ISG Playbook
APIs
7 Sneaky Cognitive Biases that Wreak Havoc on Innovation
10 min read
Introduction
Have you ever wondered why even the most brilliant projects sometimes go completely off track? The culprit might just be lurking in our own minds—cognitive biases. These sneaky mental shortcuts can wreak havoc on our ability to think objectively and sabotage collaboration. Inspired by the captivating book "The Art of Thinking Clearly," I couldn't resist exploring how biases disrupt the world of innovation - especially when it comes to working together to bring new ideas to life. So, buckle up and join me on a journey to unravel 7 lesser-known cognitive biases that can turn your collaboration into a wild ride. But fret not! Along the way, I'll equip you with clever strategies to navigate through these biases and steer your team towards success.
1. The IKEA Effect: When You Built It, You Believe It Must Be Good
Overview:
Imagine pouring your heart, soul, and Allen wrenches into a project, becoming its number one defender. That's the IKEA effect in action! This sneaky bias tricks us into overvaluing our creations just because we invested so much time and effort into building them.
Impact:
In collaboration, the IKEA effect can be a stumbling block. It makes us cling onto our ideas too tightly, blinding us to their flaws and alternative viewpoints. This bias can hinder progress and prevent us from making necessary improvements.
Prevention:
Don't worry, we've got the tools to tackle this bias! To beat the IKEA effect, create a culture of constructive critique. Encourage honest feedback, foster open discussions, and invite external perspectives. By seeking different viewpoints and being open to improvement, you'll ensure your collaborative creations are top-notch. Consider hosting a critique workshop in partnership with our team to overcome barriers.
2. The Curse of Knowledge: When Expertise Hinders Effective Communication
Overview:
Have you ever explained a mind-boggling concept to your team, but all you see are puzzled expressions. Uh-oh, you might be cursed with knowledge! This tricky bias makes it hard for us to remember what it's like not to know something we're already familiar with.
Impact:
In collaboration, the curse of knowledge can turn communication into a jumbled mess. It's like speaking a different language that only you understand. Your team might feel left in the dark, hindering their ability to contribute effectively and slowing down progress.
Prevention:
Do not despair, communication superheroes! To banish this curse, embrace the power of clear and concise communication. Seek diverse perspectives to uncover blind spots, encourage knowledge sharing within the team, and bring in visual aids, analogies, or even a captivating story. By bridging the gap in understanding, you'll ensure smooth collaboration and save the day!
3. The Spotlight Effect: When We Feel Like Everyone is Watching
Overview:
Imagine feeling like all eyes are on you, judging your every move in a meeting. Cue the spotlight effect! This bias makes us think that everyone notices and cares way more about our performance than they actually do.
Impact:
In collaborative settings, the spotlight effect can turn us into nervous wrecks, afraid to speak up or share our ideas. It's like having a mini audience of critics in our heads, holding us back from contributing our best. Collaboration suffers when we're too self-conscious to let our creativity flow freely.
Prevention:
But fear not, brave collaborator! Dim that spotlight and let your brilliance shine. Create a safe and supportive collaboration space where everyone feels comfortable being themselves. Embrace open dialogue and celebrate mistakes as opportunities for growth. Remember, we're all human, and nobody expects perfection. Foster a culture where ideas are welcomed with open arms, questions are encouraged, and judgment takes a back seat.
4. The Backfire Effect: When Beliefs Get Sticky
Overview:
Have you ever presented solid evidence that contradicts someone's beliefs, and instead of changing their minds, they dig their heels in even deeper! That's the backfire effect in action. It's like a force field that makes people cling stubbornly to their beliefs when faced with opposing evidence.
Impact:
When the backfire effect takes the stage, projects suffers. It creates a divide among team members, polarizing their beliefs and hindering constructive discussions. Instead of engaging in a productive exchange of ideas, people become defensive and resistant to alternative perspectives. This can lead to a stalemate, with no room for growth or innovation. It's like being trapped in a belief bubble, unable to break free and embrace new possibilities.
Prevention:
To defeat the backfire effect and foster a collaborative environment where ideas can flow freely, we need to embrace a few superhero strategies. First, let's focus on evidence-based discussions rather than personal opinions. When presenting conflicting information, approach it with curiosity and a willingness to learn. Encourage critical thinking and constructive debates, where everyone's input is valued. By creating an atmosphere of open-mindedness, we can burst the belief bubbles and pave the way for productive collaboration.
Remember, we're all on this collaborative journey together, and by taming the Backfire Effect, we can create a dynamic space where ideas can flourish and innovation can thrive!
