Business research proposal

SJ/-

100-8.pdf

Home >Business & Finance homework help >Management homework help >Business research proposal

Research Methods Quantitative Analysis

Dr. Sherif Abdel Fattah

Aims

• Demonstrate the importance of quantitative data in business related studies

• Identify ways of capturing quantitative data and how they could be used

• To understand the nature of the quantitative research • To point out main measurement types • Clearly demonstrate what is a survey and how it could be

conducted

• To reveal what is the experimental design research • How we can use decision making models

Definition of Quantitative Data Analysis

• A systematic approach in which researcher aims to measure (quantify) different variables during which numerical data is collected (using different scales and different approaches ) then the researcher transforms (using appropraite different statistical tools) the collected or observed data into specific findings.

Sources of Quantitative Data

Quantitative data can be collected in a variety of ways and from a number of different sources. Many of these are similar to sources of qualitative data, for example:

• Surveys • Observation (experimental design)

Quantitative Data

• Organizing and summarizing  Tables • Presenting  Tables and graphical displays • Analysing  Summary statistics and other statistical methods

Analysis of quantitative data may enable us to find:

• Similarities • Contrasts • Associations

Considerations in Quantitative Research

1. Hypotheses 2. Correlation vs. Causality 3. Generalisability 4. Reliability

Data sources

• Differentiate between primary and secondary data

• Source secondary data from World Bank website

• Distinguish between experimental and non-experimental methods

Primary vs. Secondary Data

Variables (Measurement is important)

• What is a variable? “A characteristic, number, or quantity that increases or decreases over time, or takes different values in different situations.”

Definition from Business Dictionary

• Independent variable • A variable that can assume different values and cause other

variables to change

• Dependent variable • A variable that assumes different values due to changes in the

independent variable

Experimental Study

• Definition: A test under controlled conditions that is made to demonstrate a known truth, to examine the validity of a statement, or to determine the efficacy of something previously untried.

• Experiments enable us to identify cause and effect • How it is done?

1. Treatment group vs. control group 2. Random assignment of participants to the groups 3. Set-up the situation 4. Manipulate a single variable 5. Keep the other variables same

What are the difficulties of Experimental Study?

Non-experimental Study

• An empirical study relying on observed data not obtained from experimental study

• Sources of observational data • Surveys • Administrative records • Governmental data

• Statistical techniques and models are used to establish and estimate (or model) causal relationships

2-11

Types of Non-experimental Study Data

I. Cross-sectional data: contains information on individual entities at a given point in time.

II. Time-series data: contains information on a single entity at different points in time.

III.Panel data: combines features of both. •Contains information on individual entities

at different points in time.

2-12

Example:

Difficulties of Non-experimental Studies

I. ‘Cause and Effect’ relationships may be difficult to determine

• The variables included in a model may be correlated by this may not determine causation.

II. The case of missing variables

2-14

Session 3

Learning Outcomes

• Explain what are constructs • Differentiate between the conceptualization and operationalization

of constructs

• Describe what are surveys and why they are used • Evaluate the information that can be collected through surveys • Differentiate between different types of variable and levels of data • Surveys

Surveys: It all starts with Constructs

• What is a construct? • mental abstractions  express ideas, people, organisations,

events and/or objects/things.

Construct

Conceptualization

Meaning or definition of a

concept

Operationalization

Measurement

Constructs

• Some constructs are relatively simple • e.g. Political party affiliation, age, height, gender

• Some constructs are complex (multi-dimensional) • e.g. Innovation, Service Quality; Customer satisfaction;

Happiness of population

EXAMPLE - What constructs do these items measure?

1. Have a job which leaves sufficient time for personal or family life

2. Have a job with good physical working conditions

3. Have a job that I would never think of leaving

Constructs: Different Definitions of Innovation

• ‘Turning an idea into a solution that adds value from a customer’s perspective.’ Nick Skillicorn

• ‘The introduction of new products and services that add value to the organisation.’ Kevin McFarthing

How will you operationalize these definitions?

Constructs vs. Variables

• Uni-dimensional constructs • One variable

• Examples  Age, height, price of a product

• Multi-dimensional constructs • Multiple underlying variables

• Examples  Health, wellbeing, customer satisfaction, service quality

Customer Satisfaction Model

Service Quality Construct and Underlying Variables

Class Exercise - Constructs

• Academic literature suggests that service quality (construct) determines customer satisfaction (another construct).

