The Data Analytics Blog

Our news and views relating to Data Analytics, Big Data, Machine Learning, and the world of Credit.

All Posts

Motivated Reasoning: What It Is And How To Avoid It In Data Analysis

March 2, 2017 at 2:44 PM

Motivated Reasoning text and two cherries - one with a check mark and the other with an X to represent cherry picking

Use versus abuse of statistics can often be characterised by the analytical approach adopted to the problem at hand. In this blog post, which is part of a series on Logical Fallacies to avoid in Data Analysis, I’ll be focusing on defining the motivated reasoning logical fallacy and how to avoid it in data analysis.

What is Motivated Reasoning?

If statistics are being produced or selected to prove a point – we call this motivated reasoning (regardless whether the point is true or not). Motivated reasoning is the process of finding evidence to support a pre-held belief.

The video below goes into some depth about this cognitive bias and gives some good examples.

Motivated reasoning is wide-spread in society.  We see it regularly in politics where supporters of one party will dismiss any information that contradicts their belief (a phenomenon to help them avoid cognitive dissonance – i.e. the holding of two contradictory ideas).

Similarly in law, advocates and lawyers for both the prosecution and the defence will be utilising motivated reasoning to prove guilt or innocence/doubt respectively.  The judge or jury, conversely, have to use deductive reasoning to build the evidence up to one of these two conclusions. The challenge always is how they adequately and fairly assess the evidence that had been presented by the advocates/lawyers with the intention by either the prosecution or defence and how do they as humans eliminate any motivational bias in their own assessment of the evidence.

Businesses are regularly in a process of motivational reasoning.   Holding of opinions and beliefs is part of the human cognitive process and as such data scientists may be stuck with conducting a piece of diagnostic analysis where they themselves have a preconceived idea of the result they might find. motivated-reasoning-dilbert.gif

How to avoid Motivated Reasoning in Data Analysis

  1. Be fully aware that biases may creep into your analysis (metacognition: “think about thinking”)
  2. Before you begin your analysis try and do the following:
    • Note what metrics/analysis you wish to calculate/do and why
    • Note what you’ll need to find to reach a conclusion
    • Ask yourself whether the analysis will result in a fair assessment
    • Ask yourself “If I had an opposing view would I conduct the same analysis?”
    • Is there anywhere else I can look that will help me to the truth? If so can I predict what I will see?
  3. After you have conducted your analysis answer the following:
    • Am I presenting a full version of the truth?
  4. Prevent any motivated reasoning by conducting blinded analysis.
    • If possible, “blind” your data-sets, labels or trials ensuring that the subjects, those conducting the trials and, if possible, your analysts can conduct the research without bias.
    • This Nature article describes the importance of blinding one’s analysis.


What about Deductive Reasoning?

Deductive reasoning is the process of reasoning from one or more statements to a logical conclusion.

Although deductive reasoning is a cleaner form of analysis, errors can also slip in here.  The human tendency to avoid cognitive dissonance (the holding of two conflicting ideas) means that it is human tendency to only include data and analysis that fits a clear narrative and conclusion.  Awareness of these cognitive biases is essential in ensuring the presentation of a fair narrative.

Some practices linked to motivated reasoning

  • Publication bias or the file-drawer effect – the practice of some researchers to only publicise positive studies
  • Cherry-picking – only choosing examples and data that promotes your intended conclusion
  • Confirmation bias – the act of only recognising or recalling information that supports a pre-existing belief

Falling into the habit of conducting motivated reasoning, even subconsciously so, is a common problem.  The best place to start is with awareness of the problem.  As the physicist Richard Feynman once said, “The first principle [of science] is that you must not fool yourself — and you are the easiest person to fool.” 

predictive analytics guide

Thomas Maydon
Thomas Maydon
Thomas Maydon is the Head of Credit Solutions at Principa. With over 13 years of experience in the Southern African, West African and Middle Eastern retail credit markets, Tom has primarily been involved in consulting, analytics, credit bureau and predictive modelling services. He has experience in all aspects of the credit life cycle (in multiple industries) including intelligent prospecting, originations, strategy simulation, affordability analysis, behavioural modelling, pricing analysis, collections processes, and provisions (including Basel II) and profitability calculations.

Latest Posts

Incorporating Credit Lifecycle Predictive Outcomes In Your Collections And Recoveries Call Centre

In a collections environment, an agent needs to follow up with numerous customers on their outstanding credit and the more distinct information the agent has on each customer, the better the agent will understand who they are interacting with and what the opportunities, risks and expectation of the collections call with the client are.

[Slideshare] How To Make Your Business Data Work For You

Common barriers to success: Skills shortage: data scientists are in high demand and in low supply. Companies lack the skills to develop advanced data analytics or machine learning applications. Cost: recruiting and building up or training a team, as well as infrastructure costs are immense. Inefficiency and low ROI on: acquisition campaigns; re-activation and retention campaigns; outbound sales calls and debt collection. Resulting in: No or ineffective use of data. High cost to get insights from data. Low returns from campaigns. What’s the alternative? Machine Learning as a Service (MLaaS): removes infrastructure skills and requirements for machine learning, allowing you to begin benefiting from machine learning quickly with little investment. Subscription based pricing, allowing you to benefit using machine learning while minimising your set-up costs and seeing returns sooner. Answers as a Service: Use historic data and machine learning to allow answers to increase in accuracy with time. MLaaS with predictive models pre-developed to answers specific questions: Genius Call Connect: What is the best time and number to call customers? Genius Customer Growth: Which customers are most likely to respond to cross-sell? Genius Re-activation: Which dormant customers are worth re-activating? Genius Customer Retention: Which customers are most likely to churn? Genius Leads: Which contacts are likely to respond to my campaign? Genius Risk Classifier: Which debtors are most likely to pay or roll? Benefits of Genius: Quick and cost-effective ability to leverage machine learning: Minimal set-up time Minimal involvement from IT Subscription based service Looking to make your data work for your business? Read more on Genius to see how it can help your business succeed. 

5 Must-Join Facebook Pages For Data Science, Machine Learning And Artificial Intelligence In 2019

While LinkedIn has traditionally been thought of as the business or work focussed social platform, Facebook has been making headway into gaining market share in the space as well. With company pages and groups, Facebook is catering to every interest and aspiration that people might have – and combining that with their social interactions and news sources. Facebook aims to give users a one-stop-shop experience, and it’s very good at doing it.