1. The document describes tests performed to analyze survey data on perceptions of a hypothetical car (Nano). Kolmogorov-Smirnov tests found some variables were not normally distributed.
2. Levene's tests found variances were equal (homogeneous) for variables testing the relationship between occupation and value for money, and occupation and current vehicle owned.
3. ANOVA tests found perceived value for money did not differ by occupation, but current vehicle owned did differ significantly by occupation.
Isaf2007 Presentation Bst Ito Funakubo KoutsaroffIvo Koutsaroff
油
1. The document discusses the effect of strain from the substrate on the tunability of (100) one-axis oriented (Ba0.5Sr0.5)TiO3 thin films.
2. (Ba,Sr)TiO3 films were prepared on substrates with different thermal expansion coefficients to induce varying degrees of tensile and compressive strain. The dielectric properties of the films were then characterized.
3. The results showed that the relative dielectric constant and tunability of the films increased with compressive strain and decreased with tensile strain, consistent with expectations based on thermal strain calculations and previous literature.
The document summarizes research on characterizing the in-plane relative permittivity of Sr(n+1)Ti(n)O3n+1 Ruddlesden-Popper thin films. It describes how thin film growth enables the study of this material system as a function of thickness and strain. X-ray diffraction measurements show the expected number of diffraction peaks based on the series number n. Future challenges are noted in fully characterizing the materials due to the complexity of the measurements required.
The document discusses various properties of engineering materials that are important for mechanical design. It describes six main families of materials - metals, ceramics, glasses, polymers, elastomers, and hybrid materials. Within each family, materials share common properties, such as ceramics being hard, brittle, and corrosion resistant, while metals are ductile, tough, and good conductors. The document outlines key mechanical, thermal, electrical, optical, environmental resistance, and eco-friendly properties of materials. It emphasizes that successful design requires matching the right material with the required properties for the application.
This document discusses a one sample runs test, which is used to determine if a sample is randomly drawn from a population. It defines a run as a series of like items. The document provides an example of coin flips and illustrates how different outcomes would indicate random or non-random patterns. It presents the formula for the runs test and applies it to an example of testing if diseased trees are randomly or non-randomly grouped. The requirements, advantages, and other applications of the runs test are outlined.
Simulation - Generating Continuous Random VariablesMartin Kretzer
油
The document discusses various methods for generating continuous random variables in simulations, including the inverse transform method and acceptance-rejection method. It provides examples of how to generate random variables from important distributions like the exponential, normal, Poisson, and nonhomogeneous Poisson distributions. The agenda includes an introduction, overview of methods, generating specific distributions, summary, and exercises in R to apply the methods.
Xi Zhang presented their Ph.D. dissertation which analyzed functional regression models and their application to high-frequency financial data. The presentation included:
1. An introduction to functional data analysis and the use of intraday cumulative return curves from stock price data.
2. A simulation study comparing predictive methods in functional autoregressive models, finding the estimated kernel method performed well.
3. An application of functional extensions of the Capital Asset Pricing Model to predict intraday return curves, finding simpler models with intercepts had better predictive performance than more complex models.
A pseudo random number generator (PRNG) is a mechanism for generating random numbers that appear random but are determined by an algorithm. PRNGs are important in cryptography as they are used to generate keys, initialization vectors, and other random values needed for encryption. Good PRNGs should produce numbers that are evenly distributed, unpredictable, and have a long repeating cycle. The RSA algorithm is one example of a PRNG that uses exponentiation modulo a large prime number to generate a stream of pseudorandom bits.
This document discusses tests for random number generation, including the autocorrelation test, gap test, and poker test. The autocorrelation test examines dependence between numbers in a sequence. The gap test analyzes the length of gaps between numbers that fall within a given range. The poker test categorizes groups of five consecutive numbers based on arrangements like pairs, three of a kind, etc. and applies a chi-squared test to assess randomness.
