know what we are describing with those terms, before we can improve them. Over the last two years, we have been developing a course on   Total Data Quality , soon to be available on Coursera. We start from an error classification scheme adopted by survey methodology many years ago. Known as the “Total Survey Error” perspective, it focuses on the classification of errors into measurement and representation dimensions. One goal of our course is to expand this classification scheme from survey data to other types of data. The figure shows the classification scheme as we have modified it to include both survey data and organic forms of d
Post a Comment
Read more