Tag Archives: Decision Making

Analytics and Statistics

Is analytics all hype and no substance?

Veravizion No Comments

Analytics is the process of discovering, interpreting, and communicating meaningful patterns in data. It helps us make decisions based on data and hard facts.

Most companies now use analytics to make data-driven decisions. They expect that good insights can really take their business to the next level.

Unfortunately, good insights rarely emerge.

Is analytics all hype then?

Here is a startling finding.

Research by PwC and Iron Mountain indicates that three in four businesses extract little or no advantage whatsoever from using analytics. According to the study, 43 percent of companies surveyed “obtain little tangible benefit from their information,” while 23 percent “derive no benefit whatsoever.”

Now, everyone and their uncle is claiming to use analytics in their business. If it was really useful, the world’s GDP have gone through the roof.

So, why are businesses not able to leverage analytics?

This HBR article and the PwC research discuss the root cause. Both studies point to lack of the right capabilities and competencies required to make good use of the information companies have.

This finding really warrants the question. What capabilities and competencies do we need to extract real value from data?

In fewer words, what makes analytics valuable and beneficial?

The answer is STATISTICS.

Statistics makes analytics insightful.

Analytics without statistics is bland, blunt, and bootless. It is like Ron’s broken wand in (the Harry Potter movie) The Chamber of Secrets.

Analytics without statistics, at best, gives us dull observations like ‘focus on the millennials.’ At worst, we get costly and impractical recommendations like ‘redesign the entire supply chain.’

This lack of benefits from analytics leaves businesspeople disappointed.

On the contrary,

Analytics + Statistics = INSIGHTFUL Recommendations

What is meant by insightful?

An analysis is ‘insightful’ when it goes beyond the superficial. It gives an accurate and deep (hitherto unexplored) understanding about the subject. Besides, an insightful analysis helps us break our long-held beliefs and preconceived notions that hold us back.

Here are two diverse examples of insightful findings.

Example 1: who revolves around whom?

The western world during Aristotle’s time (c. 384 B.C. to 322 B.C.) believed that the Sun revolved around the Earth. For 1,000 years, Aristotle’s view of a stationary Earth at the centre of a revolving universe dominated the studies of the universe. Surya Siddhanta and later Copernicus’ work showed that it was the other way round. That ours is a heliocentric solar system in which the Earth and the other planets revolve around the Sun.

That is insightful.

Example 2: how do you shave?

Gillette first entered the Indian market in 1984. But they failed to sell razors despite trying for many years. They even launched their newest triple-blade system in 2004. However, sales were flat for a long time. Why? Gillette did not understand the Indian consumers. They had tested the product with only a few Indian Students at MIT and hence had missed crucial insights about shaving habits in India. A large part of Indian men did not have access to running water and had longer and thicker hair (than Americans). Based on these enlightening insights, they launched Gillette Guard for the Indian market, tasted success for the first time, and never looked back.

Connecting the dots…

So, how does statistics make analytics insightful?

Statistics solves two problems: ‘isolated evidence’ and ‘random variation.’

It does so by employing systematic numerical methods to analyse enormous quantities of data representative of the entire population. Statistics helps us make inferences on the whole population from those in a representative sample. The representative sampling assures that inferences and conclusions can extend from the sample to the overall population.

Ideally, everyone using analytics must incorporate statistical techniques.

But there is one hitch.

In fact, there are three:

  • Statistics is complex. If there is one subject which is universally hated, it is statistics. Advanced statistics can get overly complicated. If they must, people use only the descriptive statistics which is easier. They tend to stay away from inferential statistics which is responsible for drawing inferences and conclusions.

  • Use of statistics needs expertise. One needs in-depth understanding of statistics to be able to apply it completely and correctly. Moreover, there are different statistical techniques for different data types. One must identify the right techniques to use depending upon the nature and quantity of data available. Many a times, we need to apply statistics in multiple stages (like the Bonferroni correction) to get more accurate results.

  • Building expertise takes time and efforts. Naturally, it is costly. It involves having the right people with deep level of knowledge and experience to apply analytics. Most people stop at the basics.