• Can you identify the dimensions that can be used to used to measure service quality in the airline industry?

• How can you measure customer satisfaction in the airline industry? • Reliability: to perform the promised service dependably and accurately • Tangibility: physical facilities, equipment, and appearance of personnel • Responsiveness: to help customers and provide prompt service • Assurance: courtesy, knowledge, ability of employees to inspire trust and confidence • Empathy: caring, individualized attention the firm provides its customers

Surveys - What and Why?

• What are surveys • Quantitative data collection tool

• Why are they used • Learn about your audience

• Data-based decision making

• Tracking trends over time

Possible Options For Survey Design

• To re-use questions which seem suitable that have already been used in other surveys.

• To adapt questions which have been developed for other purposes to suit new needs or populations.

• To write entirely new questions. • Pilot study may be required

Information Collected Through Surveys

• Knowledge questions Knowledge questions assess the respondent’s familiarity, awareness, or understanding of someone or something, such as facts, information, descriptions, or skills.

• Factual judgment questions Factual judgment questions require respondents to remember autobiographical events and use that information to make judgments. Example: During the past two weeks, how many times did you see or talk to a medical doctor?

• Socio-demographic questions Socio-demographic questions typically ask about respondent characteristics such as age, marital status, income, employment status,

and education.

Information Collected Through Surveys

• Behavioral questions Behavioral questions ask people to report on things they do or have done.

Example: Have you ever smoked cigarettes?

• Attitudinal questions Attitudinal questions ask about respondents’ opinions, attitudes, beliefs, values, judgments, emotions, and perceptions. These cannot be measured by other means; we are dependent on respondents’ answers. Example: Do you think smoking cigarettes is bad for the smoker’s health?

• Intention questions Intention questions ask respondents to indicate their intention regarding some behavior. They share features with attitudinal questions. Example: Do you intend to stop smoking?

Types Of Variables and Levels of Data

• Types of Variables  Continuous Variable: a variable that has an infinite number of possible

values.

 Discrete Variable: a variable that can only take on a certain number of

values

• Levels of Data • The numerical values in statistics are measurements taken with some kind of scale or

device. These scales provide different levels of information.

• The four types or levels of information (data) are:  Nominal

 Ordinal

 Interval

 Ratio

Example

• a) Whether you own a Panasonic television set

• b) Your status as a full-time or a part- time student

• c) Number of people who attended your school’s graduation last year

• Qualitative Variable

• two levels: yes/no

• no measurement

• Qualitative Variable

• two levels: full/part

• no measurement

• Quantitative, Discrete Variable

• a countable number

• only whole numbers

Nominal Data (Categorical)

• Nominal data is the least powerful.

• Typical examples of Nominal or categorical scales are: • The value of “1” assigned to female and “2” to male. • The count of times a head is shown when a coin is tossed. • Numbers used to denote different types of occupations, university

years, etc ...

Ordinal Data (Ranked)

Two rules apply to ordinal data: 1. Different numbers mean different thing. 2. The things being measured can be ranked or ordered along some dimension.

When things are ordered they are arranged in some logical sequence, they may have ‘more or less’ of a particular characteristic than others in a set. • Examples:

• Racing (1st, 2nd, 3rd positions) • Stage of cancer spread (Stage 1 to 4)

The primary limitation with ordinal measurements is that the numbers do not state how much ‘more or less’ the difference exists in two or more collections of data. • A typical use of ordinal data is to measure people’s preferences or rankings for

candidates (Political polls). • Another is for people to rank their preference for a variety of different uses for a new

park.

Interval Data

The third class of measurement data is ‘equidistant interval’ (usually just referred to as interval). Three rules apply to interval scale:

1. Different numbers must mean different things. 2. The things being measured can be ranked or ordered along some dimension. 3. The differences between adjacent levels on a scale must be equal.

The key requirement is that a single unit change always measures the same amount of change in whatever is being measured. The unit gradations within the scale may be as broad or as fine as needs be; but they must be equal in difference.

On a five-point scale the distance between “3” and “4” or “4” and “5” might be measured in tenths , hundreds, thousands or even finer but they must apply to every part of the scale equally.

