Questions Guide you from Data to Information

From Data to Information

The ultimate goal of data analysis is to transform data into useful information. The path from data to information is guided by asking the right questions.

• Data is raw input that can be qualitative or quantitative information, and may be structured, semi-structured, or unstructured.

• Information is processed data that provides us with knowledge and insights.

• Key Idea: Questions act as a bridge between data and information

Notes and data charts on a wooden desk illustrating the foundation of effective information gathering.

What Makes a Good Question?

1. Know the problem you are solving.

As discussed last week, problem definition comes before analysis. A well-defined problem makes it easier to formulate good, focused questions.

2. Know the goal of your analysis.

Apply the SMART framework (Specific, Measurable, Achievable, Relevant and Time-bound).

Example: Instead of “Why are patients not recovering as expected?” ask, “Why did the average recovery time for patients with community-acquired pneumonia at Hospital X increase from 7 to 10 days between January and March 2025, and which treatment or care adjustments can reduce recovery time in the next quarter?”

3. Know the type of question you are asking.

• Descriptive: What happened?

• Exploratory: Why did it happen?

• Inferential: Can we generalise this finding?

• Predictive: What is likely to happen?

• Causal: What happens is we change X?

• Mechanistic: How exactly does the system work?

From Goals to Objectives to Questions

When setting goals, you will rarely answer the goal with just one question. Instead, break down the goal into objectives, each with its own set of questions

• Goal: The big-picture aim.

• Objectives: Smaller steps that help achieve the goal.

• Questions: specific, analysis-ready prompts aligned to each objective.

Example:

Defined Problem	Goal	Objectives	Questions
Drug resistance is increasing among TB patients in Southern Africa.	Quantify and understand the prevalence of multidrug-resistant TB in rural clinics.	1. Determine the prevalence of multidrug-resistant TB among patients on first-line treatment. 2. Identify demographic or clinical factors associated with resistance. 3. Evaluate treatment adherence patterns in affected patients.	1. What proportion of patients receiving first-line TB treatment in rural clinics have multidrug-resistant TB? 2. Are certain age groups, genders, or comorbidities linked to higher resistance? 3. How does adherence to treatment protocols correlate with resistance rates?
Postgraduate students in low-resource universities struggle with online learning.	Improve understanding of barriers to online learning and inform interventions.	1. Identify technological and connectivity barriers affecting online learning. 2. Assess the impact of these barriers on academic performance. 3. Explore strategies to mitigate these challenges.	1. Which digital tools or platforms are most inaccessible to students? 2. How does internet connectivity affect submission rates and grades? 3. What interventions could improve online learning engagement?
Company profits have been declining over the past three quarters.		1. Identify product lines and regions contributing most to profit decline. 2. Analyse customer segments most affected. 3. Investigate operational or market factors influencing sales.	1. Which products experienced the largest drop in sales? 2. Are certain regions underperforming more than others? 3. How have pricing, supply, or competitor actions contributed to the decline?

Why Formulating Questions Matters

• Data analysis without the right questions is like setting sail without having a compass; you will move, but have no destination.

• Wrong questions waste time, money, resources and reputation.

• Studies show that poor question formulation and misalignment in analytics projects result in billions of wasted costs globally.

Case Studies: The Cost of Asking the Wrong Question

Let’s examine these three case studies, which illustrate the cost of asking the wrong questions.

Case Study 1: New Coke – A Sweet Mistake

In the 1980s, in response to growing competition from Pepsi, Coca-Cola realised that Pepsi was winning over the younger customers through taste tests, which showed people preferred a sweeter taste. So, they introduced a new product called “New Coke”.

But the question Coca-Cola asked was:

• “Which formula do people prefer in a sip test?”

The problem? People have a long-term relationship with Coca-Cola; it wasn’t just about taste. It was about tradition, brand loyalty and an emotional bond with the product. The company faced immediate backlash. Loyal customers complained, sales dropped, and within three months, the old formula was back.

Lesson: Asking the wrong question turned a marketing strategy into a PR disaster. The right question would have been:

• “What do customers value most about Coca-Cola beyond taste?”

Case Study 2: Wells Fargo- Measuring the Wrong Success

Wells Fargo, proud of its cross-selling record, encouraged customers to open multiple accounts. Management pushed employees with the question:

• “How can we get customers to open more accounts?”

This led to employees opening millions of unauthorised or fake accounts to meet unrealistic sales targets. The results? A scandal that cost the bank $3 billion in fines and severe reputational damage.

Had the bank asked a different question:

• “How can we deepen trust and engagement with our customers?”

The focus would have been on customer experience and retention instead of inflating numbers.

Lesson: Wrong questions can destroy trust and productivity.

Case Study 3: NASA’s Lost Orbiter – A Unit Misunderstanding

In 1992, NASA lost a $125 million spacecraft called the Mars Climate Orbiter due to a crucial mistake: one engineering team used metric units, another used imperial units.

The implicit question was:

• “Are our calculations correct?”

But they failed to ask:

• “Are we all using the same measurement system?”

This oversight led the spacecraft to enter Mars’ atmosphere at the wrong angle and disintegrate.

Lesson: Even highly skilled teams can fail when the wrong or incomplete question guides their work.

The power of writing the right question.

• Good questions guide effective analysis.

• Wrong question costs time, money, and reputations.

• Next time, we will look at how well-formed questions lead to the right analytical techniques.

Sources and Further Reading

• NASA – Mars Climate Orbiter Mishap Investigation Board Report (1999).

• Coca-Cola Company – The Real Story of New Coke (Coca-Cola’s own retrospective on the “New Coke” case).

• Wells Fargo – U.S. Securities and Exchange Commission (SEC) settlement documents & coverage (example: The Wells Fargo Fake Accounts Scandal Explained, Investopedia, 2020).

• Doran, G. T. (1981). There’s a S.M.A.R.T. Way to Write Management’s Goals and Objectives. Management Review, 70(11), 35–36. (Original article introducing SMART goals).

• Bryman, A. (2016). Social Research Methods. Oxford University Press.

• Kahneman, D. (2011). Thinking, Fast and Slow. Farrar, Straus and Giroux.

• MIT Sloan Management Review. (2019). The Analytics Mandate: Why Asking the Right Question Is Key to Data Success.

• Davenport, T. H., & Harris, J. G. (2007). Competing on Analytics: The New Science of Winning. Harvard Business School Press.