As a data guy, I take note whenever I see a new and interesting way that people are using data to inform their decisions. As just a guy, when the use of data to inform that decision-making
Tomorrow is the National Day of Civic Hacking, an event across more than 100 cities across the nation – including our very own Louisville (dubbed #Hackville). “Hacking” is somewhat out of IQS’ wheel house (as seen by the fact that we put it in quotes), as we are more on the stats end of the nerdy spectrum. However, that’s not to say that we don’t subscribe to the same purpose in life, which is to parse through the noise of the world to come to clear-cut conclusions. We just go through it by a slightly different type of analysis.
Math is like a reflex – we use it without thinking about it. Despite what your school teachers may have told you, your most often use of mathematics is not in adding/subtracting numbers – it’s actually in making decisions. This is the topic of today’s Skew, with the help of this comic. Real-world math is most often applied through the guise of what economists call “expected costs.” This is the cost of some risk which has some chance of happening.
Quick example, let’s say that you and a friend are betting $100 on a coin flip. You call heads, he calls tails. Since there’s an equal chance for heads or tails, the likelihood that you win is equal to the likelihood that you lose – 50%. So, assuming the winner gets all of the money, your expected cost is the likelihood that you lose (50%) multiplied by the value of what’s at stake ($100). So, the expected cost is $50 in this example (and equal to your expected gain, so the bet is essentially a wash between risk and reward).
The “funny” in the comic is in the assumptions that the guy is making to base his decisions. He’s saying that the expected cost of a terrorist attack exceeds just about any price. At the same time, he’s saying the opposite about a car accident – the expected cost is so low that any price would likely be too expensive. Since there are two pieces of information that drive these expected costs – the probability of the thing happening, and the cost resulting from that thing happening – then we can actually test how rational these two decisions are when taken together.
By most estimates, the probability that this guy dies in a terrorist attack is around 1 in 20 million. His odds of dying in a car accident? About 1 in 30,000. So, unless the cost of those personal safety features is more than 600 times greater than the personal cost of terrorist attack prevention, then it should make no sense for him to be more willing to ignore the safety features if he’s willing to pay to prevent attacks (there are other costs associated with both of these events, but I’m looking at it from a personal level only).
The key word there is “should.” In reality, we tend to inflate/deflate the odds of events pretty dramatically, which affects our behavior. Acts of terror are designed specifically to promote fear and inflate the perceived risks, while at the same time everyone thinks that they are the safest driver in the world. Also, we have remarkably little information about the actual costs associated with our daily risks, adding a layer of uncertainty in the decision-making process and ultimately clouding our judgment. In fact, if we had complete information about everything, then donuts and bacon would be given away almost for free, and bottles of water would become incredibly expensive.
In short, while math can (and a lot of times does) help to lead us toward rational decisions; it can also cause us to be irrational at times. However, the irrational decisions are still driven by solid math. They’re just informed by our own (often unsound) assumptions. By understanding those assumptions, we can account for the way they skew the decision-making process.view all
Yesterday, the President of IQS Research Shawn Herbig spent an hour on the radio discussing some of the intricacies involved in the research and polling process. Given the current election season, one thing we know for certain is that there is no shortage of polling results being released.
So that begs the question, how do we know which polls are right and which are not? Is each new poll released on a daily basis reflecting real changes in how we think about the candidates? Is polling and research indicative of emotions or behaviors, or both? These are some the things Herbig tackled yesterday.
We posted a discussion late last year about how it may be a good idea to look at what are called polls of polls, which take into consideration the summation of research done on a particular topic (in this case, political polling). This will help to “weed out” fluff polls that may not be very accurate, and to place a heavier emphasis on the trend rather than specific points in time.
But beyond this, understanding the the methodology behind polls is useful when deciding whether or not those results are reliable. A few things to note:
1. What is the sample size? – Political polls in particular are attempting to gauge what an entire country of over 200 million registered voters think about an election. A sample size needs to be 385 to be representative of a population of 200 million. But oftentimes you see polls with around 1,000 respondents. Oversampling allows researchers to make cuts in the data (say, what women think , or what what African Americans think) and still maintain a comfortable confidence level in the results.
2. How was the sample collected? – Polls on the internet, or ones that are done on media websites, aren’t too trustworthy. They attract a particular group of respondents, thus skewing the results one way or another. Scientific research maintains that a sample must be collected randomly in order for those results to be Representative in a population. In other words, each person selected for a political poll, for instance, must have an equal chance to be selected as any other person in the population.
3. Understand the context of poll/research – When the poll was taken is crucial in understanding what it is telling us. For instance, there was a lot of polling done after each one of the presidential debates. Not only did researchers ask who won the debate, but they also asked who those being polled were going to vote for. After the first debate (which we could argue went in Romney’s favor), most polls showed the lead Obama had going into the debate had vanished. Several polls showed Romney with a sizable lead. But was this a statistical push due to the recent debate and the emotion surrounding it? Or was this increase real?
Recent polls show a leveling between the two candidates now that the debates are over, and a more objective look at the candidates can be achieved. However, it is nearly impossible to eliminate emotion in responses, especially in a context as controversial a politics.
4. Interpreting Results – Interpretation ties in nicely with understanding the context of the research that you are viewing. But there is a task for each of us as we interpret, and that is to leave behind our preconceived notions about the results. This is very hard to do, as it is a natural human instinct to believe what justifies our own reasoning. This is know as Confirmation Bias, and it can impact the way we accept or discount the research.
Taking all this into account can help us to sift through the commotion and find the value of the research being produced. This isn’t just for political polling, but can be used for all research that you encounter. Being good consumers of research can take a lot of effort, but it is the only way to gain a more realistic view of the world around you.view all
Whether you own a restaurant, a retail store, or even just a gas station, your customers have certain expectations about you and what they want from you. Based on the research we have done for our retail customers, these are five common expectations that most customers share.
- It’s about the experience, not just the product. In this day and age, you can buy just about anything, sometimes even cheaper, on the Internet. But part of the reason people go to stores particularly local stores and specialty stores is to have the shopping experience. They want it to be clean, well-lit, and pleasant. If you can enhance the experience and give the customer a great feeling as they walk back out the door, your chances of return business grow exponentially.
- Make it easy to buy. This isn’t limited to “we take Visa, MC, and American Express” it includes everything that touches the customer. From parking, getting in the door, shopping hours, and in-store organization, it has to be easy to fit an interaction with you into their lives. The hassle factor is a huge and it will keep customers out of your store.
- There are many other options out there. Customers come to you for a reason. If the customer is in your door, they’ve already made at least a partial decision to shop with you. They could have gone somewhere else but chose your store instead. Welcome them and make them feel wanted. If you have a niche shop, then your expertise is valuable and will make customers want to come to you, not just because of products or price, but for the transfer of knowledge and help. But you have to make the experience enjoyable for the customer to learn. See our first point above.
- Everything in the retail experience counts. If you own a retail store, and have the best and widest selection available. But a lot of your product are kept in the back of the store, the staff is subpar or unfriendly, customers have to navigate though messy aisles, then it will hamper customers’ motivation to come to you, no matter how good your selection is.
- Customers are not alike. If you own a music shop you need to know that all musicians aren’t the same…a drummer is a different personality than a clarinet player, the rocker is different from the jazz musician. The customers know their own differentiating factors, and if you can learn those differences and adapt and cater to various types of customers, providing them a customized shopping based on their needs, you’ll certainly certainly be one step ahead of your competition..
Understand and follow these five basic customer expectations and you are well on the way to creating a loyal shopping experience where your customers will want to return again and again, and bring their friends.view all