The Veepstakes: Using the Solution Desirability Matrix to Help Mitt Romney Choose the VP Candidate

Minitab Blog Editor 26 July, 2012

Flag of the United StatesThe GOP vice-presidential sweepstakes, or veepstakes, is heating up. Rumors are swirling about whether Mitt Romney has picked a running mate and when he’ll announce it. Will he pick a more exciting but riskier candidate? Or, will he play it safe?

Have you ever wondered how a candidate like Romney might go about evaluating all of the possibilities? There are many potential VP candidates and many criteria. Wouldn’t it be nice if there were a tool to help sort this out? There is! And it comes from the world of Six Sigma and process improvement.

People associate Six Sigma with statistics, and it does involve a lot of data analysis. But Lean and Six Sigma also include "soft tools" for collecting data and clearly understanding situations. Minitab makes a process improvement software package called Companion that makes all of those soft tools available in a single application.

One of the many tools that Companion contains is the Solution Desirability Matrix, which is perfect for this type of decision.

The Solution Desirability Matrix is a multi-dimensional decision matrix that helps make subjective decisions more objective. This matrix provides a semi-scientific method for selecting which of several competing designs or strategies best matches a list of requirements. The proposals are scored on how well each improvement proposal matches the selection criteria.

Let's work through the decision matrix to simulate how Mitt Romney might choose his running mate.

Collecting the Data for the Solution Desirability Matrix

The data collection process for this analysis was an extensive review of news reports. Ideally, this type of matrix is a team-based tool. I completed it myself, but I got a great deal of input from my friend Chris Jordan. As I wrote before, he and I are political junkies. While we weren’t in complete agreement, he did help prevent me from overlooking relevant information. I’ve done due diligence in terms of double-checking stories to reduce the influence of individual reporters' opinions.

Developing a List of Criteria for the Solution Desirability Matrix

Now we need a list of criteria for the Solution Desirability Matrix. We’ll use a selection of commonly accepted criteria for selecting the vice presidential candidate. These criteria must be stated so that a higher score is better. We also have to weight each criterion. Most weights will be equal, but “inside sources” have indicated that several criteria are more important to Romney, so I’ll factor that in.

Geographic Diversity: It’s an advantage when running mates are from different regions of the country, so I’ve given scores of 9 for non-adjacent regions, 5 for adjacent regions, and 1 for the same region.

Important Demographic: For this category, I’ve given a score of 5 to most candidates as the average. I’ve given scores of 9 to candidates who likely attract above-average interest from strategic demographic groups. These include Marco Rubio (Latinos), Kelly Ayotte (women), and Condoleezza Rice (African-Americans and women). I’ve given several candidates scores of 1 for potentially being aversive to some in these groups.

Party Leader: Sometimes a potential VP candidate is described as a “conservative rock star,” “favorite,” or a “leader.” This variable captures all types of leadership, not just the formal positions. It involves a certain degree of name recognition as well as a known stand on positions. Marco Rubio is an example--while relatively new on the national scene, he is known for his conservatism and has polled as the Tea Party’s preferred candidate.

Experience: Some candidates simply have more experience that is relevant to Presidential politics than other candidates. Mitt Romney and his advisors have indicated that this is particularly important. Therefore, I’ve weighted this category twice as heavily as the others.

Battleground State: If a candidate has the potential of delivering a battleground state for the ticket, it’s a plus. If a candidate is not from a battleground state, they get a score of 1. If they’re from a battleground state, they’ll get a higher score.

Baggage-Free: Some candidates have political baggage. The more baggage they carry, the lower the score. The relatively fresh-on-the-scene Kelly Ayotte has little political baggage, while the divisive Paul Ryan has a bunch!

Compatibility/Known Supporters: Some candidates have better relationships with Romney, have been supporters longer, and have campaigned with him in what some have called a job interview for being the running mate. These candidates get a higher score, while those who have a more acrimonious relationship--like Rick Santorum--get a lower score. Chris Christie gets a middle score because, while he’s been an active supporter, there are reports that he’s pursued it too aggressively and is too “shoot-from-the-hip” for Romney’s taste.

Safe Choice: Conventional wisdom posits that when a race is close, the candidate will pick a safe running mate. If they’re further behind, they tend to choose riskier, game-changing candidates. There are multiple reports that Romney is interested in a safe candidate, both because he is close to President Barrack Obama in the polls and because that is his natural inclination. So I’ll weight this category twice as heavily as the others. If the polls change before he announces his VP candidate, so might this variable. For now, bland is in!

