Interpreting regression results, matching time periods. Bender, Inc., produces industrial blenders for smoothie and health food shops. It has four peak periods, each lasting 2 months, for manufacturing the merchandise suited for spring, summer, fall, and winter. In the off-peak periods, Bender schedules equipment maintenance. Bender's controller, Gina Hood, wants to understand the drivers of equipment maintenance costs.
$$
\begin{aligned}
&\text { The data collected is as follows. }\\
&\begin{array}{l|c|r|}
\hline \text { Month } & \text { Machine-Hours } & \text { Maintenance Costs } \\
\hline \text { January } & 5,150 & \$ 1,250 \\
\text { February } & 4,600 & 2,150 \\
\text { March } & 1,120 & 13,100 \\
\text { April } & 5,360 & 1,650 \\
\text { May } & 5,650 & 2,680 \\
\text { June } & 1,750 & 15,100 \\
\text { July } & 7,250 & 1,900 \\
\text { August } & 6,050 & 2,690 \\
\text { September } & 1,950 & 15,400 \\
\text { October } & 6,200 & 1,750 \\
\text { November } & 5,800 & 2,850 \\
\text { December } & 1,450 & 14,900 \\
\hline
\end{array}
\end{aligned}
$$
A regression analysis of 1 year of monthly data yields the following relationships:
$$
\text { Maintenance costs }=\$ 17,983-(\$ 2,683 \times \text { Number of machine-hours })
$$
Upon examining the results, Hood comments, "So, all I have to do to reduce maintenance costs is run my machines longer? This is hard to believe, but numbers don't lie! I would have guessed just the opposite."