Skip to main content

Myopic Calling Strategies

I'm interested in sequential decision-making problems.In these problems, there is a tension between exploration and exploitation. Exploitation is when you take actions with more certainty about the rewards. The goal of exploitation is to get maximum reward to the next action given what is currently known. Exploration is when you take actions with less certainty. The goal is to discover what the rewards are for actions about which little is known.

A strategy that always exploits is called myopic since it always tries to maximize the reward of the current action without any view to long-term gains.

Calling algorithms certainly face this tension. For example, evenings might be the best time on average to contact households. If I know nothing else, then that would be my guess about when to place the next call. But it would be foolish to stay with that option if it continues to fail. If I have failures in that call window, I might explore another call window to try and see if the reward is greater in that window for this particular household.

The following is a simple example, taken from Kulka et al. (1988). The goal is to establish contact. The contact strategy \(a_j\) can take on any of the following five values: WDM=weekday morning, WDA=weekday afternoon, WDE=weekday evening, SAT=Saturday, SUN=Sunday. We want to know which 3-call (\(j=1,2,3\)) sequence produces the highest contact rate. Using our notation, if \(Y_i=1\) denotes contact for the \(i^{th}\) case on any of the 3 calls, then the goal is to find the 3-call sequence that leads to the highest \(Pr(Y_i=1)\). A myopic strategy would choose \(a_1\) by comparing the probability of contact for each of the five possible treatments. The choice of \(a_2\) and \(a_3\) would be made in the same way. A non-myopic strategy would look at all 125 (\(5*5*5\)) possible sequences and determine which one had the highest overall probability of contact. That's basically what Kulka and colleagues did (looking at all possible combinations).

We could extend this approach across several stages of the survey process by looking at how the contact strategy impacts the ability to gain cooperation at later stages. For instance, a three-call sequence that placed three calls in the middle of the night might have a high contact rate, but would likely have a low rate of completing interviews.

Comments

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...

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 ...

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 f...