LGT5101 Statistics for Management
The Complete Exam Bible · Semester 1, 2026/27LGT5101 Overview
- The Hong Kong Polytechnic University
- Semester 1, 2026/27
- Postgraduate
- Open-book final exam
- Statistics
What this course asks you to do
Statistics for Management develops a sequence for turning business observations into defensible decisions.
- Assessment Two individual assignments, class participation and a 50% open-book final exam.
- Core method Classify the variable and scope before choosing a chart, summary or probability model.
- Calculation habit Write the formula, substitute the values, keep the event visible and interpret in original units.
- Source boundary This edition covers the captured teaching materials for Lectures 1 to 6.
How LGT5101 is assessed
| Component | Weight | Format |
|---|---|---|
| Individual Assignment 1 | 15% | Lectures 1 to 6; individual computational work; due 18 October 2026 |
| Individual Assignment 2 | 25% | Lectures 7 to 13; individual computational work; due 29 November 2026 |
| Class Participation | 10% | Attendance, in-class exercises, questions and discussion |
| Final Exam | 50% | Open book; Lectures 1 to 13; date and time announced later |
The published syllabus lists four components totalling 100%. It states that the final exam is open book and covers Lectures 1 to 13. Its date and time are announced later, and no duration, section layout, question count or separate hurdle is stated in the captured materials.
Assessment structure
Segment widths reproduce the published percentage weights and total 100%.
Current LGT5101 dates
| Date | Item | Control |
|---|---|---|
| 18 October 2026 | Individual Assignment 1 | Published deadline for the Lectures 1 to 6 assignment. |
| 29 November 2026 | Individual Assignment 2 | Published deadline for the Lectures 7 to 13 assignment. |
Dates are as published in the published Semester 1, 2026/27 syllabus and course overview. Confirm exact deadlines and submission settings in the live LMS.
What LGT5101 covers
Six chapters follow the captured teaching sequence from data types and visual displays through descriptive measures, event probability, discrete models and normal distributions.
Statistical Questions, Data Types and Samples
experimental units, populations and samples; categorical and quantitative variables; nominal, ordinal, interval and ratio scalesStart with the row
A statistical analysis begins by naming what one row represents and which property is recorded. The experimental unit prevents mixed levels: a row describing a delivery cannot silently be treated as a customer or a depot.
- Experimental units and variables
- Population and sample scope
- Descriptive and inferential methods
- Categorical and quantitative data
- Nominal and ordinal scales
- Interval and ratio scales
Frequencies, Charts and Histograms
class and relative frequencies; bar and pie charts for categories; histogram bins for quantitative distributionsChoose the picture from the variable
Frequency tables compress raw records into counts and relative frequencies. Counts show workload, while relative frequencies place groups with different totals on a common denominator.
- Class frequency
- Relative frequency
- Bar charts for categories
- Pie charts for a whole
- Histogram intervals
- Bin width decisions
Centre, Spread, Shape and Standard Scores
sample and population centre; variance and standard deviation; skewness, distribution rules and z-scoresSummaries work as a set
Mean, median and mode describe different notions of centre. The mean uses every magnitude and therefore responds to a distant value. The median uses order and remains attached to the middle position.
- Mean, median and mode
- Outliers and robust centre
- Range and standard deviation
- Sample and population formulas
- Skewness direction
- Empirical rule
Event Probability and Conditional Reasoning
sample spaces and counting; unions and intersections; conditional probability, products and independenceTranslate words into event regions
Probability begins with an experiment, a complete sample space and named events. Basic outcomes must be mutually exclusive, carry probabilities between zero and one and total one.
- Experiments and sample spaces
- Events and complements
- Permutations and combinations
- Union and intersection
- Conditional probability
- Product rule
Discrete Random Variables and Binomial Models
probability mass and cumulative distributions; expectation and variance; exact and cumulative binomial riskPut probability on countable values
A discrete random variable assigns numerical values to experimental outcomes. Its probability mass function lists P(X=x) for every possible value.