This document discusses methods for generating and testing random numbers. There are two main types of random number generators discussed: combined generators and inversive generators. Combined generators work by combining the outputs of two or more simpler random number generators. They are useful for simulating highly reliable systems or complex networks. The document also discusses how to test random numbers using the Kolmogorov-Smirnov test and runs tests. The Kolmogorov-Smirnov test compares the cumulative distribution function of observed values to expected values, while runs tests examine the arrangements of values in a sequence. Both can be used to determine if a random number generator is producing independent and identically distributed values.
The Kolmogorov-Smirnov test is used to test if an observed frequency distribution matches an expected theoretical distribution. It compares the cumulative distribution functions of the observed and expected distributions. The test statistic is the largest difference between these cumulative distributions. If this difference is larger than a critical value from tables, the null hypothesis of a good fit is rejected. An example calculates the test statistic for observed data compared to a normal distribution, and finds it is less than the critical value so the null hypothesis is accepted.
This document discusses random number generation and properties of pseudo-random numbers. It covers techniques for generating pseudo-random numbers like linear congruential methods and combined congruential methods. It also discusses hypothesis tests that can be used to test for uniformity and independence of random numbers, such as the frequency test, Kolmogorov-Smirnov test, chi-square test, runs test, and autocorrelation test.
This chapter discusses continuous random variables and their probability density functions. It introduces the normal and exponential distributions and how to calculate probabilities and descriptive statistics for continuous random variables. It also shows how to approximate the binomial distribution using the normal distribution. The key topics covered are continuous random variables, the normal distribution, finding mean and standard deviation, and the normal approximation to the binomial distribution.
Student's T-test, Paired T-Test, ANOVA & Proportionate TestAzmi Mohd Tamil
油
This document discusses various statistical tests including the T-test, ANOVA, and proportionate tests. It provides details on the independent T-test, paired T-test, ANOVA, and examples of using each test. Key concepts covered include the Student's T-test, its assumptions, and how to perform manual calculations and analyze data using SPSS.
The chi-square test is used to determine if an observed frequency distribution differs from an expected theoretical distribution. It can test goodness of fit, independence of attributes, and homogeneity. The test involves calculating chi-square by taking the sum of the squares of the differences between observed and expected frequencies divided by expected frequencies. For the test to be valid, certain conditions must be met regarding sample size, expected frequencies, independence, and randomness. The test has some limitations such as not measuring strength of association and being unreliable with small expected frequencies.
Random testing involves generating test inputs randomly without following a systematic strategy. It was first mentioned in 1979 by Glenford Myers. Random testing can be used to estimate software reliability by recording failures from randomly generated test inputs according to an operational profile. The main advantages are that it is easy to implement, allows testing a large number of cases, and can find defects that systematic testing may miss. However, it is not as effective as other techniques at finding certain types of defects and results must be carefully analyzed. Random testing is best suited for domains with well-defined boundaries and when time for testing is limited.
Getting the Best of TrueDEM April News & Updatespanagenda
油
Webinar Recording: https://www.panagenda.com/webinars/getting-the-best-of-truedem-april-news-updates/
Boost your Microsoft 365 experience with OfficeExpert TrueDEM! Join the April webinar for a deep dive into recent and upcoming features and functionalities of OfficeExpert TrueDEM. Well showcase whats new and use practical application examples and real-life scenarios, to demonstrate how to leverage TrueDEM to optimize your M365 environment, troubleshoot issues, improve user satisfaction and productivity, and ultimately make data-driven business decisions.
These sessions will be led by our team of product management and consultants, who interact with customers daily and possess in-depth product knowledge, providing valuable insights and expert guidance.
What youll take away
- Updates & info about the latest and upcoming features of TrueDEM
- Practical and realistic applications & examples for troubelshooting or improving your Microsoft Teams & M365 environment
- Use cases and examples of how our customers use TrueDEM
The Future of Materials: Transitioning from Silicon to Alternative Metalsanupriti
油
This presentation delves into the emerging technologies poised to revolutionize the world of computing. From carbon nanotubes and graphene to quantum computing and DNA-based systems, discover the next-generation materials and innovations that could replace or complement traditional silicon chips. Explore the future of computing and the breakthroughs that are shaping a more efficient, faster, and sustainable technological landscape.