Ratio Data

• Provides most information about the data • Four rules apply to ratio scales: 1. Different numbers must still mean different things. 2. The data can be ranked or ordered along some dimension. 3. The intervals between adjacent points must be equal. 4. The measurement scale must have an absolute or fixed zero point. • Typical examples of Ratio scales are time, distance, mass or temperature.

Task - Classify these variables as Nominal, Ordinal, Interval or Ratio

Gender Age Weight (lbs) Height (in) Smoking (yes/no) Nationality

Patient 1 M 59 175 69 1 American

Patient 2 F 67 140 62 0 British

Patient 3 F 73 155 59 1 Canadian

Patient 4 M 55 162 67 0 Indian

Patient 5 M 49 151 63 0 British

Patient 6 F 51 140 58 0 Indian

… … … …

Patient 75 M 48 200 72 1 Indian

Types Of Questions Used In Surveys

• Closed ended – Participants choose, among a list of possible choices, the response option that best reflects their opinions.

• Open ended – Participants are not given a list of response options, but rather are asked to answer the question in their own words.

• Combination of closed and open-ended (e.g., provide an “other” option which participants can define).

Types of Questions Used in Surveys

Types of Response Options for Close Ended Survey Questions

• Dichotomous or Multichotomus • Dichotomous: yes/no; male/female • Multichotomus: Years with the department; Highest level of education

• Multiple Choice: • Choose one response option (e.g., How would you characterize your political views? • Select multiple responses (e.g., Select all the factors you consider when choosing a

college

• Likert Rating Scale • Participants are asked to indicate their level of agreement with a statement on a

defined scale

• Ranking • Rank in order of importance the factors that influenced your decision to attend this

college

Survey Question Design: Dos And Don’ts

Dos

Don’t formulate ‘double barrelled’ questions

Don’t use ‘leading’ questions

Don’t use ‘double negative’ questions

Don’t ask questions on topics that people may not know

Don’t use questions that are unnecessarily personal/sensitive

Don'ts

Do consider why you are asking the question

Do consider whether the respondent will be able to answer the question

Do make questions short and easy to understand

Do make question wording as clear and unambiguous as possible

Examples: Avoid asking leading questions

Poor: How do you feel about building an ice arena in downtown Athens where the railroad property has been sitting unused for a number of years?

Better: An ice arena should be built on the railroad property in downtown Athens.

1 = Strongly agree

2 = Agree

3 = Disagree

4 = Strongly disagree

Examples: Use simple, clear conventional language

Poor: How often do you Discipline your toddler?

Better: How often do you put your toddler into timeout? Check only one.

___ Once a day ___ Several times a day ___ Once a week ___ Several times a week

Examples: Use mutually exclusive and exhaustive categories

Poor: What is your marital status?

___ Married ___ Single

Better: What is your marital status?

___ Married ___ Divorced

___ Separated ___ Widowed

___ Never Married

Examples: Avoid double-barreled/ double negative questions

Are your lectures and tutorials enjoyable and easy to understand?

Yes / No

Shouldn’t the UAE oppose the World Bank?

Yes / No

Validity and Reliability in Surveys

• The validity of a survey is considered to be the degree to which it measures what it claims to measure

• Internal validity is the confidence that we can place in the cause and effect relationship in a study. Internal validity only shows that you have evidence to suggest that a program or study had some effect on the observations and results. If the researcher includes all confounding variables in the study then the internal validity is high

• External validity helps to answer the question: can the research be applied to the “real world”? If the research is applicable to other situations, external validity is high. If the research cannot be replicated in other situations, external validity is low.

• Construct validity determines whether the intended construct is being measure appropriately.

• Reliability refers to the repeatability of the instrument and internal consistency of questions asked

Important Key Point in Constructing Survey

• Good survey measures must be grounded on sound theory and conceptual definitions

• Developing good survey measures takes much time, resources, experiences, and commitment, but the payoff can be immense.

• If there is a good, published measure available, Use it. Not to reinvent the vehicle.

Why Sample?

• Selecting a sample is less time-consuming & less costly than selecting every item in the population (census).

• An analysis of a sample is less cumbersome and more practical than an analysis of the entire population.