5. The Mere Exposure Effect: When Familiarity Breeds Comfort
Image via the Decision Lab
Overview:
The Mere Exposure Effect is a fascinating bias that tells us our preferences can be swayed simply by repeated encounters with something, even if there's not much substance to it. But fear not, brave innovators! We have the power to break free from this effect and embrace true progress.
Impact:
In government innovation, the Mere Exposure Effect can be a saboteur. It tricks us into clinging to outdated practices and familiar ideas, preventing us from exploring new territories. Collaboration suffers as teams fall into the comfort of the known, stifling fresh thinking and growth. It's like being stuck in a time loop, where innovation becomes a mere illusion.
Prevention:
To vanquish the Mere Exposure Effect and ignite a flame of innovation, we must embrace a few strategies. First, foster a culture of critical inquiry and openness to new ideas. Encourage diverse perspectives and invite voices from different backgrounds to challenge the status quo. Break free from the clutches of the familiar. Remember, true innovation lies in the unknown, not in the cozy corners of the familiar.
6. The Halo Effect: When a Single Trait Can Cloud Judgement
Image via the Decision Lab
Overview:
Welcome to the world of the Halo Effect where one shiny attribute dazzles us and influences our overall judgment. Imagine falling head over heels for a product just because it has a sleek design, assuming it's top-notch in every way. But hold on tight, because this bias can make us miss important details and lead us astray.
Impact:
When it comes to collaboration, the Halo Effect can create illusions and hinder thorough evaluations. When we're mesmerized by one impressive quality of a person, product, or organization, we tend to overlook other essential aspects. This can result in skewed judgments, favoritism, and missed opportunities for growth. It's like seeing only the dazzling exterior while ignoring what truly matters on the inside.
Prevention:
To prevent the Halo Effect from clouding our judgments, we need to put on our critical thinking capes! Instead of being swayed by one standout characteristic, let's take a step back and evaluate things holistically. Look beyond the shiny surface and delve into the depths of different aspects and attributes. Ask questions, gather information, and consider multiple perspectives. By embracing a comprehensive evaluation approach, we can unravel the truth beneath the halo and make more informed decisions.
7. Sunk Cost Fallacy: When We Cling to Past Investments
Image via the Decision Lab
Overview:
Let's talk about the Sunk Cost Fallacy, a tricky bias that can keep us tied to the past. Picture this: you've poured your whole treasure chest of resources into a project. But alas, it's not sailing smoothly. Yet, you find yourself clinging to it, unwilling to abandon ship. That's the Sunk Cost Fallacy in action! It's when we let past investments cloud our judgment and keep us stuck in uncharted waters.
Impact:
The Sunk Cost Fallacy can shackle us to failing projects or ideas. We become so attached to what we've already invested—time, money, and effort—that we can't bear to let go, even when it's clear they're dragging us down. This reluctance to cut our losses leads to wasted resources, missed opportunities for innovation, and a ship stuck in the doldrums. But fear not, there's a map to navigate past this treacherous fallacy!
Prevention:
To prevent the Sunk Cost Fallacy from steering us astray, we need to summon our courage and embrace a rational mindset. It's time to evaluate projects and ideas based on their current merits, not the past investments. Ask yourselves, "Is this still the right course? Can we chart a better path forward?" Don't let the fear of abandoning sunk costs weigh you down. Instead, focus on the potential for innovation, growth, and undiscovered treasures. Remember, cutting losses can free up resources for new and exciting ventures!
Conclusion
From the mighty IKEA effect to sunk cost fallacy, we've uncovered some of the secrets that shape our collaborative endeavors. But we hold the key to unlock the full potential of our teamwork! By embracing strategies like fostering a culture of constructive critique, bridging communication gaps, taming self-consciousness, balancing power dynamics, and charting realistic plans, we become masters of collaboration. Though much can be accomplished simply by being aware of our own biases and recognizing when they're at play.
CHELSEA BRIGG
Chelsea is a Senior Design Strategist with the CCSQ Human-Centered Design Center of Excellence (HCD CoE). For more than a decade she has led mixed-methods user research for science, health, and public policy organizations such as National Geographic, Johns Hopkins Medicine, Penn Medicine, Medicare/Medicaid, and Mathematica Policy Research. Chelsea holds a Master of Science in Human-Centered Computing from the University of Maryland, where she studied as a Computing Research Association scholar.
