Research Scaling & Sampling

66
© Dr.B.K.Murty, Bangalore, India © Dr.B.K.Murty, Bangalore, India Business Research Methods Module 3

Transcript of Research Scaling & Sampling

Dr.B.K.Murty, Bangalore, India

Business Research MethodsModule 3

Module 3Dr.B.K.Murty, Bangalore, India

Measurement Scales Types of Scale Selecting a Measurement Scale Sampling Design Nature Concepts Steps in Sampling Design Probability and non-probability sampling

Dr.B.K.Murty, Bangalore, India

The Scaling Process

3

ScalingScaling is the procedure for the assignment of numbers to a property of objects in order to impart some of the characteristics of numbers to the properties in question. Selecting and constructing a measurement scale requires the consideration of several factors that influence the reliability, validity, and practicality of the scale.

Dr.B.K.Murty, Bangalore, India

Dr.B.K.Murty, Bangalore, India

Types of Scales

Types of ScalesMain CategoriesDr.B.K.Murty, Bangalore, India

Rating Scales Ranking Scales Sorting Scales Cumulative Scales

Simple Category ScaleDr.B.K.Murty, Bangalore, India

Rating Scales

This scale is also called a dichotomous scale. It offers two mutually exclusive response choices. (yes and no, OR agree and disagree. )

I plan to purchase a Lenovo laptop in the next 12 months. q Yes q No7

Rating Scales Multiple-Choice, Single-Response ScaleDr.B.K.Murty, Bangalore, India

When there are multiple options for the rater but only one answer is sought. This scale produces nominal data.What newspaper do you read most often for financial news? q Economic times q Business Standard q Regional newspaper q National newspaper q Other (specify:_____________)8

Multiple-Choice, Multiple-Response ScaleIt allows the rater to select one or several alternatives. This scale generates nominal data.

Rating Scales

Dr.B.K.Murty, Bangalore, India

What sources did you use when designing your new home? Please check all that apply. q Online planning services q Magazines q Independent contractor/builder q Designer q Architect q Other (specify:_____________)9

Likert Scale

Rating Scales

Dr.B.K.Murty, Bangalore, India

1.Developed by Rensis Likert. Most frequently used variation of the summated rating scale. 2.Summated rating scales consist of statements that express either a favorable or unfavorable attitude toward the object of interest. 3.The participant is asked to agree or disagree with each statement. 4.Each response is given a numerical score 5.The scale produces interval data.The Internet is superior to traditional libraries for comprehensive searches. q Strongly disagree q Disagree q Neither agree nor disagree q Agree q Strongly agree10

Semantic DifferentialDr.B.K.Murty, Bangalore, India

Rating Scales

The semantic differential scale measures the psychological meanings of an attitude object using bipolar adjectives.

11

Adapting SD ScalesNearby Short time required to reach store ___: ___: ___: ___: ___: ___: ___: ___: ___: ___: ___: ___: ___: ___: ___: ___: ___: ___: ___: ___: ___: ___: ___: ___: ___: ___: ___: ___: ___: ___: ___: ___: ___: ___: ___: Distant

Rating Scales

Convenience of Reaching the Store from Your LocationLong time required to reach store Easy Drive Easy to find parking place Inconvenient to other stores I shop

Dr.B.K.Murty, Bangalore, India

Difficult drive Difficult to find parking place Convenient to other stores I shop

Products offeredWide selection of different kinds of products Fully stocked Undependable products High quality Numerous brands Unknown brands ___: ___: ___: ___: ___: ___: ___: ___: ___: ___: ___: ___: ___: ___: ___: ___: ___: ___: ___: ___: ___: ___: ___: ___: ___: ___: ___: ___: ___: ___: ___: ___: ___: ___: ___: ___: ___: ___: ___: ___: ___: ___: Limited selection of different kinds of products Understocked Dependable products Low quality Few brands Well-known brands

12

Rating Scales

SD Scale for Analyzing Actor Candidates

Dr.B.K.Murty, Bangalore, India

13

Rating Scales

Graphic of SD AnalysisDr.B.K.Murty, Bangalore, India

14

Numerical ScaleDr.B.K.Murty, Bangalore, India

Rating Scales

1.Numerical scales have equal intervals that separate their numeric scale points. 2.The verbal anchors serve as the labels for the extreme points. 3.Numerical scales are often 5-point scales but may have 7 or 10 points. 4.The participants write a number from the scale next to each item. 5.It produces either ordinal or interval data.

15

Rating Scales

Multiple Rating List ScalesDr.B.K.Murty, Bangalore, India

A multiple rating scale is similar to the numerical scale but differs in two ways: 1.It accepts a circled response from the rater, 2.The layout facilitates visualization of the results. This scale produces interval data.

