Question

Ice cream consumption was measured over 30 four-week periods from March 18, 1951 to July 11, 1953. The purpose of the study was to determine if ice cream consumption depends on the variables price, income, or temperature. For this HW question, we want to see if the temperature (temp) affects the ice cream consumption (IC). Attached is the output from the simple linear regression of temperature on ice cream consumption. What percentage of change in ice cream consumption can be explained by temperature

Answer 1

Log Linear Model : log y = a + bx. Slope 'b' represent % change in ice cream sale, due to unit change in temperature.

Explanation:

Assuming a log linear regression model, with dependent variable 'y' ie Ice cream sale & independent variable 'x' ie temperature sale.

In form of regression, log y = a + bx {a = intercept}. Here, slope b represents response of one unit change (Increase) in temperature leading to b% change (ie rise) in ice cream consumption. Slope coefficient 'b' is likely to be positive, as temperature & ice cream sale are likely to be directly related, higher temperature (hot weather) imply high ice cream sale, & vice versa less sales for lower temperature (cool weather)