Sampling Vs Census

A sample represents a population with certain amount of homogeneity in behavior Census deals with entire population Wrong data collected in census might get compounded to a great extent which is not there in sample In quality checking (e.g. destructive testing) only a sample can be tested and not the entire production lot..!! Sample gives greater amount of flexibility Sampling reduces time and cost Sampling improves accuracy if chosen properly

Sampling Methods
Sampling Methods

Probability

Random

Stratified

Systematic

Cluster

NonProbabilit y

Convenienc e

Quota

Judgmental

Snowball

Probability Sampling Method

Simple Random Sampling (SRS): Researchers use a
table of random numbers, random digit dialing, or some other random selection procedure that ensures that each sampling unit making up the defined target population has a known, equal, nonzero chance of being selected into the sample.

Systematic Random Sampling (SYMRS): Using

some form of an ordered list of the members of the defined target population, researchers select a random starting point for the first sampled member. After determining what the constant skip interval value needs to be to ensure representativeness, the skip interval is applied to select every nth member from the random starting point until the necessary sample is drawn. This sampling method is used such that the entire list is covered, no matter of the starting point. This method accomplishes the same end goal of the SRS method, and is more efficient.

Probability Sampling Method

Stratified Random Sampling (STRS): When the
defined target population is believed to have a non-normal (or skewed) distribution for one or more of its distinguishing characteristics (e.g., age, income, product ownership), researchers must identify subpopulations, referred to as strata. After the strata are segmented, a simple random sample is drawn for each stratum. Proportional and disproportional weighting factors may be applied to estimate overall population values.

Cluster Sampling : This method requires that the defined

target population be segmented into geographic areas, each of which is considered to be very similar to the others. Researchers randomly select a few areas, then conduct a census of the elements in each area. As an alternative, researchers can select more areas and take samples from each of those areas. This sampling method is appealing when researchers can easily identify the highly similar areas.

Non-Probability Sampling Method

Convenience Sampling: A method in which samples are
drawn at the convenience of the researcher or interviewer, often as the study is being conducted. The assumptions underlying this method are that the defined target population is homogeneous and the individuals interviewed are similar to the overall target population with regard to the characteristics being studied.

Judgmental

Participants are selected according to the researchers or some other experienced individuals belief that they will meet the requirements of the study. The underlying assumption is the researchers subjective belief that the opinions of a group of perceived experts on the topic of interest are representative of the entire defined target population.

Sampling:

Non-Probability Sampling Method

Quota Sampling: This method involves the selection of
prospective participants according to pre specified quotas regarding demographic characteristics (e.g., age, race, sex, income), specific attitudes (e.g., satisfied/dissatisfied, liking/disliking, great/marginal/no quality), or specific behaviors (e.g., regular/occasional/rare shopper, product user/nonuser, heavy user/light user). The underlying purpose of quota sampling is to provide an assurance that prespecified subgroups of the defined target population are represented on pertinent sampling factors that are determined by the researcher or client.

Snowball Sampling: A method that involves the practice of

subjectively identifying and qualifying a set of initial prospective respondents who can, in turn, help the researcher identify additional people to be included in the study. After interviewing one person, the interviewer would solicit that persons help to identify other people with similar characteristics, opinions, or feelings. Members of the defined target population who might not hold similar beliefs or feelings to those of the respondents are less likely to be included in this type of sample.

Determining Sample Size

Size of sample depends on:

Number of groups and sub-groups within the sample Importance of the information required Cost involved Extent of variation in the population data

Ad-hoc Methods:

Rule of thumb: Sample size= n% of population where Budgetary Constraints Time Constraint
n can be anything between 1 to 5 and each sample size should contain at least 25 to 30 samples

The Neyman-Pearson Approach

The Confidence Interval Method
Std Error = Std Error/deviation of the

-1.96
95% Confidence Level

1.96

sample

= Std Error deviation of the

population

= Sample size

If sample mean is m and allowable error is E then there is 95% probability that the population mean will be lying in m E provided E= 1.96 . Hence, n= (1.96 / E)

The Neyman-Pearson Approach

Hypothesis Testing Method
1. 2. 3. 4. 5. Specify the value of m under hypothesis H0 and H1 Specify the acceptable probabilities of two types of errors and Determine the std errors corresponding to these probabilities Provide some estimate of the population std deviation Calculate the sample size that meets the and error requirements by defining the Critical Value (CV) as

The Bayesian Approach

1.

Determine the expected value of information from samples of various sizes Estimate the cost of obtaining each of these samples

2.

3.

Calculate the net gain from the information obtained from each sample
Choose the sample that provides the largest gain

4.

Probability Vs Non-Probability Method

Probability Sampling
1. Sampling error can be controlled 2. The Selection process depends on specific techniques and is therefore not influenced 3. Time and cost involved may be high 4. Hypothesis testing is done through statistical techniques and hence results are more reliable 5. More reliable and representative if the population is heterogeneous 6. Preferable if complex, detailed estimates are required 7. Accuracy may be poor if the population is high 8. Formal sample frames are required 1. 2. 3. 4.

