Statistics for Business, Analytics and Data Science

Explore the statistical description of data by examining data nature, variables, and data types, including discrete vs continuous data, and learn visualizations like histograms, frequency distributions, and bar charts.

Explore the tension between pure mathematics and statistics, contrasting real-object problems and definite integrals with inferential forecasts, and highlight how mathematics and statistics can complement each other.

Learn how statistics underpins forecasting and inference across weather, insurance risk, stock markets, medicine, quality control, and everyday decision making.

Understand the limitations of statistics: statistics describe aggregates, not individuals, convert qualitative data to quantitative form, and rely on random sampling to avoid bias from convenience or snowball sampling.

Explains primary and secondary data collection, introduces questionnaires for surveys, demonstrates a customer satisfaction example using a five-point Likert scale, and contrasts open versus closed questions.

Explore data visualization with simple and multiple line charts, using January to June sales data for laptops and tablets to present performance to management.

The video explains the application of bar charts in statistics for business, analytics and data science.

Explore tabulation guidelines and standard table formats, including serial numbers, captions, table date, body data, and footnotes, to convert primary or secondary data into analyzable tables for statistics.

Organize data into class intervals and tally marks to reveal frequency distribution and how often each value occurs, then compute range and class width to form the table.

Visualize frequency distributions with histograms, frequency polygons, and cumulative frequency; convert discrete data to continuous classes, compute midpoints, and identify anomalies and the mode from the graph.

Identify the mode from a histogram by locating the highest frequency bar and estimating the modal value for continuous data, approximately 49.2 within 43.5 to 55.5.

Explore types of frequency curves, including histogram, frequency polygon, and smooth battleship curves, plus parabolic, reverse-parabolic, j- and u-shaped forms, with product lifecycle and commuter pattern examples.

Understand central tendency as data clustering around a central line and learn to measure it with mean, median, and mode. Explore the Pythagorean means: arithmetic, geometric, and harmonic.

Explore the concept of arithmetic mean as a measure of central tendency, distinguishing discrete, continuous, and frequency data, and learn how to compute mean using simple and frequency formulas.

Discover how to calculate the median for discrete data by sorting values in ascending order and identifying the middle observation, with practical step-by-step examples.

Explore two median properties: for y = a + b x, median(y) = a + b median(x); and the sum of absolute deviations is minimized when measured from the median.

This lecture explains how to compute mean, median, and mode from open-ended class frequency distributions, identifies three cases, and demonstrates methods using practical examples.

Clarify quartiles, including Q1, Q2, Q3, and relate them to 0, 25, 50, 75 percent data, while introducing percentiles and deciles amid discrete versus continuous data considerations.

Sort wage data in ascending order and compute quartiles, deciles, and percentiles for discrete data using the described interpolation formulas.

Compute the mean for continuous frequency data using the assumed mean method, class width, and deviation units, illustrated with a 36-student example yielding 61.42.

Compute the mean of grouped frequency data using the assume-mean formula or the weighted mean method; the example shows both approaches yield the same result, about 61.4.

Learn to compute quartiles, deciles, and percentiles using grouped data formulas, including L1 and F. Use continuous class intervals and cumulative frequencies to locate the median and quartile classes.

Learn to find missing frequencies in grouped data by solving two equations from quartiles q1 and q3, identifying x and y in class intervals such as 20–30 and 40–50.

Learn to handle open ended and unequal class intervals when computing quartiles, deciles, and percentiles from grouped data by constructing continuous classes, calculating cumulative frequencies, and applying the standard formula.

Learn how to identify the mode in discrete data by finding the element with the maximum frequency, with examples of no mode, a single mode, and a bimodal data set.

Explore how to solve a group frequency data problem by determining missing frequencies, computing the mode, mean, and median, and proving the median lies between mean and mode.

Apply the empirical method to estimate the mode from mean and median using the formula mode ≈ 3 median − 2 mean, useful for slightly skewed data.

Explore how mean, median, and mode describe central tendency in skewed distributions, with examples of positive and negative skew and their implications for data interpretation.

Explore kurtosis and skewness to understand data peakiness and distribution shapes. Learn how positive and negative skew and shapes like leptokurtic, mesokurtic, and platykurtic relate to the normal distribution.

Explore variance concepts, including the sum of squared distances from the mean for population and sample variance, and learn Bessel's correction (minus one from the sample size).

Explore box plots to visualize data distribution, identify quartiles and the interquartile range, and detect outliers using whiskers and fences in practical examples.

Understand population versus sample using income data from India to show how a small sample estimates population mean and standard deviation, enabling inferential statistics.

Learn how to construct and interpret a stem-and-leaf display to sort data and present datasets clearly for quick managerial insight.

Explore valid and reliable data concepts, including valid value versus reliable value. Assess measurement scales, such as nominal and five-point or seven-point scales, and address missing values.

Explore primary and secondary data sources, and learn to design effective questionnaires using open-ended and closed-ended items, including a five-point scale for customer satisfaction.

Learn to compute the range as max minus min and the coefficient of range as (max minus min)/(max plus min) times 100, with linear-equation relations for x and y.

Compute quartile deviation from Q1 and Q3 with the formula (Q3−Q1)/2, and evaluate the coefficient of quartile deviation as (Q3−Q1)/(Q3+Q1) times 100 percent using cumulative frequencies.