16

Stapel ScalesDr.B.K.Murty, Bangalore, India

Rating Scales

The Stapel scale is used as an alternative to the semantic differential, especially when it is difficult to find bipolar adjectives that match the investigative question. Stapel scales produce interval data.

17

Constant-Sum ScalesDr.B.K.Murty, Bangalore, India

Rating Scales

The constant-sum scale helps researchers to discover proportions. The participant allocates points to more than one attribute or property indicant, such that they total a constant sum, usually 100 or 10. This scale produces interval data.

18

Dr.B.K.Murty, Bangalore, India

1.Originally created to enable researchers to discern fine differences. 2.Respondents are instructed to mark their response at any point along a continuum. 3.The score is a measure of length from either endpoint. 4.The results are treated as interval data. 5.The difficulty is in coding and analysis. 6.Graphic rating scales use pictures, icons, or other visuals to communicate 7.Graphic scales are often used with children.

Graphic Rating Scales

Rating Scales

19

Ranking Scales

Ranking Scales

Dr.B.K.Murty, Bangalore, India

In ranking scales, the participant directly compares two or more objects and makes choices among them. The participant may be asked to select one as the best or most preferred.Paired-comparison

scale Forced ranking scale Comparative scale

Ranking Scales

Paired-Comparison ScaleDr.B.K.Murty, Bangalore, India

The participant can express attitudes unambiguously by choosing between two objects. The number of judgments required in a paired comparison is [(n)(n1)/2], where n is the number of stimuli or objects to be judged.

21

Forced Ranking ScaleDr.B.K.Murty, Bangalore, India

Ranking Scales

The forced ranking scale lists attributes that are ranked relative to each other. This method is faster than paired comparisons and is usually easier and more motivating to the participant.

22

Comparative ScaleDr.B.K.Murty, Bangalore, India

Ranking Scales

The participant compares an object against a standard.

23

SortingDr.B.K.Murty, Bangalore, India

Sorting Scales

Q-sorts require sorting of a deck of cards into piles that represent points along a continuum. The participant groups the cards based on his or her response to the concept written on the card.

24

Cumulative ScalesWith a cumulative scale, a participants agreement with one extreme scale item endorses all other items that take a less extreme position. A pioneering scale of this type was the scalogram.Dr.B.K.Murty, Bangalore, India

Ideal Scalogram PatternItem

2X __ __ __ __

4X X __ __ __

1X X X __ __

3X X X X __

Participant Score

4 3 2 1 0

* X = agree; __ = disagree.

25

Dr.B.K.Murty, Bangalore, India

Selecting a Measurement Scale

26

Selecting a Measurement ScaleDr.B.K.Murty, Bangalore, India

Research objectives Data properties Balanced or unbalanced Number of scale points

Response types Number of dimensions Forced or unforced choices Rater errors

27

Selecting a Measurement ScaleDr.B.K.Murty, Bangalore, India

Research objectives Data properties Balanced or unbalanced Number of scale points

Response types Number of dimensions Forced or unforced choices Rater errors

28

Research objectivesDr.B.K.Murty, Bangalore, India

Researchers face two types of scaling objectives: 1)to measure characteristics of the participants who participate in the study, 2)to use participants as judges of the objects or indicants presented to them.

Selecting a Measurement ScaleDr.B.K.Murty, Bangalore, India

Research objectives Data properties Balanced or unbalanced Number of scale points

Response types Number of dimensions Forced or unforced choices Rater errors

30

Response TypesRating scaleDr.B.K.Murty, Bangalore, India

A rating scale is used when participants score an object or indicant without making a direct comparison to another object or attitude. Ranking scale constrain the study participant to making comparisons and determining order among two or more properties or objects. Categorization asks participants to put themselves or property indicants in groups or categories. Sorting requires that participants sort card into piles using criteria established by the researcher.

Ranking scale

Categorization

Sorting

Selecting a Measurement ScaleDr.B.K.Murty, Bangalore, India

Research objectives Data properties Balanced or unbalanced Number of scale points

Response types Number of dimensions Forced or unforced choices Rater errors

Data propertiesNominal Ordinal interval Ratio

Dr.B.K.Murty, Bangalore, India

Selecting a Measurement ScaleDr.B.K.Murty, Bangalore, India

Research objectives Data properties Balanced or unbalanced Number of scale points

Response types Number of dimensions Forced or unforced choices Rater errors

34

Number of DimensionsDr.B.K.Murty, Bangalore, India

Unidimensional

Measure only one attribute of the participant or object.

A multidimensional scale recognizes that an object might Multi-dimensional be better described with several dimensions.

