Splitting Commercials Shows Their Strength Marketing Research Help

A multiple lime series design” as used to examine the buildup effect of increased advertising. The data were obtained from the Niclxen BASES split-cableTV  advertising field experiment ln the split-cable system. one group of households was assigned to the experimental panel and an equivalent group to the control panel. The two groups were matched on demographic variables. Data were collected for 76 weeks. Both panels received the same level of advertising for the first 52 weeks for the brand in question. For the next:24 weeks, the experimental panel was exposed to twice as much advertising as the control panel. The results indicated that the buildup effect of advertising was immediate with a duration of the order of the purchase cycle. Information of this type can be useful in selecting advertising timing patterns (allocating a set of advertising exposures over a specified period to obtain maximum impact).

A recent experimental study showed a new approach to relating advertising exposures of TV media schedules to sales-related market performance. These measures included cumulative sales volume, number of purchases. penetration, and repeat-purchase patterns. The approach was derived from a matched split-cable experimental design methodology. Consumer panel companies such as BASES can provide the data needed to implement such an approach. In the future, it is expected that companies like Nielsen BASES will be at the forefront of using technological advances to measure consumer advertising exposure and purchase behavior simultaneously

In concluding our discussion of experimental, true experimental, and quasi-experimental designs. we summarize in Table 7.3 the potential sources of invalidity that may affect each of these designs. In this table, a minus sign indicates a definite weakness, a plus sign indicates that the factor is controlled, a question mark denotes a possible source of concern, and a blank means that the factor is not relevant. It should be remembered that potential sources of invalidity are not the same as actual errors.

Statistical Designs

Statistical designs consist of a series of basic experiments that allow for statistical control and analysis of external variables. In other words, several basic experiments are conducted simultaneously. Thus, statistical designs are influenced by the same sources of invalidity that affect the basic designs being used. Statistical designs offer the following advantages

1. The effects of more than one independent variable can be measured.
2. Specific extraneous variables can be statistically controlled.
3. Economical designs can be formulated when each test unit is measured more than once.

The most common statistical designs are the randomized block Latin square design, and the factorial design

Sources of Invalidity of Experimental Designs

Sources of Invalidity of Experimental Designs

Randomized Block Design

A randomized block design is useful when there is only one major external variable. such as sales. store size. or income of the respondent. that might influence t~ dependent variable. The test units are blocked. or grouped. on the basis of the external variable. The researcher must be able to identify and measure the blocking variable. By blocking. the researcher ensures that the various experimental and control groups are matched closely on the external variable.

As this example illustrates. in most marketing research situations. external variables, s~ch as sales. store size. store type, location. income, occupation, and social class of the respondent, can influence the dependent variable. Therefore, generally speaking, randomized block designs are

An Example of a Randomized Block Design

An Example of a Randomized Block Design

more useful than completely random designs. Their main limitation is that the re: carcher can control for only one external variable. When more than one variable must be controlled, the researcher must use Latin square or factorial designs

Randomized Block Design

Let us exterd the department store (Sears) test commercial example to measure the impact of humor on the, effectiveness of advertising.~o Three test commercials. A, B, and Co have. respectively. no humor, some humor, and high levels of humor. Which of these would be the most effective? Management fcel~ that
the respondents’ evaluation of the commercials will be influenced b> the extent of their <tore patronage, so store patronage is identified as the blocking variable. and the randomly selected re-pondcnts are clasified into four blocks (heavy. medium, light, or non patrons of the department store). Respondents from each block are randomly assigned to the treatment groups (test commercials A, B. and C). The results reveal that the some-humor commercial (B) was the most effective overall (see Table 7.4

Latin Square Design

To illustrate the Latin square design, suppose that in the previous example, in addition to controlling for store patronage, the researcher also wanted to control for interest in the store (defined as high. medium, or low). To implement a Latin square design, store patronage would also have to be blocked at three rather

An Example of Latin Square Design

An Example of Latin Square Design

Although Latin square designs are popular in marketing research, they are not without limitations. They require an equal number of rows, columns. and treatment levels. which is sometimes problematic. Note that in the previous example. the low and nonpatrons had to be combined to satisfy this requirement. Also. only two external variables can be controlled simultaneously. An additional variable can be controlled with an expansion of this design into a Graeco-Latin square. Finally, Latin squares do not allow the researcher to examine interactions of the external variables with each other or with the independent variable. To examine interactions. factorial designs should be used

Factorial Design

A factorial design is used to measure the effects of two or more independent variables at various levels. Unlike the randomized block design and the Latin square, factorial designs allow for interactions between variables.” An interaction is said to take place when the simultaneous effect of two or more variables is different from the sum of their separate effects. For example, – an individual’s favorite drink might be coffee and favorite temperature level might be cold, but this individual might not prefer cold coffee, leading to an interaction.

The main disadvantage of a factorial design is that the number of treatment combinations increases multiplicative with an increase in the number of variables or levels. In our example of Table 7.6, if the amount of humor and store information had five levels each instead of three, the number of cells would have jumped from 9 to 25. All the treatment combinations are required if all the main effects and interactions are to be measured. If the researcher is interested in only a few of the interactions or main effects,fractional factorial designs may be used. As their name implies, these designs consist of only a fraction, or portion, of the corresponding full factorial design

An Example of a Factorial Design

An Example of a Factorial Design

Posted on November 30, 2015 in Causal Research Design Experimentation

Share the Story

Back to Top