Sampling Error • Sampling error is the difference between the information we

obtain from the sample and the information contained in the population.

• The extent of the sampling error depends on three things: a) the method by which the sample is selected; • Be smart – wouldn’t undertake a survey of high income

families in Karama

b) the variability in the population;

• The higher the variability in the population, the large your sample needs to be

c) the size of the sample.

• As the sample size increases, the sampling error decreases

Types of Samples

Samples

Non-Probability Samples

Judgment

Probability Samples

Simple

Random

Systematic

Stratified

Cluster

Convenience

Probability Sample: Simple Random Sample

• Every individual or item from the frame has an equal chance of being selected.

• Selection may be with replacement (selected individual is returned to frame for possible reselection) or without replacement (selected individual isn’t returned to the frame).

• Samples obtained from table of random numbers or computer random number generators.

Chap 7-48

• Decide on sample size: n

• Divide frame of N individuals into groups of k individuals: k=N/n

• Randomly select one individual from the 1st group

• Select every kth individual thereafter

Probability Sample: Systematic Sample

N = 40

n = 4

k = 10

First Group

Probability Sample: 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

• Samples from subgroups are combined into one

• This is a common technique when sampling population of voters, stratifying across racial or socio-economic lines.

Population

Divided

into 4

strata

Probability Sample Cluster Sample

• Population is divided into several “clusters,” each representative of the population

• A simple random sample of clusters is selected

• All items in the selected clusters can be used, or items can be chosen from a cluster using another probability sampling technique

• A common application of cluster sampling involves election exit polls, where certain election districts are selected and sampled.

Population

divided into 16

clusters. Randomly selected

clusters for sample

Probability Sample: Comparing Sampling Methods

• Simple random sample and Systematic sample • Simple to use

• May not be a good representation of the population’s underlying characteristics

• Stratified sample • Ensures representation of individuals across the entire

population

• Cluster sample • More cost effective

• Less efficient (need larger sample to acquire the same level of precision)

Education, Inc. publishing as

Prentice Hall

1-52

Procedures for Collecting Data

Data Collection Procedures

Written

questionnaires

Experiments

Telephone

surveys

Direct observation and

personal interview

Evaluating Survey Worthiness

• What is the purpose of the survey? • Is the survey based on a probability sample? • Coverage error – appropriate frame? • Nonresponse error – follow up • Measurement error – good questions elicit good responses • Sampling error – always exists

Types of Survey Errors

• Coverage error or selection bias • Exists if some groups are excluded from the frame and have no

chance of being selected

• Nonresponse error or bias • People who do not respond may be different from those who do

respond

• Sampling error • Variation from sample to sample will always exist

• Measurement error • Due to weaknesses in question design, respondent error, and

interviewer’s effects on the respondent (“Hawthorne effect”)

Chap 7-55

Types of Survey Errors

• Coverage error

• Non response error

• Sampling error

• Measurement error

Excluded from

frame

Follow up on

nonresponses

Random differences

from sample to sample

Bad or leading question

(continued)

Some Terms to be Familiar with…

• Sample: Subset of a population • When the population is too large, a subgroup is chosen to represent the population. The

representative group is called a sample and the process is called sampling.

• A sample is “a smaller (but hopefully representative) collection of units from a population used to determine truths about that population” (Field, 2005)

• Sampling Frame: The specific set of units from which a sample is chosen (Telephone directory, Class lists). Caution: Must assess sampling frame errors

• Unit of analysis: The characteristic of a unit to be measured.

• Parameter: A characteristic of a population.

• Statistic: A measured characteristic of a sample.

• Why sample? • Resources (time, money) and workload • Gives results with known accuracy that can be calculated mathematically

Steps in Sampling Process

1. Defining the population of concern 2. Identifying a sampling frame 3. Specifying a sampling method for selecting items or

events from the frame

4. Determining the sample size 5. Implementing the sampling plan 6. Sampling and data collecting 7. Reviewing the sampling process

Sampling Bias And Sampling Error

• Sampling Bias: Exists due to a flaw in the sample selection process, where a subset of the data is systematically excluded due to a particular attribute

• For example survivorship bias

• Sampling Error: Occurs when a sample does not reflect the attributes of the population studied

• More common when the target population highly diverse