The Crisis of Rural Hospital Closures
Reading Time: 4 mins
Located near U.S. Route 66 in eastern New Mexico, a 10-bed hospital has long been a crucial source of emergency care for car crash and ranching accident victims. Additionally, it has served as a convenient option for overnight stays, primarily for older residents dealing with pneumonia or heart ailments. Covering a vast area of 3,000 square miles (about twice the area of Rhode Island), home to over 4,500 people, this hospital stands as the sole medical facility in the region. However, despite a tax levy in place to support it, the hospital has suffered a financial loss of over $1 million in the last six months. Christina Campos, administrator of Guadalupe County Hospital in Santa Rosa, expressed their anticipation of closure while hoping for a sustainable program to intervene.
In response to the challenges faced by rural hospitals across the country, Guadalupe is among the first to undergo the transformation into a Rural Emergency Hospital. This designation is part of a new federal payment program introduced by the Centers for Medicare & Medicaid Services, specifically designed to assist rural providers. Although not a permanent solution, policymakers and hospital operators are optimistic that it will help alleviate the ongoing financial struggles that have forced numerous rural hospitals to shut down.
This narrative reflects the crisis in many of our rural hospitals. Rural hospitals have long been facing an ongoing crisis, with over 150 closures since 2010 and over 300 more at risk, a problem further intensified by the challenges brought on by the COVID-19 pandemic. As a result, out of approximately 5,000 facilities across the country, only about 2,230 rural hospitals remain. The closures have been escalating in recent years, leading to subsequent shutdowns of primary and specialty care providers in affected areas. While federally qualified health centers (FQHCs) attempt to address the gaps, significant healthcare deficiencies persist following these closures.
Why are rural hospitals closing?
Understanding the causes of rural hospital closures is challenging due to multiple ongoing changes in rural communities. However, certain factors have been identified. States that did not expand Medicaid under the Affordable Care Act (ACA) saw a higher likelihood of rural hospital closures. Other factors associated with closure include financial instability, declining economic conditions in rural communities, and a higher proportion of for-profit hospitals among recent closures. Additionally, rural patients increasingly bypass local hospitals, opting for care at more distant facilities, which contributes to lower occupancy rates. The reasons for this behavior remain uncertain but could be influenced by perceptions of better-quality care elsewhere or concerns about the adequacy of local hospitals.
Rural hospitals, compared to their urban and suburban counterparts, are smaller in size and face lower occupancy rates, making them more vulnerable to financial instability. Consequently, rural hospitals typically have less than half the median profit margins of urban hospitals.
Regarding the impact of the COVID-19 pandemic on rural hospitals, approximately 21 closures have been recorded since its onset, which aligns with pre-pandemic closure trends. However, some argue that rural hospitals may have been relatively resilient in the face of pandemic-related financial pressures due to the diverse roles played by staff members and the strong community-hospital relationships that were established prior to the pandemic.
Using new econometric methods, researchers have conducted a comprehensive analysis comparing counties with and without hospital closures over time. They examined 10 economic indicators, including healthcare sector jobs, overall unemployment, per capita income, and bankruptcies, providing detailed insights into the relationship between closures and economic conditions. Their findings revealed that only healthcare-sector employment experienced a significant decline, with a 14% reduction in jobs in counties with hospital closures compared to those without closures. Other outcomes, such as overall employment, total jobs, and county population, did not show significant declines. However, the analysis highlights the importance of pre-existing trends, as economies in areas with hospital closures were already deteriorating before the closures. These trends included declining per capita income, total job numbers, and increased unemployment, observed up to seven years before the hospital closures. These findings suggest that factors like unemployment in non-healthcare sectors and a general loss of local investment contribute to low hospital occupancy and financial difficulties, ultimately leading to eventual closures.
Closure Effects & Support
One concern is that rural hospital closures disproportionately affect communities of color. Research indicates that closures are more likely to occur in counties with larger non-white populations. As rural America experiences shifting demographics and increased representation of racial and ethnic minorities, previous studies have shown that rural counties with higher proportions of non-Hispanic Black populations were more prone to losing access to obstetric care. These trends raise apprehension that communities of color may be overrepresented among the populations adversely impacted by hospital closures.
Rural hospitals receive financial support from over 20 programs operated by the Department of Health and Human Services, along with local or state government subsidies and provider taxes. However, despite the availability of these support mechanisms, rural hospitals continue to face ongoing financial challenges.
What should Policymakers do?
