Case Study Description of Modeling Discrete Choice: Categorical Dependent Variables, Logistic Regression, and Maximum Likelihood Estimation
This technical note introduces business students to the concepts of modeling discrete choice (e.g., a consumer purchasing brand A versus brand B) using logistic regression and maximum-likelihood estimation. It draws the analogy between modeling discrete choice and building a regression model with a dummy dependent variable and on an example illustrates the need for estimating the probability of a choice rather than the choice itself, which leads to a special kind of regression - logistic regression. The note presents the concepts of utility and a random utility choice model, of which the logistic regression model is the most commonly used. It shows how choice probabilities can be constructed from utilities leading to the logit model. It then presents the maximum-likelihood estimation (MLE) method of fitting the logit model to the choice data. Working through a detailed example using Solver and accompanying spreadsheet model, the note gives students deep understanding for how MLE works and how it is similar and different to the standard least-squared estimation in linear regression. The note concludes by presenting the results of estimation using StatTools, a commercial statistical software. The note avoids the use of heavy mathematical machinery but still requires rudimentary knowledge of exponent and logarithmic functions, probability, and optimization with Solver, as well as familiarity with the "standard" linear regression. Applications include building of models for consumer choice, estimating price elasticity, price optimization, product versioning, product line design, and conjoint analysis.
Swot Analysis of "Modeling Discrete Choice: Categorical Dependent Variables, Logistic Regression, and Maximum Likelihood Estimation" written by Anton Ovchinnikov includes – strengths weakness that are internal strategic factors of the organization, and opportunities and threats that Regression Choice facing as an external strategic factors. Some of the topics covered in Modeling Discrete Choice: Categorical Dependent Variables, Logistic Regression, and Maximum Likelihood Estimation case study are - Strategic Management Strategies, Business models, Customers, Financial analysis, Operations management and Technology & Operations.
Some of the macro environment factors that can be used to understand the Modeling Discrete Choice: Categorical Dependent Variables, Logistic Regression, and Maximum Likelihood Estimation casestudy better are - – digital marketing is dominated by two big players Facebook and Google, technology disruption, there is increasing trade war between United States & China, competitive advantages are harder to sustain because of technology dispersion, banking and financial system is disrupted by Bitcoin and other crypto currencies, increasing household debt because of falling income levels, geopolitical disruptions,
wage bills are increasing, increasing government debt because of Covid-19 spendings, etc
Introduction to SWOT Analysis of Modeling Discrete Choice: Categorical Dependent Variables, Logistic Regression, and Maximum Likelihood Estimation
SWOT stands for an organization’s Strengths, Weaknesses, Opportunities and Threats . At Oak Spring University , we believe that protagonist in Modeling Discrete Choice: Categorical Dependent Variables, Logistic Regression, and Maximum Likelihood Estimation case study can use SWOT analysis as a strategic management tool to assess the current internal strengths and weaknesses of the Regression Choice, and to figure out the opportunities and threats in the macro environment – technological, environmental, political, economic, social, demographic, etc in which Regression Choice operates in.
According to Harvard Business Review, 75% of the managers use SWOT analysis for various purposes such as – evaluating current scenario, strategic planning, new venture feasibility, personal growth goals, new market entry, Go To market strategies, portfolio management and strategic trade-off assessment, organizational restructuring, etc.
SWOT Objectives / Importance of SWOT Analysis and SWOT Matrix
SWOT analysis of Modeling Discrete Choice: Categorical Dependent Variables, Logistic Regression, and Maximum Likelihood Estimation can be done for the following purposes –
1. Strategic planning using facts provided in Modeling Discrete Choice: Categorical Dependent Variables, Logistic Regression, and Maximum Likelihood Estimation case study
2. Improving business portfolio management of Regression Choice
3. Assessing feasibility of the new initiative in Technology & Operations field.
4. Making a Technology & Operations topic specific business decision
5. Set goals for the organization
6. Organizational restructuring of Regression Choice
Strengths Modeling Discrete Choice: Categorical Dependent Variables, Logistic Regression, and Maximum Likelihood Estimation | Internal Strategic Factors
What are Strengths in SWOT Analysis / TOWS Matrix / Weighted SWOT Analysis
The strengths of Regression Choice in Modeling Discrete Choice: Categorical Dependent Variables, Logistic Regression, and Maximum Likelihood Estimation Harvard Business Review case study are -
Innovation driven organization
– Regression Choice is one of the most innovative firm in sector. Manager in Modeling Discrete Choice: Categorical Dependent Variables, Logistic Regression, and Maximum Likelihood Estimation Harvard Business Review case study can use Clayton Christensen Disruptive Innovation strategies to further increase the scale of innovtions in the organization.