Research Data Management (RDM): the management of dat in the research processHeilaPienaar
油
Presented as part of the M.IT degree at the Department of Information Science, University of Pretoria, South Africa. Module: Data management. 2023, 2024.
Recruiting Tech: A Look at Why AI is Actually OGMatt Charney
油
A lot of recruiting technology vendors out there are talking about how they're offering the first ever (insert AI use case here), but turns out, everything they're selling as innovative or cutting edge has been around since Yahoo! and MySpace were category killers. Here's the receipts.
Packaging your App for AppExchange Managed Vs Unmanaged.pptxmohayyudin7826
油
Learn how to package your app for Salesforce AppExchange with a deep dive into managed vs. unmanaged packages. Understand the best strategies for ISV success and choosing the right approach for your app development goals.
AI in Talent Acquisition: Boosting HiringBeyond Chiefs
油
AI is transforming talent acquisition by streamlining recruitment processes, enhancing decision-making, and delivering personalized candidate experiences. By automating repetitive tasks such as resume screening and interview scheduling, AI significantly reduces hiring costs and improves efficiency, allowing HR teams to focus on strategic initiatives. Additionally, AI-driven analytics help recruiters identify top talent more accurately, leading to better hiring decisions. However, despite these advantages, organizations must address challenges such as AI bias, integration complexities, and resistance to adoption to fully realize its potential. Embracing AI in recruitment can provide a competitive edge, but success depends on aligning technology with business goals and ensuring ethical, unbiased implementation.
Next.js Development: The Ultimate Solution for High-Performance Web Appsrwinfotech31
油
The key benefits of Next.js development, including blazing-fast performance, enhanced SEO, seamless API and database integration, scalability, and expert support. It showcases how Next.js leverages Server-Side Rendering (SSR), Static Site Generation (SSG), and other advanced technologies to optimize web applications. RW Infotech offers custom solutions, migration services, and 24/7 expert support for seamless Next.js operations. Explore more :- https://www.rwit.io/technologies/next-js
Most people might think of a water faucet or even the tap on a keg of beer. But in the world of networking, "TAP" stands for "Traffic Access Point" or "Test Access Point." It's not a beverage or a sink fixture, but rather a crucial tool for network monitoring and testing. Khushi Communications is a top vendor in India, providing world-class Network TAP solutions. With their expertise, they help businesses monitor, analyze, and secure their networks efficiently.
Automated Engineering of Domain-Specific Metamorphic Testing EnvironmentsPablo G坦mez Abajo
油
Context. Testing is essential to improve the correctness of software systems. Metamorphic testing (MT) is an approach especially suited when the system under test lacks oracles, or they are expensive to compute. However, building an MT environment for a particular domain (e.g., cloud simulation, model transformation, machine learning) requires substantial effort.
Objective. Our goal is to facilitate the construction of MT environments for specific domains.
Method. We propose a model-driven engineering approach to automate the construction of MT environments. Starting from a meta-model capturing the domain concepts, and a description of the domain execution environment, our approach produces an MT environment featuring comprehensive support for the MT process. This includes the definition of domain-specific metamorphic relations, their evaluation, detailed reporting of the testing results, and the automated search-based generation of follow-up test cases.
Results. Our method is supported by an extensible platform for Eclipse, called Gotten. We demonstrate its effectiveness by creating an MT environment for simulation-based testing of data centres and comparing with existing tools; its suitability to conduct MT processes by replicating previous experiments; and its generality by building another MT environment for video streaming APIs.
Conclusion. Gotten is the first platform targeted at reducing the development effort of domain-specific MT environments. The environments created with Gotten facilitate the specification of metamorphic relations, their evaluation, and the generation of new test cases.
Testing Tools for Accessibility Enhancement Part II.pptxJulia Undeutsch
油
Automatic Testing Tools will help you get a first understanding of the accessibility of your website or web application. If you are new to accessibility, it will also help you learn more about the topic and the different issues that are occurring on the web when code is not properly written.