Developing a List of All Potential Solutions

In this study, the "solutions" are potential running mates. I’ve included most of the names that are commonly accepted as being candidates. I’ve left some off the list if they have indicated very strongly that they will not accept a spot on the ticket. These include Mitch Daniels, Mary Fallin, Nikki Halley, and Susana Martinez. I included former Secretary of State Condoleezza Rice, despite her strong objections, because the Drudge Report indicated that she is on the short list and she made such a big splash recently. I wanted to see how she compares to the rest of the field.

The Analysis of the Vice-Presidential Solution Desirability Matrix

If you follow the news, you may know that the media has settled on several leading contenders. I didn’t let that influence this analysis. I simply ranked each candidate on each criterion. I’m interested to see how the analysis compares to the media favorites!

Each score is based on an overall perception. For example, the perceived amount of political baggage that each candidate possesses will vary from person to person. I’ve tried to capture the consensus in a score from 1 (worst) to 9 (best).

During the process, I found that the decision matrix helps to reduce the complexity of a large decision by breaking it down into more manageable pieces. For the VP question, we have nearly 100 data points to ponder one-at-a-time. For example, does candidate A have more or less political baggage than candidate B? That’s easier than trying to assess than the totality of each candidate all at once.

Having said all of that, I’ll be the first to admit that deciding on the criteria, weighting, and the scores for the candidates is still subjective. I’ve done my best to fill this in as Mitt Romney might, but it certainly contains guesses.

Below, you’ll see how I scored each candidate and their overall scores. I sorted the candidates from better to worse scores. Be sure to check out the discussion below the results.

Solution Desirability Matrix for VP Candidates

Pareto Chart for VP Candidates

Discussion and Surprises

It's good practice to review the results and determine whether they make sense. If they don't, why not? In the Solution Desirability Matrix, it is easy to determine why candidates score high or low. For this study, we have a combination of expected and unexpected results. Let's take a look at why candidates ranked high or low.

The top two choices--Tim Pawlenty and Rob Portman--are virtually tied. These candidates match the consensus top choices. This match is reassuring because it indicates that the criteria, weights, and individual scores combine to produce some semblance of reality. These two are experienced leaders in battleground states and both have been called "bland" (e.g., very safe). However, both have minor drawbacks. Portman is connected to George W. Bush, who presided over the 2008 federal budget, which doubled the deficit. Pawlenty is from a battleground state, but polls indicate he’ll have a hard time delivering it to Romney.

On the other hand, Pat Toomey (#3) and Paul Ryan (#4) were surprises for me. There hasn’t been much buzz over these two, yet they scored high. Let's see why.

Toomey scores high because he is a strong, experienced conservative from a battleground state. Toomey is a “safe” choice and compatible with Romney. In fact, Toomey has not only campaigned with Mitt Romney but has even written some of Romney’s campaign material. Toomey also has the distinction of having less political baggage than most politicians with his amount of experience. Paul Ryan scores high because he is experienced, a party leader, and comes from a battleground state. However, he has more baggage and is less safe due to his polarizing budget.

There are also candidates who scored lower than expected. For example, early favorites Marco Rubio and Chris Christie both scored fairly low.

Marco Rubio provides regional diversity, comes from a battleground state, appeals to an important demographic, and is a party leader. However, he is also inexperienced and relatively “unsafe,” two heavily weighted criteria. Rubio also promoted a health marketplace similar to President Obama’s health exchanges, extra baggage that Mitt Romney probably doesn’t want to deal with. Christie has a lot of baggage from being so outspoken, particularly in his attacks against public workers. Christie isn’t a particularly safe choice, and probably can’t deliver his solidly Democratic state.

Condoleezza Rice is an interesting candidate who ultimately comes out in the middle of the pack. She has lots of obvious positives: good demographic appeal, the highest favorable ratings of all the VP candidates, and good experience. However, she is pro-choice in a pro-life party, moderately conservative, and she is strongly tied to George W. Bush. This gives her a lot of baggage and reduces her blandness (unsafe in our matrix).

Closing Thoughts

The conventional wisdom of Tim Pawlenty or Rob Portman may be correct in this case. However, public perception is often wrong about the VP choice. If there is a surprise, could it be Pat Toomey? Or someone else entirely?

Who do you think Romney will pick for his running mate? If you don’t like my numbers and want to try it yourself, you can get a free trial of Companion.

I’ll award virtual gold stars to anyone who guesses correctly!