To bolster rural health care, policymakers should focus on strengthening rural communities as a whole, considering the broader socioeconomic challenges they face rather than solely addressing health care payment and infrastructure. Policies should be integrated to prioritize improving economic and employment conditions, as these factors have a significant impact on health outcomes. While enhancing rural healthcare delivery remains essential, novel approaches like the Rural Emergency Hospital Program and the Pennsylvania Rural Health Model offer creative solutions. The former allows rural hospitals to convert to emergency departments, maintaining access to emergency care while avoiding unnecessary fixed and overhead costs of inpatient units. The latter, implemented in 2019, provides a "global budget" to rural hospitals, ensuring financial predictability and enabling transformation in patient care through telemedicine and community health worker programs. These approaches adapt to meet the unique needs of different rural communities, providing flexibility alongside financial support. Monitoring the evolution of these programs in the years to come will be crucial and promising.
Resources:
UNC Rural Hospital Closures Tracker – dynamic data for tracking by state the nationwide closures and conversions since 2005. https://www.shepscenter.unc.edu/programs-projects/rural-health/rural-hospital-closures/
Saving Rural Hospitals – another dynamic chart offers granular detail of hospitals with reduced services, closures and profits. https://ruralhospitals.chqpr.org/index.html
Economic Impact of Rural Hospital Closures By: Chris Tachibana, PhD, MS https://ldi.upenn.edu/our-work/research-updates/economic-impact-of-rural-hospital-closures/
ChatGPT is one application that leverages OpenAI’s GPT language prediction model. As of this writing, the GPT-4 version recently rolled out, boasting “human-level performance.” But rather than telling you about this manifestation of an artificial intelligence solution based on my own research, let me conduct an interview with ChatGPT, leveraging its earlier GPT-3 engine. But to make this a bit more entertaining, let’s rename this AI entity “Wall-E”, the personified robot from Pixar’s movie of the same name. The following discussion is taken directly from ChatGPT’s responses to my questions: 
Reading time: about 8 min
Rob Fay: What is a basic overview of OpenAI and its language prediction model?
Wall-E: OpenAI is an artificial intelligence research laboratory consisting of a team of researchers and engineers dedicated to creating advanced AI systems. It was founded in 2015 by a group of tech luminaries, including Elon Musk, Sam Altman, Greg Brockman, Ilya Sutskever, and others.
One of OpenAI's most well-known and groundbreaking projects is its language prediction model, which is also known as GPT (Generative Pre-trained Transformer). GPT is a deep learning model that uses a neural network to analyze and understand natural language text. It can generate human-like text by predicting the next word or phrase based on the context of the preceding text.
GPT is trained on a massive dataset of text from the internet, including books, articles, and websites. The model uses unsupervised learning to learn the patterns and structures of language, allowing it to generate coherent and realistic text without any specific instructions or examples.
GPT has been used for a variety of applications, including language translation, question-answering systems, chatbots, and more. It has set numerous records in natural language processing, such as achieving state-of-the-art results in language modeling, language generation, and machine reading comprehension.
Rob Fay: How can artificial intelligence help the Centers for Medicare and Medicaid Services fulfill its mission?
Wall-E: Artificial intelligence (AI) can help the Centers for Medicare and Medicaid Services (CMS) fulfill its mission in several ways:
- Fraud detection: CMS can use AI to detect fraudulent activities by analyzing large volumes of data to identify unusual patterns and behaviors. This can help prevent improper payments and save money.
- Predictive analytics: AI can be used to predict health outcomes and identify patients who are at risk for certain conditions. This can help CMS develop more targeted and effective programs and interventions to improve health outcomes.
- Claims processing: AI can help CMS process claims more efficiently by automating certain tasks, such as data entry and verification. This can reduce errors and improve the speed and accuracy of claim processing.
- Resource allocation: AI can help CMS optimize resource allocation by analyzing data on patient needs and service utilization. This can help CMS allocate resources more effectively and efficiently, ensuring that patients receive the care they need.
- Personalized medicine: AI can help CMS develop personalized treatment plans for patients by analyzing patient data and identifying patterns and trends. This can help improve health outcomes and reduce healthcare costs by tailoring treatment plans to individual patient needs.
Overall, AI has the potential to help CMS fulfill its mission by improving the efficiency, effectiveness, and quality of healthcare services.
Rob Fay: How can ChatGPT help the Centers for Medicare and Medicaid Services fulfill its mission?
Wall-E: As an AI language model, ChatGPT can help the Centers for Medicare and Medicaid Services (CMS) fulfill its mission in several ways:
- Information dissemination: ChatGPT can provide accurate and up-to-date information about CMS programs and services to beneficiaries, providers, and stakeholders. This can help improve access to information and promote transparency.
- Education and outreach: ChatGPT can help CMS educate beneficiaries and providers about healthcare topics, such as preventive care, chronic disease management, and healthy behaviors. This can help promote better health outcomes and reduce healthcare costs.