Selecting a Measurement ScaleDr.B.K.Murty, Bangalore, India

Research objectives Data properties Balanced or unbalanced Number of scale points

Response types Number of dimensions Forced or unforced choices Rater errors

36

Balanced or UnbalancedDr.B.K.Murty, Bangalore, India

A balanced rating scale has an equal number of categories above and below the midpoint. Scales can be balanced with or without a midpoint option. An unbalanced rating scale has an unequal number of favorable and unfavorable response choices.

How good an actress is Aishwarya Rai?

qVery bad qBad qNeither good nor bad qGood qVery good

qPoor qFair qGood qVery good qExcellent

Forced or Unforced ChoicesAn unforced-choice rating scale provides participants with an opportunity to express no opinion when they are unable to make a choice among the alternatives offered. A forced-choice scale requires that participants select one of the offered alternatives.

Dr.B.K.Murty, Bangalore, India

How good an actress is Aishwarya Rai? q Very bad Unforced q Bad q Neither good nor bad q Good q Very good q No opinion q Dont know

q Very bad Forced q Bad q Neither good nor bad q Good q Very good

Selecting a Measurement ScaleDr.B.K.Murty, Bangalore, India

Research objectives Data properties Balanced or unbalanced Number of scale points

Response types Number of dimensions Forced or unforced choices Rater errors

39

Dr.B.K.Murty, Bangalore, India

A scale should be appropriate for its purpose. For a scale to be useful, it should match the stimulus presented and extract information proportionate to the complexity of the attitude object, concept, or construct. As the number of scale points increases, the reliability of the measure increases. How good an actress is Aishwarya Rai?q Very bad q Bad q Neither good nor bad q Good q Very good q Very bad q Somewhat bad q A little bad q Neither good nor bad q A little good q Somewhat good q Very good40

Number of Scale Points

Selecting a Measurement ScaleDr.B.K.Murty, Bangalore, India

Research objectives Data properties Balanced or unbalanced Number of scale points

Response types Number of dimensions Forced or unforced choices Rater errors

41

Rater ErrorsSome raters are reluctant to give extreme judgments and this fact accounts for the error of central tendency. Participants may also be easy raters or hard raters making what is called error of leniency.Dr.B.K.Murty, Bangalore, India

Adjust strength of descriptive adjectives Space intermediate descriptive phrases farther apart Provide smaller differences in meaning between steps near the ends of the scale Use more scale points

Rater ErrorsDr.B.K.Murty, Bangalore, India

A primacy effect is one that occurs when respondents tend to choose the answer that they saw first. When respondents choose the answer seen most recently, the recency effect has occurred. These problems can be avoided by randomizing the order in which responses are presented.

Reverse order of alternatives periodically

43

Dealing with Halo EffectsThe halo effect is the systematic bias that the rater introduces by carrying over a generalized impression of the subject from one rating to another.Dr.B.K.Murty, Bangalore, India

e.g, a teacher may expect that a student who did well on the first exam to do well on the second.

Rate one trait at a time

Reveal one trait per page

Reverse anchors periodically

Dr.B.K.Murty, Bangalore, India

Sampling

The Nature of SamplingSamplingDr.B.K.Murty, Bangalore, India

Population Population Census Sampling

Element

frame

46

1.The basic idea of sampling is that by selecting some of the elements in a population, we may draw conclusions about the entire population. 2.A population element is the individual participant or object on which the measurement is taken. It is the unit of study. It may be a person but it could also be any object of interest. 3.A population is the total collection of elements about which we wish to make some inferences. 4.A census is a count of all the elements in a population. 5.A sample frame is the listing of all population elements from which the sample will be drawn.

Dr.B.K.Murty, Bangalore, India

Why Sample?Dr.B.K.Murty, Bangalore, India

Availability of elements Availability of elements

Greater speed Greater speed

Samplin Samplin g g provides provides

Lower cost Lower cost

Greater accuracy

48

When Is a Census Appropriate?

Dr.B.K.Murty, Bangalore, India

Feasible

Necessary

When the population is small and the variability within the population is high. A census is feasible when the population is small and necessary when the elements are quite different from each other.

What Is a Valid Sample? AccurateDr.B.K.Murty, Bangalore, India

Precise

1.Validity of a sample depends on accuracy and precision. 2.Accuracy is the degree to which bias is absent from the sample. 3.Precision of estimate is how correctly it represents the characteristics of the population it purports to represent 4.Sampling error is what is left after all known sources of systematic variance have been accounted for. 5.Precision is measured by the standard error of estimate, a type of standard deviation measurement.