Highly skilled collaborators
– Regression Choice has highly efficient outsourcing and offshoring strategy. It has resulted in greater operational flexibility and bringing down the costs in highly price sensitive segment. Secondly the value chain collaborators of the firm in Modeling Discrete Choice: Categorical Dependent Variables, Logistic Regression, and Maximum Likelihood Estimation HBR case study have helped the firm to develop new products and bring them quickly to the marketplace.
Operational resilience
– The operational resilience strategy in the Modeling Discrete Choice: Categorical Dependent Variables, Logistic Regression, and Maximum Likelihood Estimation Harvard Business Review case study comprises – understanding the underlying the factors in the industry, building diversified operations across different geographies so that disruption in one part of the world doesn’t impact the overall performance of the firm, and integrating the various business operations and processes through its digital transformation drive.
Superior customer experience
– The customer experience strategy of Regression Choice in the segment is based on four key concepts – personalization, simplification of complex needs, prompt response, and continuous engagement.
Ability to lead change in Technology & Operations field
– Regression Choice is one of the leading players in its industry. Over the years it has not only transformed the business landscape in its segment but also across the whole industry. The ability to lead change has enabled Regression Choice in – penetrating new markets, reaching out to new customers, and providing different value propositions to different customers in the international markets.
Sustainable margins compare to other players in Technology & Operations industry
– Modeling Discrete Choice: Categorical Dependent Variables, Logistic Regression, and Maximum Likelihood Estimation firm has clearly differentiated products in the market place. This has enabled Regression Choice to fetch slight price premium compare to the competitors in the Technology & Operations industry. The sustainable margins have also helped Regression Choice to invest into research and development (R&D) and innovation.
Low bargaining power of suppliers
– Suppliers of Regression Choice in the sector have low bargaining power. Modeling Discrete Choice: Categorical Dependent Variables, Logistic Regression, and Maximum Likelihood Estimation has further diversified its suppliers portfolio by building a robust supply chain across various countries. This helps Regression Choice to manage not only supply disruptions but also source products at highly competitive prices.
High brand equity
– Regression Choice has strong brand awareness and brand recognition among both - the exiting customers and potential new customers. Strong brand equity has enabled Regression Choice to keep acquiring new customers and building profitable relationship with both the new and loyal customers.
Learning organization
- Regression Choice is a learning organization. It has inculcated three key characters of learning organization in its processes and operations – exploration, creativity, and expansiveness. The work place at Regression Choice is open place that encourages instructiveness, ideation, open minded discussions, and creativity. Employees and leaders in Modeling Discrete Choice: Categorical Dependent Variables, Logistic Regression, and Maximum Likelihood Estimation Harvard Business Review case study emphasize – knowledge, initiative, and innovation.
Digital Transformation in Technology & Operations segment
- digital transformation varies from industry to industry. For Regression Choice digital transformation journey comprises differing goals based on market maturity, customer technology acceptance, and organizational culture. Regression Choice has successfully integrated the four key components of digital transformation – digital integration in processes, digital integration in marketing and customer relationship management, digital integration into the value chain, and using technology to explore new products and market opportunities.
High switching costs
– The high switching costs that Regression Choice has built up over years in its products and services combo offer has resulted in high retention of customers, lower marketing costs, and greater ability of the firm to focus on its customers.
Diverse revenue streams
– Regression Choice is present in almost all the verticals within the industry. This has provided firm in Modeling Discrete Choice: Categorical Dependent Variables, Logistic Regression, and Maximum Likelihood Estimation case study a diverse revenue stream that has helped it to survive disruptions such as global pandemic in Covid-19, financial disruption of 2008, and supply chain disruption of 2021.
Weaknesses Modeling Discrete Choice: Categorical Dependent Variables, Logistic Regression, and Maximum Likelihood Estimation | Internal Strategic Factors
What are Weaknesses in SWOT Analysis / TOWS Matrix / Weighted SWOT Analysis
The weaknesses of Modeling Discrete Choice: Categorical Dependent Variables, Logistic Regression, and Maximum Likelihood Estimation are -
No frontier risks strategy
– After analyzing the HBR case study Modeling Discrete Choice: Categorical Dependent Variables, Logistic Regression, and Maximum Likelihood Estimation, it seems that company is thinking about the frontier risks that can impact Technology & Operations strategy. But it has very little resources allocation to manage the risks emerging from events such as natural disasters, climate change, melting of permafrost, tacking the rise of artificial intelligence, opportunities and threats emerging from commercialization of space etc.