This document discusses methods for generating and testing random numbers. There are two main types of random number generators discussed: combined generators and inversive generators. Combined generators work by combining the outputs of two or more simpler random number generators. They are useful for simulating highly reliable systems or complex networks. The document also discusses how to test random numbers using the Kolmogorov-Smirnov test and runs tests. The Kolmogorov-Smirnov test compares the cumulative distribution function of observed values to expected values, while runs tests examine the arrangements of values in a sequence. Both can be used to determine if a random number generator is producing independent and identically distributed values.
The Kolmogorov-Smirnov test is used to test if an observed frequency distribution matches an expected theoretical distribution. It compares the cumulative distribution functions of the observed and expected distributions. The test statistic is the largest difference between these cumulative distributions. If this difference is larger than a critical value from tables, the null hypothesis of a good fit is rejected. An example calculates the test statistic for observed data compared to a normal distribution, and finds it is less than the critical value so the null hypothesis is accepted.
This document discusses random number generation and properties of pseudo-random numbers. It covers techniques for generating pseudo-random numbers like linear congruential methods and combined congruential methods. It also discusses hypothesis tests that can be used to test for uniformity and independence of random numbers, such as the frequency test, Kolmogorov-Smirnov test, chi-square test, runs test, and autocorrelation test.
This chapter discusses continuous random variables and their probability density functions. It introduces the normal and exponential distributions and how to calculate probabilities and descriptive statistics for continuous random variables. It also shows how to approximate the binomial distribution using the normal distribution. The key topics covered are continuous random variables, the normal distribution, finding mean and standard deviation, and the normal approximation to the binomial distribution.
Student's T-test, Paired T-Test, ANOVA & Proportionate TestAzmi Mohd Tamil
油
This document discusses various statistical tests including the T-test, ANOVA, and proportionate tests. It provides details on the independent T-test, paired T-test, ANOVA, and examples of using each test. Key concepts covered include the Student's T-test, its assumptions, and how to perform manual calculations and analyze data using SPSS.
The chi-square test is used to determine if an observed frequency distribution differs from an expected theoretical distribution. It can test goodness of fit, independence of attributes, and homogeneity. The test involves calculating chi-square by taking the sum of the squares of the differences between observed and expected frequencies divided by expected frequencies. For the test to be valid, certain conditions must be met regarding sample size, expected frequencies, independence, and randomness. The test has some limitations such as not measuring strength of association and being unreliable with small expected frequencies.
Random testing involves generating test inputs randomly without following a systematic strategy. It was first mentioned in 1979 by Glenford Myers. Random testing can be used to estimate software reliability by recording failures from randomly generated test inputs according to an operational profile. The main advantages are that it is easy to implement, allows testing a large number of cases, and can find defects that systematic testing may miss. However, it is not as effective as other techniques at finding certain types of defects and results must be carefully analyzed. Random testing is best suited for domains with well-defined boundaries and when time for testing is limited.
Getting the Best of TrueDEM April News & Updatespanagenda
油
Webinar Recording: https://www.panagenda.com/webinars/getting-the-best-of-truedem-april-news-updates/
Boost your Microsoft 365 experience with OfficeExpert TrueDEM! Join the April webinar for a deep dive into recent and upcoming features and functionalities of OfficeExpert TrueDEM. Well showcase whats new and use practical application examples and real-life scenarios, to demonstrate how to leverage TrueDEM to optimize your M365 environment, troubleshoot issues, improve user satisfaction and productivity, and ultimately make data-driven business decisions.
These sessions will be led by our team of product management and consultants, who interact with customers daily and possess in-depth product knowledge, providing valuable insights and expert guidance.
What youll take away
- Updates & info about the latest and upcoming features of TrueDEM
- Practical and realistic applications & examples for troubelshooting or improving your Microsoft Teams & M365 environment
- Use cases and examples of how our customers use TrueDEM
The Future of Materials: Transitioning from Silicon to Alternative Metalsanupriti
油
This presentation delves into the emerging technologies poised to revolutionize the world of computing. From carbon nanotubes and graphene to quantum computing and DNA-based systems, discover the next-generation materials and innovations that could replace or complement traditional silicon chips. Explore the future of computing and the breakthroughs that are shaping a more efficient, faster, and sustainable technological landscape.