- Discrete random variables
- Probability mass functions
- Cumulative distributions
- Expectation
- Variance and standard deviation
- Binomial conditions
Continuous Variables and Normal Models
density area and cumulative probability; normal standardisation; tail calculations and inverse percentilesProbability becomes area
A continuous random variable takes infinitely many values across an interval and assigns probability through area under a density curve. Total area is one, while a single exact point has area zero.
- Continuous random variables
- Probability density
- Cumulative distribution
- Normal parameters
- Standard normal variable
- Interval and tail probability
The official description begins with data preparation and analysis, then moves through descriptive statistics, sampling, probability, distributions, estimation, testing, analysis of variance and regression. The teaching materials captured for this edition cover the first six lectures.
They begin with experimental units, populations, samples and measurement scales, then build frequency displays, centre and spread, event probability, discrete random variables and continuous normal models.
Why set-up matters more than software
The course uses Excel, but the assessed reasoning begins before a function is entered.
A student has to identify whether a variable is categorical or quantitative, whether the rows form a sample or population, which event is being requested and whether a model's conditions hold. The published first assignment asks for formulas and calculation steps wherever possible.
This guide therefore keeps model, formula, substitution and interpretation visible in every worked answer.
How the chapters fit together
The first chapter establishes the nouns that control scope. The second turns raw records into frequency tables and honest displays. The third compares mean, median and mode, adds variance and standard deviation, and uses skewness and z-scores to interpret unusual values.
The fourth builds event logic with unions, intersections, complements, conditioning and independence. The fifth packages repeated trials into discrete distributions and binomial decisions.
The sixth converts continuous probability into area under a density curve, then uses the normal cdf and inverse cdf for forward and reverse questions.
How to revise for the final
The final exam is published as open book, worth half of the course and covering Lectures 1 to 13. The captured source does not state its duration, sections, question count or detailed permitted-material rules.
Build an index by question type and confirm the live arrangements on Canvas@PolyU.
Open-book access helps retrieval only after you can recognise the model from the wording and sketch the relevant chart or probability area.
LGT5101 cheatsheet for the final exam
AskSia publishes a free LGT5101 cheatsheet for the final exam, an open-book exam sheet that follows the official permitted-materials rule for this assessment and condenses the topics in this guide.
Worked example · free
Choose the honest centre for a delayed process
- 2Calculate the mean from all six delays.
- 2Find the median from the ordered middle pair.
- 2Use the mean-median gap to describe the shape.
- 2Select a lead centre and explain the management use.
Key terms
- Experimental Unit
- The object, person, transaction or event on which a variable is observed.
- Population
- The complete set of units addressed by the statistical question.
- Sample
- The observed subset used to describe or infer something about a population.
- Relative Frequency
- A class count divided by the total number of observations.
- Sample Variance
- Average squared deviation from the sample mean using n minus one as denominator.
- Standard Score
- The signed distance of a value from its mean in standard-deviation units.
- Conditional Probability
- The probability of an event after the sample space is restricted by given information.
- Independence
- A relationship in which learning one event occurred does not change the probability of another.
- Probability Mass
- The probability assigned to one possible value of a discrete random variable.
- Binomial Model
- A count of successes across fixed independent trials with constant success probability.
- Probability Density
- A continuous curve whose area over an interval equals probability.
- Inverse Cdf
- A calculation that returns the threshold associated with a stated left-tail probability.
LGT5101 FAQ
What is included in the published assessment structure?
The syllabus lists Individual Assignment 1 at 15%, Individual Assignment 2 at 25%, Class Participation at 10% and a Final Exam at 50%. The numeric weights total 100%. The assignments are individual computational work, while participation includes attendance, in-class exercises, questions and discussion.
What is known about the final exam format?
The captured syllabus states that the final exam is open book, worth 50% and covers Lectures 1 to 13. It does not publish a duration, section layout, question count or detailed permitted-material rule. Confirm those live arrangements on Canvas@PolyU when the course releases them.
