Wähle die Ordner aus, zu welchen Du "QM" hinzufügen oder entfernen möchtest
0 Exakte Antworten
10 Text Antworten
0 Multiple Choice Antworten
Karte wurde gelöscht
Assignment 1 (20 Points) each 5 Points
What is the differentiation between specialized analytical programs like SPSS and a typical spreadsheet program like MS Excel?
Please, name three typical differentiations.
1: SPSS can work with more data points
2: SPSS is able to make use of much more analytical methods
3: SPSS is much faster in overall handling of ordinary and advances analytics
What is estimated concretely in a multiple regression model on the right hand side of the equation?
Summarize one of the Articles mentioned in chapter “0.Introduction of Quantitative Analysis” in one sentence: (Publications from Andrew McAfee, McKinsey, Roland Berger, The Economist, BITKOM)
possible answers: 1. Big Data refers to datasets whose size is beyond the ability of typical database software tools to capture, store, manage and analyze.
2. The rise of Big Data is due to new technologies and the generation of more information (e.g. from customer cards, in social media, mobile applications etc.)
3. The volumes and varieties of data require new analytic technologies („Analytics“). I.e. it is not just about collecting and storing bigger amounts of data
On the McKinsey entry homepage David Court is being seen giving a speech on Big Data. According to his speech what is the formula or what’s the three key success factors for exploiting data analytics?
Data, models, transformation. Data is the creative use of internal and external data to give you a broader view on what is happening to your operations or your customer. Modeling is all about using that data to get workable models that can either help you predict better or allow you to optimize better in terms of your business. And the third success factor is about transforming the company to take advantage of that data in models.
Aufgabe 2 (20 Punkte) / Each 10 Points
a) Name one aspect on which within the family of Linear Models we observe different models. Also, name the corresponding model and mention a practical example.
b) Multinomial Logistic Regression is useful for situations in which you want to be able to classify subjects based on values of a set of predictor variables. This type of regression is similar to binary logistic regression, but is more general because the dependent variable is not restricted to two categories. Please, describe one potential example on the application of such a model in a business situation. Also, describe a possible (short) relationship to a strategy concept (use case).
Two possible solutions listed: 1. For example, you can conduct a survey in which participants are asked to select one of several competing products as their favorite. Using multinomial logistic regression, you can create profiles of people who are most likely to be interested in your product, and plan your advertising strategy accordingly (use case). 2. A telecommunications provider has segmented its customer base by service usage patterns, categorizing the customers into four groups. If demographic data can be used to predict group membership, you can customize offers for individual prospective customers (use case).
Aufgabe 3 (20 Punkte) / Each 5 Points Within our class program we used Binary Logistic Regression to Assess Credit Risk. a) In a first step list the SPSS analysis steps which we used to analyze this case-study.
1. Data Management: sample size was n=850 bank clients, consisting out of 700 clients with a default outcome and 150 without. We created a random sample of 70% from the 700 as a model sample and the rest 30% as the validation sample.
2. Model: We entered the dependent binary variable (default) and the other independent variables into the analysis window. Within the optional model items we defined the categorical variable (education) and selected probabilities and group membership to be saved information. We selected Forward Method LR as a stepwise binary regression procedere
b) What was the aim of the analyses (bold and simple)?
We want to be able to identify characteristics that are indicative of people who are likely to default on loans, and use those characteristics to identify good and bad credit risks.