Skip to main content

An Experimental Adaptive Contact Strategy

I'm running an experiment on contact methods in a telephone survey. I'm going to present the results of the experiment at the FCSM conference in November. Here's the basic idea.

Multi-level models are fit daily with the household being a grouping factor. The models provide household-specific estimates of the probability of contact for each of four call windows. The predictor variables in this model are the geographic context variables available for an RDD sample.

Let $\mathbf{X_{ij}}$ denote a $k_j \times 1$ vector of demographic variables for the $i^{th}$ person and $j^{th}$ call. The data records are calls. There may be zero, one, or multiple calls to household in each window. The outcome variable is an indicator for whether contact was achieved on the call. This contact indicator is denoted $R_{ijl}$ for the $i^{th}$ person on the $j^{th}$ call to the $l^{th}$ window. Then for each of the four call windows denoted $l$, a separate model is fit where each household is assumed to have its own intercept which is from a $N(0,\sigma^{2}_{il})$ distribution. The model is estimated:

$Pr ( R_{ijl} = 1 ) = logit^{-1} ( \beta_{0l} + \beta_{0il} + \sum_{j=1}^{k} \beta_{jl} X_{ijl}) $

The next step is to compare the estimated contact probabilities within a household and find the window with the highest probability of contact for that household. In that window, the case -- along with all other cases that meet this criterion -- will be sorted to the top of list by the call scheduling algorithm. Under this approach, a case with a low probability of contact could be sorted to the top of the list in any given call window, as long as the estimated probability of contact was highest for the case within that window.

The experimental design required frequent sorting of the list as the call windows were specific to the time zone. For example, on a Tuesday, the list was sorted first thing in the morning, at 5pm EST, 6pm EST, 7pm EST, and at 8pm EST as the various time zones crossed the call window boundary. The experimental design required that the experimental and control groups be sorted in an intervleaving fashion. The past practice had been to sort at the beginning of the day. The sort was based on sorting more promising cases to the top -- cases with more contacts, selected respondents, number of calls and so on.

So far, the experiment has been going well. In the first month, the contact rate for the experimental group had a 15% increase relative to the control group.

Comments

  1. This concept is a good way to enhance the knowledge.thanks for sharing. please keep it up selenium Online Course

    ReplyDelete
  2. If you come with any issue which many of us is just not conscious of then it`s not most likely a challenge for the team as it's quick and sharp to locate out from the issue and resolving it straight away. Go right ahead and e mail us anytime at Quickbooks Enhanced Payroll Customer Support.

    ReplyDelete
  3. Our Intuit QuickBooks Support channel- We comprehend the complexity and need using this accounting software in day to day life. You can’t be cautious about just about time because of it to obtain a fix of each single QB error.

    ReplyDelete
  4. Any way I'll be subscribing to your feed and I hope you post again soon. Big thanks for the useful info.
    will help you more:
    Take Survey

    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...

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...