(a) Plot the voter participation rate.

(b) Describe the trend (if any) and discuss possible causes.

(c) Fit both a linear and a quadratic trend to the data.

(d) Which model is preferred? Why?

(e) Make a forecast for 2012, using a trend model of your choice (or a judgment forecast).

(f) If possible, check the web for the actual 2012 voter participation rate. How close was your forecast?

Note: Time is in 4-year increments, so use $t$ = 16 for the 2012 forecast.

U.S. Presidential Election Voter Participation, 1952–2008
Year	Voting Age Population	Voted for President	% Voting Pres
1952	99,929	61,551	61.6
1956	104,515	62,027	59.3
1960	109,672	68,838	62.8
1964	114,090	70,645	61.9
1968	120,285	73,212	60.9
1972	140,777	77,719	55.2
1976	152,308	81,556	53.5
1980	163,945	86,515	52.8
1984	173,995	92,653	53.3
1988	181,956	91,595	50.3
1992	189,524	104,425	55.1
1996	196,928	96,278	49.0
2000	207,884	105,397	50.7
2004	220,377	122,349	55.5
2008	229,945	131,407	57.1

(a) Plot both Swiss watch time series on the same graph.

(b) Describe the trend (if any) and discuss possible causes.

(c) Fit an exponential trend to each time series.

(d) Interpret each fitted trend carefully. What conclusion do you draw?

(e) Make forecasts for the next 3 years, using the linear trend model. Why might 2009 have been unusual? Explain.

(a) Plot both Swiss watch time series on the same graph. (b) Describe the trend (if any) and discuss possible causes. (c) Fit an exponential trend to each time series. (d) Interpret each fitted trend carefully. What conclusion do you draw? (e) Make forecasts for 2003, using the linear trend model. Do you feel confident in your forecasts? Explain.

$$\begin{aligned} &\text { Swiss Watch Exports (thousands of units), 1998-2003 }\\ &\begin{array}{ccc} \hline \text { Year } & \text { Mechanical } & \text { Electronic } \\ \hline 1998 & 2,558 & 29,678 \\ 1999 & 2,526 & 28,766 \\ 2000 & 2,549 & 27,313 \\ 2001 & 2,580 & 23,811 \\ 2002 & 2,722 & 24,107 \\ 2003 & 2,718 & 21,864 \\ \hline \end{array} \end{aligned}$$

Two contingency tables below show return on investment (ROI) and percent of sales growth over the previous 5 years for 85 U.S. firms. ROI is defined as percentage of return on a combination of stockholders’ equity (both common and preferred) plus capital from long-term debt including current maturities, minority stockholders’ equity in consolidated subsidiaries, and accumulated deferred taxes and investment tax credits.

Research question: At $\alpha = .05$, is ROI independent of sales growth? Would you expect it to be? Do the two tables (2 x 2 and 3 x 3) agree? Are small expected frequencies a problem?

(a) Plot the data on revolving credit (credit cards and home equity lines of credit are the two major types of revolving credit).

(b) Use MegaStat or MINITAB to calculate estimated seasonal indexes and trend. Is there a trend in the deseasonalized data? (c) Which months have the most borrowing? The least? Is this logical?

$$\begin{aligned} &\text { U.S. Consumers Revolving Credit (billions) }\\ &\begin{array}{lllll} \hline \text { Month } & \mathbf{2 0 0 1} & \mathbf{2 0 0 2} & \mathbf{2 0 0 3} & \mathbf{2 0 0 4} \\ \hline \text { Jan } & 223.2 & 232.5 & 240.6 & 276.7 \\ \text { Feb } & 221.5 & 229.7 & 239.7 & 272.8 \\ \text { Mar } & 220.1 & 230.2 & 234.0 & 268.3 \\ \text { Apr } & 227.7 & 235.6 & 235.4 & 270.6 \\ \text { May } & 229.1 & 233.1 & 240.4 & 278.0 \\ \text { Jun } & 225.7 & 231.0 & 240.7 & 275.6 \\ \text { Jul } & 222.1 & 229.9 & 238.6 & 278.7 \\ \text { Aug } & 219.6 & 241.1 & 240.7 & 286.4 \\ \text { Sep } & 216.3 & 243.1 & 239.9 & 286.7 \\ \text { Oct } & 223.3 & 242.4 & 235.8 & 286.1 \\ \text { Nov } & 233.2 & 244.2 & 269.5 & 285.8 \\ \text { Dec } & 238.3 & 250.2 & 284.7 & 315.8 \\ \hline \end{array} \end{aligned}$$

Why do you think the students participated in the new system? Did pressure from the rest of the class have any influence on participation? Explain.

The actual distribution of car colors for 2006 model car buyers is shown below. Based on the sample of 200 car buyers for 2012 model vehicles, use the multinomial chi-square GOF test at $\alpha = .05$ to test whether car buyers’ color preferences have changed.

Oxnard Kortholt, Ltd., employs 50 workers.

Research question: At $\alpha = .05$, do Oxnard employees differ significantly from the national percent distribution?

A student rolled a supposedly fair die 60 times, resulting in the distribution of dots shown.

Research question: At $\alpha = .10$, can you reject the hypothesis that the die is fair?

Name an advantage and a disadvantage of each method.

Explain two ways to initialize the forecasts in an exponential smoothing process.

(a) Plot the total minutes of TV viewing time per household. (b) Describe the trend (if any) and discuss possible causes. (c) Fit a linear trend to the data. (d) Would this model give reasonable forecasts? Would another trend model be better? Explain. (e) Make a forecast for 2015. Show the forecast calculations. (f) Would these data ever approach an asymptote? Explain. Note: Time is in 5-year increments, so use t =14 for the 2015 forecast.

A student rolled a supposedly fair die 60 times, resulting in the distribution of dots shown. Research question: At $\alpha = .10$, can you reject the hypothesis that the die is fair?

$$\begin{aligned} &\text { Number of Dots }\\ &\begin{array}{lccccccc} & \mathbf{1} & \mathbf{2} & \mathbf{3} & \mathbf{4} & \mathbf{5} & \mathbf{6} & \text { Total } \\ \hline \text { Frequency } & 7 & 14 & 9 & 13 & 7 & 10 & 60 \\ \hline \end{array} \end{aligned}$$

The table below shows the number of ATM customer arrivals per minute in 60 randomly chosen minutes. Research question: At $\alpha = .025$, can you reject the hypothesis that the number of arrivals per minute follows a Poisson process?