Non-Probability Sampling
Sampling error cannot be controlled Selection bias can be high Usually low cost, quicker alternative Parametric tests are not applicable and hence results are not that reliable More reliable if the population is homogeneous Reasonably useful if parameters to parameters be estimated are at broad, aggregated levels such as market share and total sales Accuracy in such situation is quite scattered Can be effective even in absence of an elaborate sample frame

5.

6.

7.

8.

Measurement
Measurement means assigning numbers or other symbols to characteristics of objects according to certain pre-specified rules.

One-to-one correspondence between the numbers and the characteristics being measured. The rules for assigning numbers should be standardized and applied uniformly. Rules must not change over objects or time.

Scaling

Scaling involves creating a continuum upon which measured objects are located.

Consider an attitude scale from 1 to 100. Each respondent is assigned a number from 1 to 100, with 1 = Extremely Unfavorable, and 100 = Extremely Favorable. Measurement is the actual assignment of a number from 1 to 100 to each respondent. Scaling is the process of placing the respondents on a continuum with respect to their attitude toward department stores

Primary Scales of Measurement

Scale Nominal
Numbers Assigned to Runners Rank Order of Winners
Finish
7 8 3

Ordinal

Finish Third place 8.2 Second place 9.1 First place 9.6

Interval

Performance Rating on a 0 to 10 Scale Time to Finish, in Seconds

Ratio

15.2

14.1

13.4

Primary Scales of Measurement Nominal Scale

The numbers serve only as labels or tags for identifying and classifying objects. When used for identification, there is a strict oneto-one correspondence between the numbers and the objects.

The numbers do not reflect the amount of the characteristic possessed by the objects.
The only permissible operation on the numbers in a nominal scale is counting. Only a limited number of statistics, all of which are based on frequency counts, are permissible, e.g., percentages, and mode.

Primary Scales of Measurement Ordinal Scale

A ranking scale in which numbers are assigned to objects to indicate the relative extent to which the objects possess some characteristic. Can determine whether an object has more or less of a characteristic than some other object, but not how much more or less. Any series of numbers can be assigned that preserves the ordered relationships between the objects. In addition to the counting operation allowable for nominal scale data, ordinal scales permit the use of statistics based on centiles, e.g., percentile, quartile, median.

Primary Scales of Measurement Interval Scale

Numerically equal distances on the scale represent equal values in the characteristic being measured.

It permits comparison of the differences between objects.

The location of the zero point is not fixed. Both the zero point and the units of measurement are arbitrary.

Any positive linear transformation of the form y = a + bx will preserve the properties of the scale.
It is not meaningful to take ratios of scale values. Statistical techniques that may be used include all of those that can be applied to nominal and ordinal data, and in addition the arithmetic mean, standard deviation, and other statistics commonly used in marketing research.

Primary Scales of Measurement Ratio Scale

Possesses all the properties of the nominal, ordinal, and interval scales.
It has an absolute zero point.

It is meaningful to compute ratios of scale values.

Only proportionate transformations of the form y = bx, where b is a positive constant, are allowed. All statistical techniques can be applied to ratio data.

Primary Scales of Measurement

Scale Nominal Basic Characteristics Numbers identify & classify objects Common Examples Social Security nos., numbering of football players Nos. indicate the Quality rankings, relative positions rankings of teams of objects but not in a tournament the magnitude of differences between them Differences Temperature between objects (Fahrenheit) Zero point is fixed, Length, weight ratios of scale values can be compared Marketing Permissible Statistics Examples Descriptive Inferential Brand nos., store Percentages, Chi-square, types mode binomial test Preference Percentile, rankings, market median position, social class Rank-order correlation, Friedman ANOVA

Ordinal

Interval Ratio

Attitudes, opinions, index Age, sales, income, costs

Range, mean, standard Geometric mean, harmonic mean

Productmoment Coefficient of variation

Classification of Scaling Techniques

Scaling Techniques

Comparative Scales

Noncomparative Scales

Paired Rank Comparison Order

Constant Q-Sort and Sum Other Procedure s

Continuous Itemized Rating ScalesRating Scales

Likert

Semantic Differential

Stapel

Comparison of Scaling Techniques

Comparative scales involve the direct comparison of stimulus objects. Comparative scale data must be interpreted in relative terms and have only ordinal or rank order properties. In non-comparative scales, each object is scaled independently of the others in the stimulus set. The resulting data are generally assumed to be interval or ratio scaled.

Relative Advantages of Comparative Scales

Small differences between stimulus objects can be detected.

Same known respondents.

reference

points

for

all

Easily understood and can be applied.

Involve fewer theoretical assumptions.

Tend to reduce halo or carryover effects from one judgment to another.

Relative Disadvantages of Comparative Scales

Ordinal nature of the data Inability to generalize beyond the stimulus objects scaled.

Comparative Scaling Techniques Paired Comparison Scaling

A respondent

is presented with two objects and asked to select one according to some criterion.