Why should formulas and calculation steps be shown?
The published Assignment 1 instructions explicitly ask students to show formulas and calculation steps wherever possible, even when a calculator or software is used. A visible audit trail also reveals whether the wrong denominator, tail, event or model entered the calculation before the final number.
When do I use sample rather than population variance?
Use sample variance when the observed values are a subset used to learn about a larger population, and divide squared deviations by n minus one. Use population variance when the data cover every unit addressed by the question, and divide by N. Scope, not dataset size, chooses the formula.
How do I choose between a bar chart and a histogram?
Use separated bars for categorical classes and a histogram with touching, non-overlapping intervals for quantitative data. A bar chart preserves category frequencies, while a histogram deliberately loses exact values to reveal centre, spread and shape. State the bin boundaries so every observation belongs to exactly one interval.
What is the safest workflow for a probability problem?
Define the event or random variable in words, sketch the relevant regions or density area, state the rule and its conditions, substitute the numbers, and interpret the result in the original context. For normal calculations, remember that a cdf returns left-tail area, so right tails need a complement.
Questions students ask in each LGT5101 chapter
- Can a number be categorical data?
- Yes. Depot codes, product identifiers and satisfaction labels may use digits while remaining categories. Ask whether subtraction or ratios have a defensible interpretation. If code four is not twice code two in the real setting, the digits are labels rather than measured quantities. Chapter 01 · Statistical Questions, Data Types and Samples
- Why do histogram bars touch?
- Each bar occupies an adjacent interval on one continuous measurement scale, so the bars meet at their boundaries. Categorical bars remain separated because the categories are distinct classes rather than neighbouring sections of a numerical line. Chapter 02 · Frequencies, Charts and Histograms
- When should the median lead the report?
- Lead with the median when a skewed distribution or distant observations make the mean unrepresentative of an ordinary case. Retain the mean when total resources or cumulative impact matter, because every magnitude still contributes to the total. The two centres answer different management questions. Chapter 03 · Centre, Spread, Shape and Standard Scores
- Why is overlap subtracted in the union rule?
- Adding P(A) and P(B) counts outcomes in their intersection twice, once inside each event. Subtracting P(A intersection B) once leaves every outcome in the union counted exactly once. If the events are mutually exclusive, the overlap is zero. Chapter 04 · Event Probability and Conditional Reasoning
- How do I check whether a pmf is valid?
- Verify that every listed probability lies between zero and one and that the probabilities across all possible values sum to one. Both conditions are necessary. A table whose entries are individually plausible but total 0.90 is missing probability mass and cannot support an expectation. Chapter 05 · Discrete Random Variables and Binomial Models
- Why is the probability of one exact continuous value zero?
- Probability is represented by area under the density curve. One point has no width and therefore no area, even when the density height there is positive. As a result, including or excluding the endpoints of a continuous interval does not change its probability. Chapter 06 · Continuous Variables and Normal Models
How to study for the exam
Build a revision index by decision rather than lecture number. Put variable classification, chart choice, sample versus population spread, union, conditioning, independence, pmf validity, binomial tails, normal standardisation and inverse percentiles on separate lines with page references. For each chapter, redo the worked example without looking and write four visible stages: model, formula, substitution and interpretation.
Then use the notes only to check the stage where your result diverged. Mix question types after the first pass, because the final challenge is recognising which model applies before software is opened. Keep an error log with four columns: wording missed, wrong event or scope, incorrect calculation and the quick check that would have caught it.
Before the final, confirm the current exam arrangements on Canvas@PolyU and rehearse finding each rule in your open-book materials under time pressure.
Your AI Statistics tutor for LGT5101
Stuck on a hard LGT5101 question? Sia is AskSia’s AI Statistics tutor — ask any LGT5101 Statistics for Management question and get a clear, step-by-step explanation grounded in how the course is actually taught and assessed. Read this whole study guide free, then take your hardest questions to Sia.
