MODULE ONE: PRESENTING AND DESCRIBING INFORMATIONTOPIC 1: DATA COLLECTIONDeakin University CRICOS Provider Code: 00113B+Learning ObjectivesAt the completion of this topic, you should be able to:•identify…

MODULE ONE: PRESENTING AND DESCRIBING INFORMATIONTOPIC 1: DATA COLLECTIONDeakin University CRICOS Provider Code: 00113B+Learning ObjectivesAt the completion of this topic, you should be able to:•identify how statistics is used in business•recognise the sources of data used in business•identify the types of data used in business•distinguish between different survey sampling methods•evaluate the quality of surveys2+1.1 Basic Concepts of StatisticsStatistics is a large discipline that comprises three broad tasks:1.collection of data2.processing and presentation of data3.analysis and interpretation of data3+1.1 Basic Concepts of Statistics (cont)Key Definitions•Apopulationconsists of all the members of a group about which you want to draw a conclusion•Asampleis the portion of the population selected for analysis•Aparameteris a numerical measure that describes a characteristic of a population•Astatisticis a numerical measure that describes a characteristic of a sample4+1.1 Basic Concepts of Statistics (cont)As a field of study, statistics can be split into two main groups:1.Descriptive statistics, which relates to a set of techniques based around certain tables, graphs and calculated summary measures used for describing the important features of a given set of data2.Inferential statistics, which relates to the use of sample data to draw inferences and conclusions about the whole population of individuals or items from which the sample was drawn5+1.1 Basic Concepts of Statistics (cont)6+1.3 Collecting DataIdentifying Sources of Data:•External sources•Data collected by others (Use if acceptable)or•Collect your own•Census•Sample7+1.3 Collecting Data (cont)Existing Sources•Within a firm–almost any department•Business database services–Australian Stock Exchange•Government agencies–Australian Bureau of Statistics•Industry associations–Real Estate Institute of Australia•Special-interest organizations –Graduate Management Admission Council•Internet–more and more firms and government departments/authorities8+1.3 Collecting Data (cont)There are many issues and potential traps when collecting your own data, including:•Do we take a Census or a Sample?•How big a sample size?•Collection methodology•Time and cost issue9+1.3 Collecting Data (cont)Sample surveys: Purpose, Purpose, Purpose•The broadpurposeof a cross-sectional survey is:•To draw conclusions or make inferences about thewholegroup (population) of items or individuals at a given point of time•For example, a University wishes to determine if student grades are beingadversely affected by work at part-time jobs•We must ALWAYS keep thepurposein mind10+1.3 Collecting Data (cont)Given a purpose and desired outcome, we first need tocollectrelevant dataCollectinghigh quality data is arguably the most difficult part of a statistical exerciseTwo options:•Census: We investigate the whole population•Sample: Investigate some of the populationBut the purpose isthe same11+1.3 Collecting Data (cont)Census vs Sample:•Census•In theory, more accurate•But time consuming and expensive•Sample•Saves time and money•Only option if items have to be destroyed, and for some types ofexperiments•Can provide a very high level of accuracy12+1.3 Collecting Data (cont)Census vs Sample•Both census and sample require similar attention to detail in terms of:•survey type used•questionnaire design•training of interviewers•etc.•Taking a sample has the added complication ofchoosingthe sample13+1.4 Types of Variables -Data 14+1.4 Types of Variables –Data (cont) 15+Levels of Measurement and Types of Measurement Scales16+Levels of Measurement and Types of Measurement Scales17+Levels of Measurement and Types of Measurement Scales18+Levels of Measurement and Types of Measurement Scales19+Levels of Measurement and Types of Measurement Scales20+Levels of Measurement and Types of Measurement ScalesNominal•Data arelabelsor namesused to identify an attribute of the element•A nonnumeric label or numeric code may be used•Eg: Nominal data that would relate to employees21GenderCodeFemale0Male1Female0+Levels of Measurement and Types of Measurement ScalesOrdinal•The data have the properties of nominal data and theorderor rankof the data is meaningful•A nonnumeric label or numeric code may be used22+Levels of Measurement and Types of Measurement ScalesInterval•The data have the properties of ordinal data, and the interval betweenobservations is expressed in terms of a fixed unit of measure•Interval data are always numeric•Eg: Temperature –today is 20C and yesterday was 24C. The difference between them is 4C (Celsius)23+Levels of Measurement and Types of Measurement ScalesRatio•The data have all the properties of interval data and theratio of two valuesis meaningful.•This scale must containa zero value that indicates that nothing existsfor the variable at the zero point.•Eg: Nominal data that would relate to employees24Salary Years Emp$43,0002$72,0003.5$48,50012+7.4 Types of Survey Sampling MethodsReasons for Taking a Sample:•less time-consuming than a census•less costly to administer than a census•less cumbersome and more practical to administer than acensus of the targeted population25+7.4 Types of Survey Sampling MethodsNon-probability sample•Items included are chosen without regard to their probability ofoccurrenceProbability sample•Items in the sample are chosen on the basis of known probabilities26+Simple Random Sample•Every individual or item from the frame (N) has an equalchance of being selected (1/N)•Selection may be with replacement or without replacement•Samples can be obtained from table of random numbers orcomputer random number generators•Simple to use but may not be a good representation of thepopulation’s underlying characteristics27+Systematic Sample•Divide frame of N individuals into n groups of k individuals:k = N/n•Randomly select one individual from the 1st group•Select every kth individual thereafter•Like simple random sampling, simple to use but may not be agood representation of the population’s underlying characteristics28+Systematic Sample (cont)•Divide our frame of 64 into 8 groups with 8 people in eachgroup•Randomly select one individual from the 1st group, say thethird person and then select every 8th person after that29+Stratified Sample•Divide population into two or more subgroups (called strata)according to some common characteristic•A simple random sample is selected from each subgroup,with sample sizes proportional to strata sizes (called proportionate stratified sampling)•Samples from subgroups are combined into one30+Stratified Sample (cont)•More efficient than simple random sampling or systematicsampling because of assured representation of items across entire population•Homogeneity of items within each stratum provides greaterprecision in the estimates of underlying population parameters31+
Let’s block ads! (Why?)

Do you need any assistance with this question?
Send us your paper details now
We’ll find the best professional writer for you!

 



error: Content is protected !!