High dependence on star products
– The top 2 products and services of the firm as mentioned in the Modeling Discrete Choice: Categorical Dependent Variables, Logistic Regression, and Maximum Likelihood Estimation HBR case study still accounts for major business revenue. This dependence on star products in has resulted into insufficient focus on developing new products, even though Regression Choice has relatively successful track record of launching new products.
High operating costs
– Compare to the competitors, firm in the HBR case study Modeling Discrete Choice: Categorical Dependent Variables, Logistic Regression, and Maximum Likelihood Estimation has high operating costs in the. This can be harder to sustain given the new emerging competition from nimble players who are using technology to attract Regression Choice 's lucrative customers.
Compensation and incentives
– The revenue per employee as mentioned in the HBR case study Modeling Discrete Choice: Categorical Dependent Variables, Logistic Regression, and Maximum Likelihood Estimation, is just above the industry average. Regression Choice needs to redesign the compensation structure and incentives to increase the revenue per employees. Some of the steps that it can take are – hiring more specialists on project basis, etc.
Skills based hiring
– The stress on hiring functional specialists at Regression Choice has created an environment where the organization is dominated by functional specialists rather than management generalist. This has resulted into product oriented approach rather than marketing oriented approach or consumers oriented approach.
Lack of clear differentiation of Regression Choice products
– To increase the profitability and margins on the products, Regression Choice needs to provide more differentiated products than what it is currently offering in the marketplace.
Ability to respond to the competition
– As the decision making is very deliberative, highlighted in the case study Modeling Discrete Choice: Categorical Dependent Variables, Logistic Regression, and Maximum Likelihood Estimation, in the dynamic environment Regression Choice has struggled to respond to the nimble upstart competition. Regression Choice has reasonably good record with similar level competitors but it has struggled with new entrants taking away niches of its business.
High bargaining power of channel partners
– Because of the regulatory requirements, Anton Ovchinnikov suggests that, Regression Choice is facing high bargaining power of the channel partners. So far it has not able to streamline the operations to reduce the bargaining power of the value chain partners in the industry.
Capital Spending Reduction
– Even during the low interest decade, Regression Choice has not been able to do capital spending to the tune of the competition. This has resulted into fewer innovations and company facing stiff competition from both existing competitors and new entrants who are disrupting the industry using digital technology.
High cash cycle compare to competitors
Regression Choice has a high cash cycle compare to other players in the industry. It needs to shorten the cash cycle by 12% to be more competitive in the marketplace, reduce inventory costs, and be more profitable.
Slow to harness new channels of communication
– Even though competitors are using new communication channels such as Instagram, Tiktok, and Snap, Regression Choice is slow explore the new channels of communication. These new channels of communication mentioned in marketing section of case study Modeling Discrete Choice: Categorical Dependent Variables, Logistic Regression, and Maximum Likelihood Estimation can help to provide better information regarding products and services. It can also build an online community to further reach out to potential customers.
Opportunities Modeling Discrete Choice: Categorical Dependent Variables, Logistic Regression, and Maximum Likelihood Estimation | External Strategic Factors
What are Opportunities in the SWOT Analysis / TOWS Matrix / Weighted SWOT Analysis
The opportunities highlighted in the Harvard Business Review case study Modeling Discrete Choice: Categorical Dependent Variables, Logistic Regression, and Maximum Likelihood Estimation are -
Use of Bitcoin and other crypto currencies for transactions
– The popularity of Bitcoin and other crypto currencies as asset class and medium of transaction has opened new opportunities for Regression Choice in the consumer business. Now Regression Choice can target international markets with far fewer capital restrictions requirements than the existing system.
Better consumer reach
– The expansion of the 5G network will help Regression Choice to increase its market reach. Regression Choice will be able to reach out to new customers. Secondly 5G will also provide technology framework to build new tools and products that can help more immersive consumer experience and faster consumer journey.
Low interest rates
– Even though inflation is raising its head in most developed economies, Regression Choice can still utilize the low interest rates to borrow money for capital investment. Secondly it can also use the increase of government spending in infrastructure projects to get new business.
Learning at scale
– Online learning technologies has now opened space for Regression Choice to conduct training and development for its employees across the world. This will result in not only reducing the cost of training but also help employees in different part of the world to integrate with the headquarter work culture, ethos, and standards.