Due to this, it is rare to see use of statistics in analytics. Hence, despite being beneficial for business, useful analytical insights are hard to achieve.

Thus, analytics without statistics is anything but useful. But analytics with statistics is powerful. It delivers meaningful benefits.

That is why, at Veravizion, statistics is the indispensable part of all our analytics and consulting work.

There are several instances where the right kind of analytics (that include statistics) have rendered spectacular results. Analytics is reshaping industries like retail, consumer goods, healthcare, banking, and agriculture, among others. But that is a topic for another Veracle.

What has been your experience of implementing analytics?

Related Posts:

<– What are isolated evidence and random variation

Fields Medal, Open Problem, and Business Decisions –>

Cover Photo courtesy: Online stat psu edu

If you liked reading this article, then please subscribe to our blog – Veracles. That way, you can receive interesting insights in email.

Also, please do follow Veravizion on LinkedInTwitter or Facebook to receive easy updates.

What are isolated evidence and random variation

Veravizion No Comments

We know that inferential statistics helps people to make intelligent and accurate conclusions about a greater population based on analysis results of a small sample. Simply put, we can make estimations about populations based on a small sample of people.

One example: if we met a small group of doctors and find that the cardiologists among them earned more than general physicians, we could infer that cardiologists, generally, earned more than physicians.

Another example: In exit polls, the pollsters ask a small group of people at polling stations about who they have voted. Based on their responses, the pollsters make a generalised estimation on who is likely to win from that constituency.

However, there can be two problems in here.

  1. Isolated evidence
  2. Random variation

Isolated evidence

The problem of isolated evidence happens when we draw inferences based on only a few cases. Such inferences might not be accurate.

Like the above example, if we happen to know only the top cardiologists who earn high salaries, we might be tempted to generalise that all cardiologists earn high salaries. This is because we personally know a few that earn high salaries. Here, we have isolated evidence of only a few known cardiologists that do not represent the entire population of cardiologists.

In case of isolated evidence, we generalise based on known cases. So, there is an element of cognitive bias. Since cognitive biases strongly influence our decisions, we tend to generalise based on these cognitive biases. It influences so much that we look at every evidence in the light of our cognitive biases.

This problem is more likely to occur in the context of personal experiences.

For example, if we do not have a good experience of a certain product (or a service or an institution), we will desist our friend from using it. Ours may be a case of isolated evidence of bad experience with that product (or service or person). Most other people might have had other experiences. In short, our isolated evidence is not enough to conclude whether something is good or bad.

Random variation

The problem of random variation happens when we have insufficient sample data which may not be representative of the population. Here, we are likely to make inaccurate predictions about the entire population based on inadequate data. In such cases, any observed trend is out of randomness.

Random variation is independent of the effects of cognitive and systematic biases. We must aim to collate sufficient data points to nullify the effect of random variation. In general, the larger the sample size, the smaller the effect of random variation on our estimation. As the sample size increases, the random variation decreases, and the estimation accuracy increases.

In the above polling example, the pollsters may survey only a few people from a tiny number of polling stations. The variation thus obtained is more likely to be random than indicative of the entire population.

Don’t they sound the same?

It is easy to confuse between isolated evidence and random variation.

We can even say that isolated evidence is a special case of random variation.

However, there is one key difference.

Isolated evidence is rooted in the form of personal bias. Whereas the random variation comes purely from inadequate sample data.

That is why isolated evidence is more prevalent in people’s personal experiences. So, a friend asking us not to purchase a product is a case of isolated evidence. The star rating of the product on an e-commerce platform is statistical evidence and solves this problem if the rating is given by thousands of unknown people.

So, the next time we are tempted to make a conclusion based on a small sample size, check whether it is statistical evidence, or a case of isolated evidence or random variation.

Related Posts:

<– How can we make difficult decisions?

Is analytics all hype and no substance? –>

If you liked reading this article, then please subscribe to our blog – Veracles. That way, you can receive interesting insights in email.

Also, please do follow Veravizion on LinkedInTwitter or Facebook to receive easy updates.

make difficult decisions

How can we make difficult decisions?

Veravizion No Comments

We make decisions all the time. Some decisions are easy while others are difficult.