Research Data Management (RDM): the management of dat in the research processHeilaPienaar
油
Presented as part of the M.IT degree at the Department of Information Science, University of Pretoria, South Africa. Module: Data management. 2023, 2024.
Recruiting Tech: A Look at Why AI is Actually OGMatt Charney
油
A lot of recruiting technology vendors out there are talking about how they're offering the first ever (insert AI use case here), but turns out, everything they're selling as innovative or cutting edge has been around since Yahoo! and MySpace were category killers. Here's the receipts.
Packaging your App for AppExchange Managed Vs Unmanaged.pptxmohayyudin7826
油
Learn how to package your app for Salesforce AppExchange with a deep dive into managed vs. unmanaged packages. Understand the best strategies for ISV success and choosing the right approach for your app development goals.
AI in Talent Acquisition: Boosting HiringBeyond Chiefs
油
AI is transforming talent acquisition by streamlining recruitment processes, enhancing decision-making, and delivering personalized candidate experiences. By automating repetitive tasks such as resume screening and interview scheduling, AI significantly reduces hiring costs and improves efficiency, allowing HR teams to focus on strategic initiatives. Additionally, AI-driven analytics help recruiters identify top talent more accurately, leading to better hiring decisions. However, despite these advantages, organizations must address challenges such as AI bias, integration complexities, and resistance to adoption to fully realize its potential. Embracing AI in recruitment can provide a competitive edge, but success depends on aligning technology with business goals and ensuring ethical, unbiased implementation.
Next.js Development: The Ultimate Solution for High-Performance Web Appsrwinfotech31
油
The key benefits of Next.js development, including blazing-fast performance, enhanced SEO, seamless API and database integration, scalability, and expert support. It showcases how Next.js leverages Server-Side Rendering (SSR), Static Site Generation (SSG), and other advanced technologies to optimize web applications. RW Infotech offers custom solutions, migration services, and 24/7 expert support for seamless Next.js operations. Explore more :- https://www.rwit.io/technologies/next-js
Most people might think of a water faucet or even the tap on a keg of beer. But in the world of networking, "TAP" stands for "Traffic Access Point" or "Test Access Point." It's not a beverage or a sink fixture, but rather a crucial tool for network monitoring and testing. Khushi Communications is a top vendor in India, providing world-class Network TAP solutions. With their expertise, they help businesses monitor, analyze, and secure their networks efficiently.
Automated Engineering of Domain-Specific Metamorphic Testing EnvironmentsPablo G坦mez Abajo
油
Context. Testing is essential to improve the correctness of software systems. Metamorphic testing (MT) is an approach especially suited when the system under test lacks oracles, or they are expensive to compute. However, building an MT environment for a particular domain (e.g., cloud simulation, model transformation, machine learning) requires substantial effort.
Objective. Our goal is to facilitate the construction of MT environments for specific domains.
Method. We propose a model-driven engineering approach to automate the construction of MT environments. Starting from a meta-model capturing the domain concepts, and a description of the domain execution environment, our approach produces an MT environment featuring comprehensive support for the MT process. This includes the definition of domain-specific metamorphic relations, their evaluation, detailed reporting of the testing results, and the automated search-based generation of follow-up test cases.
Results. Our method is supported by an extensible platform for Eclipse, called Gotten. We demonstrate its effectiveness by creating an MT environment for simulation-based testing of data centres and comparing with existing tools; its suitability to conduct MT processes by replicating previous experiments; and its generality by building another MT environment for video streaming APIs.
Conclusion. Gotten is the first platform targeted at reducing the development effort of domain-specific MT environments. The environments created with Gotten facilitate the specification of metamorphic relations, their evaluation, and the generation of new test cases.
Testing Tools for Accessibility Enhancement Part II.pptxJulia Undeutsch
油
Automatic Testing Tools will help you get a first understanding of the accessibility of your website or web application. If you are new to accessibility, it will also help you learn more about the topic and the different issues that are occurring on the web when code is not properly written.