Building a culture of innovation
– managers at Regression Choice can make experimentation a productive activity and build a culture of innovation using approaches such as – mining transaction data, A/B testing of websites and selling platforms, engaging potential customers over various needs, and building on small ideas in the Technology & Operations segment.
Reforming the budgeting process
- By establishing new metrics that will be used to evaluate both existing and potential projects Regression Choice can not only reduce the costs of the project but also help it in integrating the projects with other processes within the organization.
Remote work and new talent hiring opportunities
– The widespread usage of remote working technologies during Covid-19 has opened opportunities for Regression Choice to expand its talent hiring zone. According to McKinsey Global Institute, 20% of the high end workforce in fields such as finance, information technology, can continously work from remote local post Covid-19. This presents a really great opportunity for Regression Choice to hire the very best people irrespective of their geographical location.
Lowering marketing communication costs
– 5G expansion will open new opportunities for Regression Choice in the field of marketing communication. It will bring down the cost of doing business, provide technology platform to build new products in the Technology & Operations segment, and it will provide faster access to the consumers.
Loyalty marketing
– Regression Choice has focused on building a highly responsive customer relationship management platform. This platform is built on in-house data and driven by analytics and artificial intelligence. The customer analytics can help the organization to fine tune its loyalty marketing efforts, increase the wallet share of the organization, reduce wastage on mainstream advertising spending, build better pricing strategies using personalization, etc.
Creating value in data economy
– The success of analytics program of Regression Choice has opened avenues for new revenue streams for the organization in the industry. This can help Regression Choice to build a more holistic ecosystem as suggested in the Modeling Discrete Choice: Categorical Dependent Variables, Logistic Regression, and Maximum Likelihood Estimation case study. Regression Choice can build new products and services such as - data insight services, data privacy related products, data based consulting services, etc.
Manufacturing automation
– Regression Choice can use the latest technology developments to improve its manufacturing and designing process in Technology & Operations segment. It can use CAD and 3D printing to build a quick prototype and pilot testing products. It can leverage automation using machine learning and artificial intelligence to do faster production at lowers costs, and it can leverage the growth in satellite and tracking technologies to improve inventory management, transportation, and shipping.
Developing new processes and practices
– Regression Choice can develop new processes and procedures in Technology & Operations industry using technology such as automation using artificial intelligence, real time transportation and products tracking, 3D modeling for concept development and new products pilot testing etc.
Redefining models of collaboration and team work
– As explained in the weaknesses section, Regression Choice is facing challenges because of the dominance of functional experts in the organization. Modeling Discrete Choice: Categorical Dependent Variables, Logistic Regression, and Maximum Likelihood Estimation case study suggests that firm can utilize new technology to build more coordinated teams and streamline operations and communications using tools such as CAD, Zoom, etc.
Threats Modeling Discrete Choice: Categorical Dependent Variables, Logistic Regression, and Maximum Likelihood Estimation External Strategic Factors
What are Threats in the SWOT Analysis / TOWS Matrix / Weighted SWOT Analysis
The threats mentioned in the HBR case study Modeling Discrete Choice: Categorical Dependent Variables, Logistic Regression, and Maximum Likelihood Estimation are -
Consumer confidence and its impact on Regression Choice demand
– There is a high probability of declining consumer confidence, given – high inflammation rate, rise of gig economy, lower job stability, increasing cost of living, higher interest rates, and aging demography. All the factors contribute to people saving higher rate of their income, resulting in lower consumer demand in the industry and other sectors.
Barriers of entry lowering
– As technology is more democratized, the barriers to entry in the industry are lowering. It can presents Regression Choice with greater competitive threats in the near to medium future. Secondly it will also put downward pressure on pricing throughout the sector.
Easy access to finance
– Easy access to finance in Technology & Operations field will also reduce the barriers to entry in the industry, thus putting downward pressure on the prices because of increasing competition. Regression Choice can utilize it by borrowing at lower rates and invest it into research and development, capital expenditure to fortify its core competitive advantage.
Aging population
– As the populations of most advanced economies are aging, it will lead to high social security costs, higher savings among population, and lower demand for goods and services in the economy. The household savings in US, France, UK, Germany, and Japan are growing faster than predicted because of uncertainty caused by pandemic.
Increasing international competition and downward pressure on margins
– Apart from technology driven competitive advantage dilution, Regression Choice can face downward pressure on margins from increasing competition from international players. The international players have stable revenue in their home market and can use those resources to penetrate prominent markets illustrated in HBR case study Modeling Discrete Choice: Categorical Dependent Variables, Logistic Regression, and Maximum Likelihood Estimation .
