27.10.2012 Views

Analysis of Sales Promotion Effects on Household Purchase Behavior

Analysis of Sales Promotion Effects on Household Purchase Behavior

Analysis of Sales Promotion Effects on Household Purchase Behavior

SHOW MORE
SHOW LESS

Create successful ePaper yourself

Turn your PDF publications into a flip-book with our unique Google optimized e-Paper software.

esulting residuals were incorporated in the binary logistic regressi<strong>on</strong> model for promoti<strong>on</strong><br />

resp<strong>on</strong>se (omitting the highest level <str<strong>on</strong>g>of</str<strong>on</strong>g> educati<strong>on</strong>). The findings regarding the relati<strong>on</strong>ship<br />

between educati<strong>on</strong> and promoti<strong>on</strong> resp<strong>on</strong>se can be found in Table 7.9. The variables<br />

represent the effect <str<strong>on</strong>g>of</str<strong>on</strong>g> educati<strong>on</strong> as far as it is not incorporated in social class. The<br />

estimated parameters are relative to the highest level <str<strong>on</strong>g>of</str<strong>on</strong>g> educati<strong>on</strong>.<br />

Table 7.9: Relati<strong>on</strong>ship promoti<strong>on</strong> resp<strong>on</strong>se and educati<strong>on</strong><br />

EDUCATION (number <str<strong>on</strong>g>of</str<strong>on</strong>g> years <str<strong>on</strong>g>of</str<strong>on</strong>g> schooling)<br />

H6: Educati<strong>on</strong> and promoti<strong>on</strong> resp<strong>on</strong>se are positively related.<br />

B S.E. Sign. Exp(B)<br />

- standard (6 years) 0.0013 0.2138 0.9950 1.0013<br />

- lower (10 years) -0.2480 0.1044 0.0174 0.7801<br />

- middle (12 years) 0.1324 0.0858 0.1226 1.1416<br />

Test results: Educati<strong>on</strong> (after having corrected for social class) and promoti<strong>on</strong> resp<strong>on</strong>se are<br />

not positively related.<br />

The influence <str<strong>on</strong>g>of</str<strong>on</strong>g> educati<strong>on</strong> after correcting for the influence <str<strong>on</strong>g>of</str<strong>on</strong>g> social class <strong>on</strong> promoti<strong>on</strong><br />

resp<strong>on</strong>se, is not significantly positive. The general assumpti<strong>on</strong> is that with experience<br />

(reflected in for example age and educati<strong>on</strong>), c<strong>on</strong>sumers are more efficient and have greater<br />

capability to engage in search. Although we did find a positive relati<strong>on</strong>ship between age<br />

and promoti<strong>on</strong> resp<strong>on</strong>se, the positive relati<strong>on</strong>ship between educati<strong>on</strong> (otherwise then<br />

measured by social class) and promoti<strong>on</strong> resp<strong>on</strong>se is not empirically supported.<br />

<str<strong>on</strong>g>Promoti<strong>on</strong></str<strong>on</strong>g> type could be interacting with the relati<strong>on</strong>ship between educati<strong>on</strong> and<br />

promoti<strong>on</strong> resp<strong>on</strong>se. Out-<str<strong>on</strong>g>of</str<strong>on</strong>g>-store promoti<strong>on</strong>s need more search behavior, which could be<br />

carried out more efficiently by more highly educated households. The results are presented<br />

in the Table 7.10. Based <strong>on</strong> the results, <strong>on</strong>e could c<strong>on</strong>clude that the effect <str<strong>on</strong>g>of</str<strong>on</strong>g> educati<strong>on</strong> after<br />

correcting for social class seems to be positive. But, the coefficients are not significant.<br />

136

Hooray! Your file is uploaded and ready to be published.

Saved successfully!

Ooh no, something went wrong!