Why are some decisions difficult to make?

It is because they involve a trade-off.

A trade-off is an exchange of something of value for another, usually as a compromise. Simply put, it is a situation that presents us with two or more desirable choices, but we can choose only one.

  1. Easy decisions – involve little or no trade-offs
  2. Difficult decisions – involve tough trade-offs

Naturally, there is a tension involved where you have to trade-off (or lose) something of value for another.

Consider these examples involving trade-offs.

In healthcare, a patient suffering from seizures is offered the choice of brain surgery or long-term medication. The brain surgery can cure the condition but has low probability of success and may impair some other function like speech or memory. Whereas the medication may or may not be highly effective and cause unintended side effects like excessive drowsiness.

It is a gut-wrenching trade-off.

In career, we want a high-paying job having future growth prospects. But it may require frequent travel to different time zones and odd working hours. The decision involves a trade-off between career and health. Moreover, the job comes with the pain of staying away from family.

Unfortunately, such situations are common in business.

In business, a CEO may need to choose between closing the loss-making plant (and firing hundreds of employees) and attempting a turnaround possibly incurring further losses (and risking the survival of the entire business).

Thus, a trade-off implies an opportunity cost, or a sacrifice, or a pain to gain something. And these things hurt. That is why, decisions involving a trade-off are painful and difficult.

A tough trade-off makes us freeze or flee in the face of tough decisions.

How do we resolve a trade-off?

There is an interesting aspect about how the human psychology works when forced to face a trade-off.

In deciding between two options, we like to choose the higher value option over a lower value alternative.

Likewise, we prefer picking the less risky option over the riskier one. This is because human brain equates uncertainty with danger and causes anxiety. So, it wants us to make such decisions quickly to minimize the anxiety and stress.

In short, both the rational brain (i.e., prefrontal cortex) and the emotional brain (i.e., limbic system) are in action.

In such a situation, the key is to listen to the rational brain.

When forced to face a trade-off, be fiercely rational.

This is easier said that done. Because it is extremely difficult to suppress the limbic brain. Only a well-defined process can help.

That is why, to make difficult decisions, we need a rational decision-making process that:

  • gives us the best value option (with higher probability of success),
  • is quick and efficient (saving the anxiety and pain), and
  • helps us achieve the organisation’s purpose and vision.

In business context, the need for such a methodical decision-making process is vital. The analytics based decision-making process fills this space.

Analytics based decision-making process

This process satisfies all the above criteria:

  • It gives us the best value option. Analytics uses tools like classification and decision trees. These tools evaluate a quantitative value for each decision option. We can compare these values to better assess the trade-offs. We can weigh cost and benefits of each decision. Overall, this process helps us choose the best value option.
  • It is quick and efficient (and saves from anxiety). Analytics employs proven techniques and frameworks applied on data. These techniques are time-tested and use data as factual inputs. This brings objectivity in the decision-making process. As a result, the process takes away the emotional anxiety and appears unbiased.
  • It helps achieve our long-term vision. Most importantly, analytics makes use of statistical algorithms based on probability. This entails assessing each decision with the likelihood of achieving organisational objectives.

Thus, analytics based decision-making process helps in achieving organisational objectives in a facts-based, timely, and efficient manner.

More benefits

There is an additional yet understated benefit in using analytics for decision making.

The approach helps in communicating and justifying the decision to all the stakeholders. The pyramid principle made popular by Barbara Minto uses analytical reasoning to communicate a decision. It enables managers to get buy-in from the shareholders and employees for successful implementation of decisions.

In sum, analytics helps make, communicate, and justify difficult decisions.

What approach do you take to make important decisions?

Related Posts:

<– What business are you really in?

What are isolated evidence and random variation –>

Cover Photo courtesy: Vladislav Babienko on unsplash

If you liked reading this article, then please subscribe to our blog – Veracles. That way, you can receive interesting insights in email.

Also, please do follow Veravizion on LinkedInTwitter or Facebook to receive easy updates.

1

Most Viewed Veracles

Schedule Your Complimentary Session with us Today!

We promise you will come away with insights on utilizing your business data productively and cost-effectively. This session will be free of charge and there is no obligation.