The data obtained are ordinal in nature.

Paired comparison scaling is the most widelyused comparative scaling technique.

Under the assumption of transitivity, it is possible to convert paired comparison data to a rank order.

Paired Comparison Selling

The most common method of taste testing is paired comparison. The consumer is asked to sample two different products and select the one with the most appealing taste. The test is done in private and a minimum of 1,000 responses is considered an adequate sample. A blind taste test for a soft drink, where imagery, self-perception and brand reputation are very important factors in the consumers purchasing decision, may not be a good indicator of performance in the marketplace. The introduction of New Coke illustrates this point. New Coke was heavily favored in blind paired comparison taste tests, but its introduction was less than successful, because image plays a major role in the purchase of Coke.

Comparative Scaling Techniques Rank Order Scaling

Respondents are presented with several objects simultaneously and asked to order or rank them according to some criterion.
It is possible that the respondent may dislike the brand ranked 1 in an absolute sense. Furthermore, rank order scaling also results in ordinal data. Only (n - 1) scaling decisions need to be made in rank order scaling.

Comparative Scaling Techniques Constant Sum Scaling

Respondents allocate a constant sum of units, such as 100 points to attributes of a product to reflect their importance. If an attribute is unimportant, the respondent assigns it zero points. If an attribute is twice as important as some other attribute, it receives twice as many points. The sum of all the points is 100. Hence, the name of the scale.

Q Sort Scaling
A comparative scaling technique that uses a rank order procedure to sort objects based on similarity with respect to some criterion.

Non - comparative Scaling Techniques

Respondents evaluate only one object at a time, and for this reason non-comparative scales are often referred to as monadic scales. Non-comparative techniques consist continuous and itemized rating scales. of

Continuous Rating Scale

Respondents rate the objects by placing a mark at the appropriate position on a line that runs from one extreme of the criterion variable to the other. The form of the continuous scale may vary considerably. How would you rate Sears as a department store? Version 1 Probably the worst - - - - - - -I - - - - - - - - - - - - - - - - - - - - - - - - - - - - - Probably the best Version 2 Probably the worst - - - - - - -I - - - - - - - - - - - - - - - - - - - - - - - - - - - - -Probably the best 0 10 20 30 40 50 60 70 80 90 100 Version 3 Neither good Very good nor bad Probably the worst - - - - - - -I - - - - - - - - - - - - - - - - - - - - - -- - - - - - - Probably the best Very bad

Itemized Rating Scales

The respondents are provided with a scale that has a number or brief description associated with each category. The categories are ordered in terms of scale position, and the respondents are required to select the specified category that best describes the object being rated.

The commonly used itemized rating scales are the Likert, semantic differential, and Stapel scales.

Likert Scale
The Likert scale requires the respondents to indicate a degree of agreement or disagreement with each of a series of statements about the stimulus objects. SD D Neither A A or D
1. Sears sells high quality merchandise. 2. Sears has poor in-store service. 5 3. I like to shop at Sears. 5 1 2X 1 3 2X 4 3

SA

5 4

3X

The analysis can be conducted on an item-by-item basis (profile analysis), or a total (summated) score can be calculated.

When arriving at a total score, the categories assigned to the negative statements by the respondents should be scored by reversing the scale.

Semantic Differential Scale

The semantic differential is a seven-point rating scale with end points associated with bipolar labels that have semantic meaning. SEARS IS: Powerful --:--:--:--:-X-:--:--: Weak Unreliable --:--:--:--:--:-X-:--: Reliable Modern --:--:--:--:--:--:-X-: Old-fashioned The negative adjective or phrase sometimes appears at the left side of the scale and sometimes at the right. This controls the tendency of some respondents, particularly those with very positive or very negative attitudes, to mark the right- or left-hand sides without reading the labels. Individual items on a semantic differential scale may be scored on either a -3 to +3 or a 1 to 7 scale.

Stapel Scale
The Stapel scale is a uni-polar rating scale with ten categories numbered from -5 to +5, without a neutral point (zero). This scale is usually presented vertically. SEARS +5 +5 +4 +4 +3 +3 +2 +2X +1 +1 HIGH QUALITY POOR SERVICE -1 -1 -2 -2 -3 -3 -4X -4 -5 -5 The data obtained by using a Stapel scale can be analyzed in the same

Basic Non - comparative Scales

Scale Continuous Rating Scale Itemized Rating Scales Likert Scale
Degrees of agreement on a 1 (strongly disagree) to 5 (strongly agree) scale Seven - point scale with bipolar labels Measurement of attitudes Easy to construct, administer, and understand More time - consuming

Basic Characteristics
Place a mark on a continuous line

Examples
Reaction to TV commercials

Advantages
Easy to construct

Disadvantages
Scoring can be cumbersome unless computerized

Semantic Differential

Brand, product, and company images Measurement of attitudes and images

Versatile to whether the

Stapel Scale

Unipolar ten - point scale, - 5 to +5, witho ut a neutral point (zero)

Easy to construct, administer over telephone

Confusing and