Statistics MCQs and Case Studies
Uploaded by
kartik.pathak2026Statistics MCQs and Case Studies
Uploaded by
kartik.pathak2026Common questions
Powered by AIThe mean is sensitive to extreme outliers as it considers all data points, while the median is resistant because it focuses on the middle value. This matters because choosing the wrong measure may lead to misleading conclusions during data analysis .
Positive skewness indicates that the dataset has a tail extending towards higher values, implying that the data may not be symmetrically distribtued and can affect the interpretation of central tendency and variability .
Regression can be used to identify relationships between variables affecting quality, predict future defects, optimize processes, and ultimately improve quality control by allowing the company to focus on significant factors affecting product quality .
Using appropriate methods like the Z-Score helps to correctly identify and address outliers, preventing them from skewing results and leading to more reliable and valid interpretations of data .
Statistics provide tools for summarizing data, predicting outcomes, and making informed decisions, all of which are crucial in business for making strategic and efficient decisions .
I recommend using the median as the measure of central tendency for monitoring widget dimensions, as it is more robust against any outliers that might occur due to defective production .
Reducing dataset dimensions helps in eliminating redundancy and noise, aiding in a clearer and more manageable analysis. It benefits data analysis by simplifying complex datasets, facilitating more accurate interpretations and improving the efficiency of further analysis .
A company would choose a statistical test like ANOVA when comparing more than two groups to understand if there are significant differences in outcomes, ensuring a comprehensive analysis of varied marketing strategies without inflating type I error rates .
ANOVA's strength lies in detecting significant differences across multiple groups without inflating type I errors. However, its limitations include assumptions of homogeneity of variances, normality, and the requirement of independent samples, which, if violated, could lead to incorrect conclusions .
High kurtosis in product dimension data suggests that there are more values at the extremes and possibly more frequent outliers, implying potential quality control issues often requiring further investigation .