GDG on Campus Monash hosted Info Session to provide details of the Solution Challenge to promote participation and hosted networking activities to help participants find their dream team
How Telemedicine App Development is Revolutionizing Virtual Care.pptxDash Technologies Inc
油
Telemedicine app development builds software for remote doctor consultations and patient check-ups. These apps bridge healthcare professionals with patients via video calls, secure messages, and interactive interfaces. That helps practitioners to provide care without immediate face-to-face interactions; hence, simplifying access to medical care. Telemedicine applications also manage appointment scheduling, e-prescribing, and sending reminders.
Telemedicine apps do not only conduct remote consultations. They also integrate with entire healthcare platforms, such as patient forums, insurance claims processing, and providing medical information libraries. Remote patient monitoring enables providers to keep track of patients' vital signs. This helps them intervene and provide care whenever necessary. Telehealth app development eliminates geographical boundaries and facilitates easier communication.
In this blog, we will explore its market growth, essential features, and benefits for both patients and providers.
GDG Cloud Southlake #41: Shay Levi: Beyond the Hype:How Enterprises Are Using AIJames Anderson
油
Beyond the Hype: How Enterprises Are Actually Using AI
Webinar Abstract:
AI promises to revolutionize enterprises - but whats actually working in the real world? In this session, we cut through the noise and share practical, real-world AI implementations that deliver results. Learn how leading enterprises are solving their most complex AI challenges in hours, not months, while keeping full control over security, compliance, and integrations. Well break down key lessons, highlight recent use cases, and show how Unframes Turnkey Enterprise AI Platform is making AI adoption fast, scalable, and risk-free.
Join the session to get actionable insights on enterprise AI - without the fluff.
Bio:
Shay Levi is the Co-Founder and CEO of Unframe, a company redefining enterprise AI with scalable, secure solutions. Previously, he co-founded Noname Security and led the company to its $500M acquisition by Akamai in just four years. A proven innovator in cybersecurity and technology, he specializes in building transformative solutions.
Automating Behavior-Driven Development: Boosting Productivity with Template-D...DOCOMO Innovations, Inc.
油
https://bit.ly/4ciP3mZ
We have successfully established our development process for Drupal custom modules, including automated testing using PHPUnit, all managed through our own GitLab CI/CD pipeline. This setup mirrors the automated testing process used by Drupal.org, which was our goal to emulate.
Building on this success, we have taken the next step by learning Behavior-Driven Development (BDD) using Behat. This approach allows us to automate the execution of acceptance tests for our Cloud Orchestration modules. Our upcoming session will provide a thorough explanation of the practical application of Behat, demonstrating how to effectively use this tool to write and execute comprehensive test scenarios.
In this session, we will cover:
1. Introduction to Behavior-Driven Development (BDD):
- Understanding the principles of BDD and its advantages in the software development lifecycle.
- How BDD aligns with agile methodologies and enhances collaboration between developers, testers, and stakeholders.
2. Overview of Behat:
- Introduction to Behat as a testing framework for BDD.
- Key features of Behat and its integration with other tools and platforms.
3. Automating Acceptance Tests:
- Running Behat tests in our GitLab CI/CD pipeline.
- Techniques for ensuring that automated tests are reliable and maintainable.
- Strategies for continuous improvement and scaling the test suite.
4. Template-Based Test Scenario Reusability:
- How to create reusable test scenario templates in Behat.
- Methods for parameterizing test scenarios to enhance reusability and reduce redundancy.
- Practical examples of how to implement and manage these templates within your testing framework.
By the end of the session, attendees will have a comprehensive understanding of how to leverage Behat for BDD in their own projects, particularly within the context of Drupal and cloud orchestration. They will gain practical knowledge on writing and running automated acceptance tests, ultimately enhancing the quality and efficiency of their development processes.