Learn to compute quartiles from open-ended class intervals using cumulative frequencies. Convert to class frequencies, identify q1, q2, q3 by interpolation, and apply this method to business statistics problems.

Explore the concept of mean deviation from the center line using mean, median, or mode; apply formulas to raw or frequency data and compute the coefficient as a percentage.

Compute the mean deviation about the median and the coefficient of mean deviation about the median for the grouped data. Extend the approach to mean-based versions.

Explain standard deviation as a measure of dispersion from the mean, show why deviations are squared, and present formulas for raw and frequency data with practical examples.

Explore how standard deviation reveals how scores spread around the mean in assessment data. See how normal distribution and the one-standard-deviation rules help interpret distributions.

Compute the coefficient of variation by dividing the standard deviation by the mean and multiplying by 100 percent. Use CV to compare variability and assess data consistency across distributions.

Compare two batsmen using the coefficient of variation to assess consistency, compute means and standard deviations from ten innings, and select batsman B for the tournament.

Address the cv missing frequency problem by completing a grouped distribution with an unknown frequency, use the given mean of 16.4, and compute the standard deviation and coefficient of variance.

This lecture analyzes a four-digit no-repetition password puzzle to save a father, calculating possible codes from digits 0–9 and the worst-case time at ten seconds per attempt.

Learn how combinations differ from permutations when order does not matter, using the formula C(n,r)=n!/(r!(n−r)!), with examples and a practice problem to solve for n.

Explore core combinatorics concepts through solved problems: binomial coefficients and factorials, arranging letters, forming committees with at least two ladies, and counting non-collinear triangles from 12 points.

Explore the concept of probability, from classical and subjective to axiomatic approaches, and apply sample space, independence, conditional and marginal probabilities through real-world examples.

Apply probability axioms to assess the sample space outcomes, verify probabilities lie between 0 and 1, and ensure they sum to 1, identifying valid versus invalid assignments.

Explore the sample space and key probability concepts—simple points, events, impossible, sure, complements, unions, intersections, and mutually exclusive or exhaustive events.

Apply core probability concepts to real problems: red, yellow, and blue disk draws; mutually exclusive events; and inclusion–exclusion for committees and math or biology scenarios.

Understand the relative probability approach within the classical framework by computing probabilities as favorable outcomes over total outcomes using class intervals, with examples from student marks and wages distributions.

this lecture introduces basic probability axioms, including probabilities between 0 and 1 and the complement rule p(a^c)=1-p(a), plus the union–intersection formula p(a∪b)=p(a)+p(b)-p(a∩b).

Apply conditional probability using P(A|B)=P(A∩B)/P(B) to a project example: given on-time completion, the probability of being under budget is 1/3.

Explore the addition and multiplication rules in probability, distinguish mutually exclusive events, and apply union and intersection concepts to real-world examples like coin tosses and project outcomes.

Explore Bayes theorem and conditional probability to determine the probability of an event given another, using formulas like P(A|B)=P(B|A)P(A)/P(B) and its business analytics applications.

Apply Bayes theorem to determine the chance a part is truly defective after diagnostic tests, using true and false positive rates; a second positive test raises confidence.

Learn to solve business decisions with a decision tree by weighing probabilistic outcomes and losses to compute expected monetary value, as shown in airline and franchise investment examples.

Form and test hypotheses by defining the null and alternate hypotheses, identifying rejection regions and the significance level alpha, and evaluating sample means to accept or reject claims.

Explore how the burden of proof governs hypothesis testing, distinguishing population mean from sample mean and using null hypotheses as the default until challenged.

Explore type i and type ii errors, defined as false positives and false negatives, with examples and the roles of alpha, power, and null versus alternative hypotheses.

Form hypotheses correctly by labeling the null as mu equals 150 and the alternate as mu less than or greater than 150, identifying which is which and expressing them mathematically.

Form null and alternate hypotheses from real examples, such as house prices and YouTube ages, using equalities in null and not-equal, greater than, or less than alternatives.

Frame the null and alternative hypotheses, assume the null is true unless disproven, and use the test type, prediction region, and cutoff to decide whether to reject.

Explains how researchers choose a significance level (alpha) and confidence level in hypothesis testing. Discusses type I error, rejection region, and why zero percent error is impossible.

Compare the theoretical frequency distribution with the binomial distribution using three independent coin tosses, and show that the binomial results match the expected outcomes for 0 to 3 heads.

Explore the Poisson distribution for discrete random variables, define lambda as average occurrence, apply the probability formula, and solve real-world problems like deliveries per hour and cumulative probability.

Explore the Poisson distribution for rare events, where events are large and probability is small, with examples like printing mistakes, road accidents, and calculating mean and standard deviation from lambda.

Explore the Poisson distribution, a single-parameter model with lambda, whose mean and variance equal lambda. Understand its standard deviation sqrt(lambda), the additive property, and its binomial and normal approximations.

Understand the normal distribution as a symmetric curve defined by mean and standard deviation, and standardize to the standard normal (z) distribution with zero mean and unit variance.

Apply the z-score to standardize data against the mean and standard deviation, transforming values to the standard normal distribution for percentile interpretation in business problems.