Instability in the European markets
– European Union markets are facing three big challenges post Covid – expanded balance sheets, Brexit related business disruption, and aggressive Russia looking to distract the existing security mechanism. Regression Choice will face different problems in different parts of Europe. For example it will face inflationary pressures in UK, France, and Germany, balance sheet expansion and demand challenges in Southern European countries, and geopolitical instability in the Eastern Europe.
Stagnating economy with rate increase
– Regression Choice can face lack of demand in the market place because of Fed actions to reduce inflation. This can lead to sluggish growth in the economy, lower demands, lower investments, higher borrowing costs, and consolidation in the field.
High level of anxiety and lack of motivation
– the Great Resignation in United States is the sign of broader dissatisfaction among the workforce in United States. Regression Choice needs to understand the core reasons impacting the Technology & Operations industry. This will help it in building a better workplace.
New competition
– After the dotcom bust of 2001, financial crisis of 2008-09, the business formation in US economy had declined. But in 2020 alone, there are more than 1.5 million new business applications in United States. This can lead to greater competition for Regression Choice in the Technology & Operations sector and impact the bottomline of the organization.
Technology acceleration in Forth Industrial Revolution
– Regression Choice has witnessed rapid integration of technology during Covid-19 in the Technology & Operations industry. As one of the leading players in the industry, Regression Choice needs to keep up with the evolution of technology in the Technology & Operations sector. According to Mckinsey study top managers believe that the adoption of technology in operations, communications is 20-25 times faster than what they planned in the beginning of 2019.
Environmental challenges
– Regression Choice needs to have a robust strategy against the disruptions arising from climate change and energy requirements. EU has identified it as key priority area and spending 30% of its 880 billion Euros European post Covid-19 recovery funds on green technology. Regression Choice can take advantage of this fund but it will also bring new competitors in the Technology & Operations industry.
Regulatory challenges
– Regression Choice needs to prepare for regulatory challenges as consumer protection groups and other pressure groups are vigorously advocating for more regulations on big business - to reduce inequality, to create a level playing field, to product data privacy and consumer privacy, to reduce the influence of big money on democratic institutions, etc. This can lead to significant changes in the Technology & Operations industry regulations.
Learning curve for new practices
– As the technology based on artificial intelligence and machine learning platform is getting complex, as highlighted in case study Modeling Discrete Choice: Categorical Dependent Variables, Logistic Regression, and Maximum Likelihood Estimation, Regression Choice may face longer learning curve for training and development of existing employees. This can open space for more nimble competitors in the field of Technology & Operations .
Weighted SWOT Analysis of Modeling Discrete Choice: Categorical Dependent Variables, Logistic Regression, and Maximum Likelihood Estimation Template, Example
Not all factors mentioned under the Strengths, Weakness, Opportunities, and Threats quadrants in the SWOT Analysis are equal. Managers in the HBR case study Modeling Discrete Choice: Categorical Dependent Variables, Logistic Regression, and Maximum Likelihood Estimation needs to zero down on the relative importance of each factor mentioned in the Strengths, Weakness, Opportunities, and Threats quadrants.
We can provide the relative importance to each factor by assigning relative weights. Weighted SWOT analysis process is a three stage process –
First stage for doing weighted SWOT analysis of the case study Modeling Discrete Choice: Categorical Dependent Variables, Logistic Regression, and Maximum Likelihood Estimation is to rank the strengths and weaknesses of the organization. This will help you to assess the most important strengths and weaknesses of the firm and which one of the strengths and weaknesses mentioned in the initial lists are marginal and can be left out.
Second stage for conducting weighted SWOT analysis of the Harvard case study Modeling Discrete Choice: Categorical Dependent Variables, Logistic Regression, and Maximum Likelihood Estimation is to give probabilities to the external strategic factors thus better understanding the opportunities and threats arising out of macro environment changes and developments.
Third stage of constructing weighted SWOT analysis of Modeling Discrete Choice: Categorical Dependent Variables, Logistic Regression, and Maximum Likelihood Estimation is to provide strategic recommendations includes – joining likelihood of external strategic factors such as opportunities and threats to the internal strategic factors – strengths and weaknesses. You should start with external factors as they will provide the direction of the overall industry. Secondly by joining probabilities with internal strategic factors can help the company not only strategic fit but also the most probably strategic trade-off that Regression Choice needs to make to build a sustainable competitive advantage.
Feel free to connect with us if you need business research.
You can download Excel Template of Case Study Solution & Analysis of Modeling Discrete Choice: Categorical Dependent Variables, Logistic Regression, and Maximum Likelihood Estimation