This presentation, delivered at Boston Code Camp 38, explores scalable multi-agent AI systems using Microsoft's AutoGen framework. It covers core concepts of AI agents, the building blocks of modern AI architectures, and how to orchestrate multi-agent collaboration using LLMs, tools, and human-in-the-loop workflows. Includes real-world use cases and implementation patterns.
1. 1. Run Test:
Ho : The sequence of observations is random.
H1 : The sequence of observations is not random.
If significance value(p) > .05 , we fail to reject Ho i.e. the sequence of observations is random. Hence
the hypothesis that the sample is drawn in a random order is accepted.
2. 2.Kolmogorov-Smirnov Test This test is used for testing whether the sample drawn has normal
distribution.
Ho: The population of random variable is normally distributed.
H1: The population of random variable is not normally distributed.
One-Sample Kolmogorov-Smirnov Test
3. would you want
sex to buy a NANO?
N 35 35
a,,b
Normal Parameters Mean 1.40 1.37
Std. Deviation .497 .490
Most Extreme Differences Absolute .390 .404
Positive .390 .404
Negative -.286 -.272
Kolmogorov-Smirnov Z 2.304 2.392
Asymp. Sig. (2-tailed) .000 .000
One-Sample Kolmogorov-Smirnov Test
how do you plan
to finance the Rate the design
car? Space of the car?
4. N 35 35 35
a,,b
Normal Parameters Mean 1.83 3.23 3.74
Std. Deviation 1.098 1.497 1.221
Most Extreme Differences Absolute .375 .167 .241
Positive .375 .132 .152
Negative -.225 -.167 -.241
Kolmogorov-Smirnov Z 2.217 .990 1.423
Asymp. Sig. (2-tailed) .000 .280 .035
One-Sample Kolmogorov-Smirnov Test
Rate the safety
of the car? Fuel effeciency
N 35 35
a,,b
Normal Parameters Mean 4.17 4.37
Std. Deviation .954 .646
Most Extreme Differences Absolute .257 .292
Positive .193 .260
Negative -.257 -.292
Kolmogorov-Smirnov Z 1.522 1.728
Asymp. Sig. (2-tailed) .019 .005
a. Test distribution is Normal.
b. Calculated from data.
One-Sample Kolmogorov-Smirnov Test
Considering the
increase in traffic
and pollution is it
Value for money a boon or curse
N 35 35
a,,b
Normal Parameters Mean 3.29 1.34
Std. Deviation 1.100 .482
Most Extreme Differences Absolute .202 .419
Positive .202 .419
Negative -.142 -.257
Kolmogorov-Smirnov Z 1.198 2.478
5. Asymp. Sig. (2-tailed) .113 .000
a. Test distribution is Normal.
b. Calculated from data.
As we can see from the above test result, the significance level of the variables sex,would you buy
nano,model preferred,Financeplan,Design,Safety,Fuelefficiency,View on pollution <.05,
so we fail to accept Ho which shows that the population of this variable is not normally distributed.
For all other variables as the significance level is greater than .05, so the population of these
variables is normally distributed.
For all the variables which have passed the KS Test, we are going to test it for homogeneity by
performing the Levenes Test.
3.Levene Test- This test is used for testing the homogeneity of the variable.
Ho: The population of variable is homogeneous (variances are equal)
H1: The population of variable is not homogeneous (variances are not equal)
We take Value for Money as andependent variable and Occupation as a independent variable.
Performing the Levene Test, we get the following result.
Test of Homogeneity of Variances
Value Value for money
Levene Statistic df1 df2 Sig.
.352 3 31 .788
Levene's test is used to assess Variance homogeneity, which is a precondition for parametric
tests such as the t-test and ANOVA. The test can be used with two or more samples. With two
samples, it provides the test of variance homogeneity for the t-test. With more samples, it provides
the test for ANOVA.
6. If the significance from this test is less than 0.05, then variances are significantly different and
parametric tests cannot be used (and a non-parametric test will probably have to be used).
As significance value is greater than .05, we do accept the null hypothesis. The population of
variable is homogeneous. Since this variables variance is not significantly different, we are going
to perform the parametric test on it.
