Profile Picture
Email Address
Research Projects
Organizational Units
Professor of Marketing
Professor Armstrong is internationally known for his pioneering work on forecasting methods. He is author of Long-Range Forecasting, the most frequently cited book on forecasting methods, and Principles of Forecasting, voted the "Favorite Book – First 25 Years" by researchers and practitioners associated with the International Institute of Forecasters. He is a co-founder of the Journal of Forecasting, the International Journal of Forecasting, the International Symposium on Forecasting, and forecastingprinciples.com. He is a co-developer of new methods including rule-based forecasting, causal forces for extrapolation, simulated interaction, and structured analogies.
Research Interests

Search Results

Now showing 1 - 10 of 227
  • Publication
    Creative Obfuscation
    (1982-03-01) Armstrong, J. Scott
    A rational and popular viewpoint is that the function of scientific writing is to communicate knowledge. A study of prominent journals, however, suggests that clear communication is not appreciated within the reading-writing-refereeing community. If clarity is a goal for a journal, the editor must take action.
  • Publication
    Book Review of Corporate Strategic Planning
    (1990-04-01) Armstrong, J. Scott
    Book Review of Corporate Strategic Planning by Noel Capon, John U. Farley, and James M. Hulbert, New York: Columbia University Press, 1988.
  • Publication
    Research on Forecasting: A Quarter-Century Review, 1960-1984
    (1986-02-01) Armstrong, J. Scott
    Before 1960, little empirical research was done on forecasting methods. Since then, the literature has grown rapidly, especially in the area of judgmental forecasting. This research supports and adds to the forecasting guidelines proposed before 1960, such as the value of combining forecasts. New findings have led to significant gains in our ability to forecast and to help people to use forecasts. What have we reamed about forecasting over the past quarter century? Does recent research provide guidance for making more accurate forecasts, obtaining better assessments of uncertainty, or gaining acceptance of our forecasts? I will first describe forecasting principles that were believed to be the most advanced in 1960. Following that, I will examine the evidence produced since 1960.
  • Publication
    Publication Bias Against Null Results
    (1997) Hubbard, Raymond; Armstrong, J. Scott
    Studies suggest a bias against the publication of null (p > .05) results. Instead of significance, we advocate reporting effect sizes and confidence intervals, and using replication studies. If statistical tests are used, power tests should accompany them.
  • Publication
    Moneyball: Message for Managers
    (2012-01-22) Armstrong, J. Scott
    Michael Lewis’ book and film, Moneyball, provide valuable advice for people involved with the selection and retention of employees. However, judging from some reviews, there is confusion about the message in Moneyball. I describe the problem and the Moneyball solutions here. The solutions are valuable for personnel decisions in any large organization.
  • Publication
    How Expert Are the Experts?
    (1981-12-01) Armstrong, J. Scott
    If you want good forecasts for your industry, you should hire the best experts. Right? Well, maybe not.
  • Publication
    The Case of the Detrimental Drug: Implications for the Stakeholder Theory of Directorship
    (1980) Armstrong, J. Scott
    The Winter 1979 issues of Directors and Boards presented readers with a questionnaire based to a degree on a 1969 board incident at Upjohn Corporation [see Box 1 (on page 2) and Box 2 (on pages 3-4)]. In this questionnaire, a profitable drug named “Wondola” was being produced by the so-called International Drug Corporation (IDC). Readers were told that members of the American Medical Association's Council on Drugs had objected to the sale of most fixed -ratio (combination) drugs on the grounds that they grant no benefits superior to those of single-ingredient drugs, and are more likely to produce detrimental side effects, including death. Wondola, with an approximated fatality record of 14 to 22 deaths per year, was no exception. The Federal Drug Administration had asked IDC to withdraw the drug. Readers were asked how they would have voted at a board meeting called to resolve the withdrawal issue. Several months after the publication of the first questionnaire, follow-up questionnaires were sent to D&B readers and to select corporate constituents. These letters solicited comments on a “stakeholder” theory of board membership which I proposed in conjunction with the Wondola experiment. In the following pages, I present the background of the experiment. The stakeholder theory will then be proposed as a solution to the “responsiblity dilemma” the Wondola case raises. Finally, questionnaire respondents will speak for themselves on this complex issue.
  • Publication
    On the Effectiveness of Marketing Planning
    (1989) Armstrong, J. Scott
    Managers are often told that formal planning helps. It is useful to examine whether this is good advice. Thus, I applaud this effort to study marketing planning in New Zealand. Nevertheless, I find it difficult to accept the conclusions drawn by the authors of “Marketing Planning in New Zealand” (MPNZ). I am concerned with the definition of marketing planning, the criteria, and the design of the study.
  • Publication
    Eclectic Research and Construct Validation
    (1974) Armstrong, J. Scott
    Consider the following situation: You have a fixed budget and would like to measure causal relationships in a study involving buyer behavior. How would you go about allocating the budget for this study? This paper outlines two possible research strategies – intensive research and eclectic research. Each strategy utilizes the budget in a different manner. The intensive approach involves allocating the budget to a single study, and the eclectic approach divides the budget among a series of smaller-scale studies that differ markedly from one another. Intensive research is called for when problems of reliability are of utmost concern; eclectic research is called for when problems of construct validity are paramount. Since we believe that problems of construct validity deserve more attention than they currently receive for problems in non-experimental research, we advocate stronger emphasis on eclectic research.
  • Publication
    The Case for Minimum Teaching Standards
    (1990-01-16) Armstrong, J. Scott
    Author's Note: The following was sent to the Wharton faculty in November, 1989, challenging a set of proposals by the Wharton Teaching Committee.1 The committee's proposal was presented as an "all or nothing" choice. Despite a substantial amount of support for the position stated below, the Wharton Committee recommendations were passed as originally proposed; this includes punitive measures for faculty who get low ratings (referred to below as the committee's Proposal #1). The proposals said that for tenure or promotion, a faculty member must get better than an "average" rating (3.0 on a five point scale). The vote was close. It seems likely that Proposal #1 would have been defeated had a secret ballot been conducted on this item alone. Action was not taken on any of the nine proposals in my paper, and neither of the proposals on process were accepted. Since that time, faculty from other schools have read the memo and suggested that it be reprinted in Almanac in order to gain further faculty comment. They are concerned that similar events in their schools may affect the quality of the educational environment.