Skip to main content

Description

  • 733 Accesses

Part of the Springer Texts in Business and Economics book series (STBE)

Abstract

This chapter portrays data description as an integral prelude to economic modeling, a key aspect of shaping a model. It lays out three principles that exemplify effective description and presents three techniques for creating graphs and tables that adhere to these principles. These ideas come to life in applications to ultramarathoning, beer prices, and the incentive effects of letter grades.

This is a preview of subscription content, access via your institution.

Buying options

Chapter
USD   29.95
Price excludes VAT (USA)
  • DOI: 10.1007/978-3-030-01734-7_7
  • Chapter length: 15 pages
  • Instant PDF download
  • Readable on all devices
  • Own it forever
  • Exclusive offer for individuals only
  • Tax calculation will be finalised during checkout
eBook
USD   84.99
Price excludes VAT (USA)
  • ISBN: 978-3-030-01734-7
  • Instant PDF download
  • Readable on all devices
  • Own it forever
  • Exclusive offer for individuals only
  • Tax calculation will be finalised during checkout
Hardcover Book
USD   109.99
Price excludes VAT (USA)
Fig. 7.1
Fig. 7.2
Fig. 7.3

Notes

  1. 1.

    No quantitative interpretation of the coefficient estimates is offered in the text of the paper. After it discusses this table, we learn the average price of beer is 0.2207 Euros per 100 mL, with brand-specific price dispersion averaging around 0.1 Euros per 100 mL. But this can’t be the unit used in Table 7.1—the coefficients are far too small. The units on temperature and the time trend are also unrecorded. The remaining variables are dummies, including the ambiguously-titled “promotion frequency.”

  2. 2.

    It turns out that the z-scores in the latter splits were somewhat sensitive to the method used to handle censored observations–runners forced off the course for going too slow. As a result Fig. 7.3 was omitted from the published paper, replaced with a sequence of histograms . The censoring issue is irrelevant for the purposes of this chapter–and the approach used in Fig. 7.3 could be applied to the vast majority of races, which do not censor to any material degree.

  3. 3.

    Elsewhere, of course, the two sets of results might be expected to differ in predictable ways. Suspicion follows if this does not come to pass; enhanced credibility if it does.

References

  • Empen J, Hamilton SF (2015) How do retailers price beer during periods of peak demand? Evidence from game weeks of the German Bundesliga. South Econ J 81(3):679–696

    CrossRef  Google Scholar 

  • Grant D (2016) The essential economics of threshold-based incentives: theory, estimation, and evidence from the Western States 100. J Econ Behav Organ 130:180–197

    CrossRef  Google Scholar 

  • Grant D, Green WB (2013) Grades as incentives. Empir Econ 44(3):1563–1592

    CrossRef  Google Scholar 

  • Hansen B (2015) Punishment and deterrence: evidence from drunk driving. Am Econ Rev 105(4):1581–1617

    CrossRef  Google Scholar 

  • Quan TW (2015) Demand heterogeneity: implications for welfare estimates and policy. Doctoral dissertation. University of Minnesota, Minneapolis, MN

    Google Scholar 

  • Rudder C (2014) Dataclysm: who we are (when we think no one’s looking). Random House Canada, Toronto

    Google Scholar 

Download references

Author information

Authors and Affiliations

Authors

Food for Thought

Food for Thought

  1. 1.

    In that most basic of chemical constructs, the periodic table, what is the micropicture ? The macropicture ? How is the former embedded in the latter?

  2. 2.

    The method Quan (2015) used to examine spatial scale was relatively crude. Given a large set of products and localities, each product’s local market share, and each market’s size, sketch out both graphical and tabular ways of documenting the spatial scale of product preferences in this data. You may want to incorporate standard measures of “unequalness,” such as the Gini coefficient, in the methods you propose.

  3. 3.

    The grades and ultramarathoning papers both examine the motivational effects of an achievement threshold, yet use different forms of description to depict their underlying dynamics. Design a table in the spirit of Table 7.2 that captures the dynamics of the ultramarathon discussed in this chapter. How would the essential content of the table differ from that of the graph? Why is a table inferior to the figure for displaying the dynamics of the ultramarathon, and vice versa for grades?

  4. 4.

    In a sizable literature on the effect of education on health, many authors take pains to instrument for education, expecting bias otherwise, as people with healthy habits should also get more schooling . But OLS and two-stage least squares estimates of the effect tend to be quite similar. Is this reassuring or not? How could descriptive statistics provide information relevant to deciding, one way or the other?

  5. 5.

    Consider the paired difference in means example discussed in the text, for the case of a single, discrete control variable that is associated with both the dependent variable and the treatment . Design a graph that segues from pure description to estimation .

  6. 6.

    This question applies the techniques developed in this chapter to Empen and Hamilton (2015).

    1. (a)

      Improve Table 7.1’s organization , labeling, and content, making up any information needed to complete this task.

    2. (b)

      Design a graph to illustrate the price dynamics underlying Empen and Hamilton’s findings. This graph should have more than one line, present both the macropicture and the micropicture , and be highly kinetic. It may help to know that Bundesliga “fixtures” typically alternate each team’s home and away games. My favorite, of the options I generated, illustrated the mean of price changes, not that of prices per se.

  7. 7.

    A graph that exemplifies the principle of maximizing information transfer is the International Diabetes Center’s Continuous Glucose Monitor AGP report (see agpreport.org). Identify at least five features of this graph that would make Edward Tufte proud.

Rights and permissions

Reprints and Permissions

Copyright information

© 2018 Springer Nature Switzerland AG

About this chapter

Verify currency and authenticity via CrossMark

Cite this chapter

Grant, D. (2018). Description. In: Methods of Economic Research. Springer Texts in Business and Economics. Springer, Cham. https://doi.org/10.1007/978-3-030-01734-7_7

Download citation