This preview shows pages 1–2. Sign up to view the full content.
This preview has intentionally blurred sections. Sign up to view the full version.View Full Document
Unformatted text preview: MN1025 – Business Statistics 1 Lecture 1—Friday 11/1/2008 SAMPLES and POPULATIONS: DESCRIPTIVE STATISTICS Reference: Lind et al. , Chapters 1,2,3,4 (see reading list on moodle.rhul.ac.uk for full book title). 1.1 Practical matters Lecturer: Prof. R. Schack, office C245 See Moodle (http://moodle.rhul.ac.uk) for • General course information • Office hours • Workshop times and registration • Reading list • Past exam papers • Lecture notes and worksheets • How to get Minitab Each week, the new worksheet will be sent to your college email address . Please keep the deadlines, as they will be strictly enforced. You should always attend the workshop for which you are registered. 1.2 Sampling STATISTICS: this means analysing data to obtain information with a view to making decisions on the basis of the data. So we have DATA-→ INFORMATION-→ DECISION The basic idea: data obtained are usually a sam- ple which (if chosen randomly) is representative of a larger population. We need to know how to make statements about the population based on what we see in the sample. Having got a large sample we must first organise the data to see the information clearly. So: first we deal with the topic of Descriptive Statistics—setting out data in a way that reveals as much information as possible. 1.3 Example: TV viewing figures A sample of persons/households is examined and for each programme a deduction is made about the total number of viewers, their social class, etc. (for exam- ple, for advertising purposes). Here the population is all persons/households in the UK; the sample is a manageable number chosen in some way so as to be representative. This is how TV viewing figures are obtained in practice. 1.4 Example: Quality control Every 50th item off a production line is removed. Together these provide a daily sample which is ex- amined for quality. From the results we wish to make an estimate of the quality of the day’s production (= population) as a whole. 1.5 Reasons for sampling (i) Sometimes examining a whole population is im- practical: for example we might want to get people’s opinions—if we tried to interview everyone it would take so long that those first interviewed might have changed their minds. A sample lets us get a “snap- shot” of opinions. (ii) Sometimes examining a whole population is too expensive. (iii) Some tests destroy the object being tested (safety tests on cars in crashes, lifetimes of light bulbs), so we must sample. 1.6 Example: R&D expenditure The data in this example are percentages of revenue spent on research and development by US computer firms (from McClave et al. , Statistics for Business and Economics). We get a jumble of numbers which we will organise and set out in ways which display more information....
View Full Document
This note was uploaded on 04/17/2008 for the course MN 1025 taught by Professor Schack during the Spring '08 term at Royal Holloway.
- Spring '08