- Customer service: ChatGPT can assist beneficiaries and providers with their inquiries and concerns about CMS programs and services. This can help improve customer satisfaction and reduce call center wait times.
- Data analysis: ChatGPT can analyze large volumes of data to identify trends and patterns that can inform policy decisions and program development. This can help CMS develop more effective and efficient healthcare programs and services.
- Quality improvement: ChatGPT can provide feedback and insights to CMS about the quality of healthcare services and the patient experience. This can help CMS identify areas for improvement and develop strategies to enhance the quality of care.
Overall, ChatGPT has the potential to assist CMS in achieving its mission by providing information, education, customer service, data analysis, and quality improvement support.
Rob Fay: What technical positions could be replaced by AI in the future?
Wall-E: Artificial Intelligence (AI) has the potential to automate many tasks and job functions that are currently performed by humans. Here are a few examples of technical positions that could be replaced by AI in the future:
- Data entry and processing: AI can be used to automate many data-related tasks, including data entry, data processing, and data analysis. This could reduce the need for human workers to perform these tasks.
- Quality assurance and testing: AI can be used to automate software testing and quality assurance tasks, which could reduce the need for human testers and improve the speed and accuracy of testing.
- Technical support and customer service: AI-powered chatbots and virtual assistants can be used to provide technical support and customer service, which could reduce the need for human support agents.
- Cybersecurity: AI can be used to automate cybersecurity tasks, including threat detection and response, which could reduce the need for human cybersecurity professionals.
- Manufacturing and assembly line jobs: AI-powered robots and automation systems can be used to perform manufacturing and assembly line tasks, which could reduce the need for human workers.
It's important to note that while AI has the potential to automate many tasks and job functions, it is unlikely to completely replace human workers in the near future. Instead, it is more likely that AI will be used to augment and enhance human capabilities, rather than replace them.
Rob Fay: What are the criticisms of ChatGPT about its biases?
Wall-E: One of the main criticisms of ChatGPT and other language models is that they can exhibit biases based on the data they were trained on. This is because language models learn from large datasets of text, and if these datasets contain biases or stereotypes, the model may learn and replicate those biases in its output.
Here are some specific criticisms of ChatGPT regarding biases:
- Gender and racial biases: Some studies have found that ChatGPT and other language models can exhibit gender and racial biases in their output. For example, the language model may associate certain professions or activities with specific genders or races, which can perpetuate stereotypes and reinforce existing biases.
- Lack of diversity in training data: Another criticism of ChatGPT is that it may not be trained on diverse datasets that represent a wide range of languages, cultures, and perspectives. This can result in biases and inaccuracies in its output when used in contexts that it was not specifically trained for.
- Amplifying harmful content: ChatGPT has also been criticized for its ability to generate and amplify harmful content, such as hate speech or misinformation. This can have negative effects on individuals and society as a whole.
- Ethics and transparency: Some critics have also raised concerns about the ethical implications of using ChatGPT and other language models, and have called for greater transparency in how these models are developed, tested, and deployed.
It's important to note that OpenAI, the organization behind ChatGPT, has acknowledged these criticisms and has taken steps to address them, such as releasing more diverse training datasets and working to reduce biases in its models. However, the issue of biases in AI is complex and ongoing, and there is still much work to be done to ensure that language models like ChatGPT are as fair and accurate as possible.
Rob Fay: Thank you Wall-E, for taking the time (average answer took ~10 seconds) to answer our questions.
If you’d like to learn more about OpenAI or experiment for yourself with ChatGPT, please refer to the following:
- OpenAI - https://openai.com/
- ChatGPT - https://chat.openai.com/chat
- ChatGPT Tutorial - A Crash Course on Chat GPT for Beginners: https://youtu.be/JTxsNm9IdYU
- ChatGPT for iOS: https://apps.apple.com/us/app/chatgpt/id6448311069
ROB FAY
Rob currently leads the CCSQ Human-Centered Design Center of Excellence (HCD CoE). The HCD CoE is an organization that impacts the way the CCSQ delivers policy, products and services to its customers. Through the provision of education, support and resources, he promotes the continued implementation and usage of HCD best practices and seeks to fulfill the charge of OMB Circular A-11 Section 280 (i.e., “Managing Customer Experience and Service Delivery”). For over 20 years Rob has focused on making products and services delightful and easy to use by leading research and design initiatives at government agencies like CMS, NIH, and USPTO and commercial organizations including Blackboard and Allegis Group. Rob holds a Master of Information Management and a Master of Science in Marriage & Family Therapy from the University of Maryland, College Park.