Big Andy’s Burger Barn

Hansl is used to estimate the model for Big Andy’s. The following two lines are typed into a script file, which is executed by clicking your mouse on the “gear” button of the script window.

1 open "@gretldirdatapoeandy. gdt"

2 ols sales const price advert

3 scalar S_hat = $coeff(const) + $coeff(price)*5.5 + $coeff(advert)*1.2

This assumes that the gretl data set andy. gdt is installed at c:ProgramFiles(x86)gretldata poe. The results, in tabular form, are in Table 5.1 and match those in POE4.

In addition to providing information about how average sales change when price or advertising changes, the estimated equation can be used for prediction. To predict sales revenue for a price of $5.50 and an advertising expenditure of $1,200 we can use genr or scalar to do the computations. From the console,

Generated scalar S_hat (ID 4) = 77.6555

which also matches the result in POE4.

Model 1: OLS, using observations 1-75
Dependent variable: sales

Coefficient

Std. Error

t-ratio

p-value

const

118.914

6.35164

18.7217

0.0000

price

-7.90785

1.09599

-7.2152

0.0000

advert

1.86258

0.683195

2.7263

0.0080

Mean dependent var 77.37467 S. D. dependent var 6.488537

Sum squared resid 1718.943 S. E. of regression 4.886124

R2 0.448258 Adjusted R2 0.432932

F(2,72) 29.24786 P-value(F) 5.04e-10

Log-likelihood -223.8695 Akaike criterion 453.7390

Schwarz criterion 460.6915 Hannan-Quinn 456.5151

Table 5.1: The regression results from Big Andy’s Burger Barn

Leave a reply

You may use these HTML tags and attributes: <a href="" title=""> <abbr title=""> <acronym title=""> <b> <blockquote cite=""> <cite> <code> <del datetime=""> <em> <i> <q cite=""> <s> <strike> <strong>