Sampling Design within the Research Process

Dr.B.K.Murty, Bangalore, India

51

Steps in Sampling DesignWhat is the target population? What is the target population? What are the parameters of interest? What are the parameters of interest? What is the sampling frame? What is the sampling frame? What is the appropriate sampling method? What is the appropriate sampling method? What size sample is needed? What size sample is needed?

Dr.B.K.Murty, Bangalore, India

When to Use Larger Sample Sizes?Population varianceDr.B.K.Murty, Bangalore, India

Number of subgroups Number of subgroups

Desired precision Desired precision

Confidence level Confidence level

Small error range53

Types of Sampling DesignsDr.B.K.Murty, Bangalore, India

Nonprobability sampling is an arbitrary and

subjective sampling procedure where each population element does not have a known, nonzero chance of being included.

Probability sampling is a controlled, randomizedprocedure that assures that each population element is given a known, nonzero chance of selection.

Types of Sampling DesignsDr.B.K.Murty, Bangalore, India

Element Selection Unrestricted Restricted

Probability Simple random Complex random Systematic Cluster Stratified Double

Nonprobability Convenience Purposive Judgment Quota Snowball

55

Dr.B.K.Murty, Bangalore, India

1.In drawing a sample with simple random sampling, each population element has an equal chance of being selected into the samples. 2.The sample is drawn using a random number table or generator. 3.The probability of selection is equal to the sample size divided by the population size. Advantages Easy to implement with random dialing Disadvantages Requires list of population elements Time consuming Uses larger sample sizes Produces larger errors High cost

Simple Random

Probability

56

Systematic

Probability

Dr.B.K.Murty, Bangalore, India

An element of the population is selected at the beginning with a random start and then every Kth element is selected until the appropriate size is selected.

Advantages Simple

Disadvantages Periodicity

to design Easier than simple random Easy to determine sampling distribution of mean or proportion

within population may skew sample and results Trends in list may bias results Moderate cost

57

Stratified

Probability

Dr.B.K.Murty, Bangalore, India

The population is divided into subpopulations or strata and uses simple random on each strata. Results may be weighted or combined.

Advantages

Disadvantages

Control of sample size in strata Increased statistical efficiency Provides data to represent and analyze subgroups Enables use of different methods in strata

Increased error will result if subgroups are selected at different rates Especially expensive if strata on population must be created High cost

ClusterDr.B.K.Murty, Bangalore, India

Probability

The population is divided into internally heterogeneous subgroups. Some are randomly selected for further study.Advantages

Disadvantages

Provides an unbiased estimate of population parameters if properly done Economically more efficient than simple random Lowest cost per sample Easy to do without list

Often lower statistical efficiency due to subgroups being homogeneous rather than heterogeneous Moderate cost

Stratified and Cluster Sampling

Probability

Stratified Population divided into a few subgroups Homogeneity within subgroups Heterogeneity between subgroups Choice of elements from within each subgroup

Cluster Population divided into many subgroups Heterogeneity within subgroups Homogeneity between subgroups Random choice of subgroups

Dr.B.K.Murty, Bangalore, India

Area SamplingDr.B.K.Murty, Bangalore, India

Probability

Area sampling is a cluster sampling technique applied to a population with welldefined political or geographic boundaries. It is a low-cost and frequently used method.

61

Double SamplingDr.B.K.Murty, Bangalore, India

Probability

In drawing a sample with double (sequential or multiphase) sampling, data are collected using a previously defined technique. Based on the information found, a subsample is selected for further study. Disadvantages Advantages May reduce costs if Increased costs if first stage results in discriminately used enough data to stratify or cluster the population

62

When the research does not require generalization to a population parameter, then there is no need to ensure that the sample fully reflects the population. The researcher may have limited objectives such as those in exploratory research.Dr.B.K.Murty, Bangalore, India

Nonprobability Samples

No need to generalize

Feasibility Feasibility

Limited objectives Limited objectives

Time Time

Cost

Nonprobability Sampling MethodsDr.B.K.Murty, Bangalore, India

Convenience Convenience Judgment Judgment Quota Quota Snowball Snowball

64

Nonprobability Sampling MethodsConvenience ConvenienceDr.B.K.Murty, Bangalore, India

Convenience samples are nonprobability samples where the element selection is based on ease of accessibility. Judgment sampling is purposive sampling where the researcher arbitrarily selects sample units to conform to some criterion. Quota sampling is also a type of purposive sampling. Relevant characteristics are used to stratify the sample which should improve its representativeness. Snowball sampling means that subsequent participants are referred by the current sample elements.

Judgment Judgment

Quota Quota

Snowball Snowball

Dr.B.K.Murty, Bangalore, India

End of Module 3