Improving E-Mail Marketing Response essay

ImprovingE-Mail Marketing Response

ImprovingE-Mail Marketing Response

Fromthe DOE carried out using the linear model, R-square, is 0.74. Thisshows that 74 percent of variations in the response variables can beexplained by predictors within the model. The ideal value is 100percent, and this implies that the linear model fit is commendable.

Theone-way ANOVA analysis revealed that together, predictor variableswere effectual since the F-statistic was 7.833 and alpha value 0.003.This is as shown in the table below. The significance value wasconsiderably lower than 0.05, the hence hypothesis of predictorvariables being significant is rejected.

Coefficients

Usingthe coefficients in the table above and taking response rate asconstant, the model can be described using the model below

WhereY is the response rate, X1 = Heading, X2 =Email Open, X3 = Body whileX4 = Replicate (Blocking factor).

Fromthe coefficient table, the p values for replicate (blocking factor)and heading were are higher than 0.05 0.388 and 0.049 respectively.Therefore, it can be concluded that there is no statisticalsignificance between heading and email responses, and betweenreplicate values and email responses.

ModelEffects Tests

Thesignificance of the main effects and effects of interactions wastested using Wald Chi-square.

Fromthe results of the tests for model effects, it can be concluded thatthe pairwise interactions were statistically significant for headingand email open (p=0.00), heading and replicate (p=0.00), email openand body (p=0.00), and email open and replicate (p=0.03) since theirp values were higher than 0.05. The statistically insignificantpairwise interactions include heading and body (p=0.299) and body andreplicate (p=0.109) since their p-value is greater than 0.05.

MainEffects Plot

Theplot for the main effect reveals that the main effects for the termsof the model were significant. This plot is as shown below.

Plotfor the main effects

Plotfor Interaction effects matrix

Theplot for interaction plot for DOE to facilitate interaction for boththe 2-factor and main effects. This plot confirms the effectivenessof all the pairwise interactions with exceptions of those betweenbody and replicate, and heading and body.

PlotShowing Interaction Effects

Recommendation

Theanalysis results reveal high response rate for open emails.Therefore, the researcher recommends the application of open emailsin marketing. The company should formulate a strategy to createcustomized HTML email blasts since the results revealed that theytend to perform better than text emails. It is also recommended thatthe company establish a targeted audience list and reporting tools.

ProposedModel

Theresearcher proposes Strategic Alignment Model (SAM) by Venkatramanand Henderson (1991). According to this model, for the company to besuccessful, there is need to ensure that the Information Technologystrategy is ranged within the business strategy.If implemented,this model will be instrumental in perfecting the current marketingstrategy, as well as addressing all factors affecting the currentmarketing methods.

StrategicAlignment Model

Reference

Baumgartner,H., &amp Steenkamp, J. B. E. (2001). Response styles in marketingresearch: A cross-national investigation.&nbspJournalof marketing research,&nbsp38(2),143-156.