Mathematics for Computer Science Engineers Quiz

Evaluation Policy in Mathematics for Computer Science Engineers

• ISA 1 and ISA 2 each contribute 40 marks, reduced to 20 marks.
• Assignments include Coding (5 marks) and Datathon (20 marks), totaling 25 marks.
• Hands-on session codes are to be submitted on the same day, impacting marks by 5.

Data Science Overview

• Data Science combines various disciplines to extract knowledge and insights from data.
• Essential for solving real-world problems and deriving actionable insights.

Convenience Sampling

• Involves gathering data from easily accessible subjects, such as surveying classmates immediately after class.
• Advantages include cost-effectiveness and time efficiency.
• Disadvantages focus on potential sampling bias and non-representative results.

Judgemental Sampling

• A non-probability sampling method where researchers select samples based on their judgement of appropriateness.
• Useful when the population has limited expertise.
• Advantages include time efficiency; disadvantages involve risks of bias and low reliability.

Quota Sampling

• Sample selection until predetermined quotas are met based on characteristics without random selection.
• Similar to stratified sampling but relies on non-random methods.
• Efficient in cost and time, yet can lead to sampling bias.

Snowball Sampling

• Subjects are recruited through referrals from existing participants, expanding the sample size effectively.
• Particularly beneficial for hard-to-reach populations, such as the homeless or undocumented individuals.
• Advantages include ease of access; disadvantages include risk of selection bias.

Sample Size Considerations

• Larger sample sizes are preferable for probability sampling due to population heterogeneity.
• Factors affecting sample size include total population size, margin of error, and desired confidence level.

Sample Statistic vs. Population Parameter

• Sample Statistic refers to metrics derived from a sample (e.g., sample average).
• Population Parameter refers to metrics applicable to the entire population (e.g., population mean).
• Recognize the distinction between statistics based on samples versus the entire population.

Errors in Sampling

• Sampling Error occurs when the sample does not accurately represent the population.
• Non-sampling Error arises during data collection, leading to discrepancies from true values.

Measures of Central Tendency: Median

• Median divides data into higher and lower halves, robust against outliers.
• Calculation involves ordering data and determining the middle value based on whether the sample size is odd or even.
• Advantages include resilience to outliers; disadvantages limit further algebraic analysis.

Measures of Central Tendency: Mode

• The most frequently occurring value in a dataset; can be multimodal.
• Quick to compute and not influenced by extreme values, useful in identifying common items.
• Potential unrepresentativeness if the subgroup skews the data.

Skewness in Distributions

• Skewness indicates the asymmetry around the mean; can be positive, negative, zero, or undefined.
• In symmetric distributions, mean, median, and mode coincide, while in skewed distributions, they differ.
• The extent of skewness increases with the distance between the mean and median.

This quiz evaluates key concepts from the 'Mathematics for Computer Science Engineers' course at Brigham Young University. It explores topics essential for understanding mathematical foundations in computer science, focusing on evaluation methods and assignment components.