As the number of samples are more than two,we perform ANOVA test,the result of which is as
follows:
ANOVA
Value Value for money
Sum of Squares df Mean Square F Sig.
Between Groups 4.082 3 1.361 1.138 .349
Within Groups 37.061 31 1.196
Total 41.143 34
Here: Ho: Nanos Value for money perceived is same across all occupations
H1: Nanos Value for money perceived is different for different occupations
As the Significance value is 0.379>0.05,we need to accept the null hypothesis,i.e. theNanos value
for money perceived does not significantly differ across the different types of occupations.
We,now, take Occupation as an dependent variable and Vehicle currently owned as a
independent variable.
Performing the Levene Test, we get the following result.
Test of Homogeneity of Variances
occupation
Levene Statistic df1 df2 Sig.
.211 2 32 .811
Since Significance is 0.811>0.05. As significance value is greater than .05, we do accept the null
hypothesis. The population of variable is homogeneous. Since this variables variance is not
significantly different, we are going to perform the parametric test on it.
7. ANOVA
occupation
Sum of Squares df Mean Square F Sig.
Between Groups 8.771 2 4.386 8.066 .001
Within Groups 17.400 32 .544
Total 26.171 34
Here: Ho: There are no significant differences between the groups'(occupation) mean
scores for the type of vehicle owned.
H1:There are significant differences between the groups'(occupation) mean scores for the
type of vehicle owned.
As the Significance value is 0.001<0.05,we need to reject the null hypothesis, i.eThere are
significant differences between the groups'(occupation) mean scores for the type of vehicle
owned.
Thus the type of vehicle owned varies significantly across the different types of populations.
For those variables which fail to pass the required assumptions, non parametric test such as
Kruskal-Wallis Test(Anova) or Mann Whitney Test (2 sample) is performed on it.
Lets consider the variables which have failed the Assumptions of parametric tests .
Independent variable :Sex
Dependent Variable : Perceived safety of the car
Ho: Safety of the car is perceived not differently across the two genders.
H1: : Safety of the car isperceived differently across the two genders.
Since variable sex results into a 2 samples and both the variables failed to qualify the assumptions
of the Parametric tests,we apply Mann Whitney test on them.
Results are as follows:
Ranks
sex N Mean Rank Sum of Ranks
Safety Rate the safety of the 1 male 21 18.95 398.00
car? 2 female 14 16.57 232.00
Total 35
b
Test Statistics
Safety Rate the
safety of the
car?
8. Mann-Whitney U 127.000
Wilcoxon W 232.000
Z -.728
Asymp. Sig. (2-tailed) .467
a
Exact Sig. [2*(1-tailed Sig.)] .516
a. Not corrected for ties.
b. Grouping Variable: sex
As we can see,the significance value is 0.467> 0.05 ,thus have to accept the null hypothesis.
Thus,Safety of the car is perceived similarly across the two genders.
Similarly we can consider all the parameters which had failed the parametric test assumptions
against Gender variable.
The results are as follows:
Ranks
sex N Mean Rank Sum of Ranks
View Considering the 1 male 21 17.83 374.50
increase in traffic and 2 female 14 18.25 255.50
pollution is it a boon or curse Total 35
Fuel Fueleffeciency 1 male 21 15.93 334.50
2 female 14 21.11 295.50
Total 35
Safety Rate the safety of the 1 male 21 18.95 398.00
car? 2 female 14 16.57 232.00
Total 35
Design Rate the design of 1 male 21 17.95 377.00
the car? 2 female 14 18.07 253.00
Total 35
Model which model would 1 male 21 18.33 385.00
you prefer? 2 female 14 17.50 245.00
Total 35
Buy would you want to buy a 1 male 21 18.17 381.50
NANO? 2 female 14 17.75 248.50
Total 35
Finance how do you plan to 1 male 21 20.24 425.00
finance the car? 2 female 14 14.64 205.00
Total 35
9. As we can for none of the variables the significance variable is <0.05 ,thus ,for all the variables the
the values do not differ according to gender or no distinction can be made in the variables on the
basis of gender.