M10 – Simple Linear Regression: CFAI Practice Problems

Source: CFAI CFA1 Quant Practice 2026, pp.310–325 Back to module: M10 Glossary: M10 Terms


Questions 1–3: ROE and Growth Opportunities

The following estimated regression equation relates return on equity (ROE, in %) to growth opportunities (GO, in %):


Question 1

Using this regression, the predicted ROE when is closest to:

  • A. 1.8%
  • B. 15.8%
  • C. 22.0%

Question 2

The estimated change in ROE when GO changes from 5% to 6% is closest to:

  • A. 1.8%
  • B. 4.0%
  • C. 5.8%

Question 3

When and the observed ROE = 21%, the residual is closest to:

  • A. −1.8%
  • B. 2.6%
  • C. 12.0%

Question 4

Homoskedasticity is best described as a condition in which the variance of the residuals is:

  • A. zero
  • B. normally distributed
  • C. constant across all observations

Questions 5–8: Money Supply Growth and Policy Shift

An analyst regresses money supply growth (%) on an indicator variable SHIFT (= 0 before policy change, = 1 after policy change) using 30 observations.

CoefficientStd. Error-statistic
[[quantitative-methods/glossary/m10-simple-linear-regression#interceptIntercept]]5.7672640.445229
SHIFT−5.1391200.629649−8.16

Critical values: one-tailed ; two-tailed (at 5% significance).


Question 5

The variable SHIFT is best described as:


Question 6

The intercept of 5.767264 represents the mean money supply growth rate:

  • A. before the policy shift
  • B. over the entire sample period
  • C. after the policy shift

Question 7

The slope coefficient of −5.139120 is best interpreted as:

  • A. the change in money supply growth per year
  • B. the average money supply growth rate after the shift
  • C. the difference in average money supply growth before versus after the policy change

Question 8

To test whether money supply growth changed after the policy shift at the 0.05 significance level, the analyst should conclude:

  • A. there is sufficient evidence that growth changed after the shift
  • B. there is not enough evidence that the slope is different from zero
  • C. there is not enough evidence to indicate a change in growth after the shift

Questions 9–12: McCoin Regression (CFO/Sales on Net Income/Sales)

Regression of CFO/sales () on net income/sales () using observations:

CoefficientStd. Error-statistic-value
Intercept0.0770.00711.330.000
Net income/sales0.8260.1037.990.000

[[quantitative-methods/glossary/m10-simple-linear-regression#r|]] = 0.7436, SEE = 0.0213,


Question 9

The coefficient of determination for this regression is:

  • A. 0.7436
  • B. 0.8261
  • C. 0.8623

Question 10

The correlation between net income/sales and CFO/sales is closest to:

  • A. −0.7436
  • B. 0.7436
  • C. 0.8623

Question 11

If a company’s net income/sales = 5%, the predicted CFO/sales is closest to:

  • A. −4.054%
  • B. 0.524%
  • C. 4.207%

Question 12

Is the relationship between net income/sales and CFO/sales significant at the 0.05 level?

  • A. No, because [[quantitative-methods/glossary/m10-simple-linear-regression#r|]] > 0.05
  • B. No, because the p-values of the intercept and slope are less than 0.05
  • C. Yes, because the p-values for the F-statistic and the slope coefficient are less than 0.05

Questions 13–17: Stellar Energy vs. CPIENG

Regression of Stellar Energy monthly returns () on CPIENG energy index returns () using monthly observations:

CoefficientStd. Error-statistic
[[quantitative-methods/glossary/m10-simple-linear-regression#interceptIntercept]]0.01380.0046
CPIENG−0.64860.2818−2.3014

[[quantitative-methods/glossary/m10-simple-linear-regression#r|]] = 0.0211, [[quantitative-methods/glossary/m10-simple-linear-regression#see|]] = 0.0710 Critical values: one-tailed ; two-tailed (5% significance)


Question 13

This regression is best described as:

  • A. a time-series regression
  • B. a cross-sectional regression
  • C. both a time-series and cross-sectional regression

Question 14

If the CPIENG energy index decreases by 1%, the expected return of Stellar Energy is closest to:

  • A. 0.73%
  • B. 1.38%
  • C. 2.03%

Question 15

The [[quantitative-methods/glossary/m10-simple-linear-regression#r|]] = 0.0211 indicates that:

  • A. Stellar Energy returns explain 2.11% of the variation in CPIENG returns
  • B. Stellar Energy returns explain 14.52% of the variation in CPIENG returns
  • C. CPIENG returns explain 2.11% of the variation in Stellar Energy returns

Question 16

The value 0.0710 (SEE) is the standard deviation of the:


Question 17

Which of the following conclusions is incorrect?

  • A. The intercept is significantly different from zero
  • B. After a decline in CPIENG, a positive Stellar return is expected
  • C. Both the slope and intercept are not significantly different from zero

Questions 18–26: Anh Liu – Short Interest Ratio vs. Debt Ratio

Anh Liu regresses the short interest ratio () on the debt ratio () for companies.

ANOVA Table:

SourceSSdfMS
Regression (SSR)38.4404138.4404
Error (SSE)373.7638487.7867
Total (SST)412.204249

[[quantitative-methods/glossary/m10-simple-linear-regression#r|]] = 0.0933, [[quantitative-methods/glossary/m10-simple-linear-regression#see|]] = 2.7905

CoefficientStd. Error-statistic
Intercept5.49750.84166.5322
Debt ratio−4.15891.8718−2.2219

Critical values: one-tailed ; two-tailed (5% significance)


Question 18

Based on the regression results, the scatter plot of short interest ratio vs. debt ratio most likely has:

  • A. a horizontal pattern
  • B. an upward-sloping pattern
  • C. a downward-sloping pattern

Question 19

The sample covariance between debt ratio and short interest ratio is closest to:

  • A. −9.2430
  • B. −0.1886
  • C. 8.4123

Question 20

The correlation between debt ratio and short interest ratio is closest to:

  • A. −0.3054
  • B. 0.0933
  • C. 0.3054

Question 21

Which interpretation best describes the findings of Anh Liu’s regression?

  • A. Interpretation 1: Higher debt ratios cause lower short interest ratios
  • B. Interpretation 2: Higher short interest ratios cause companies to take on more debt
  • C. Interpretation 3: Companies with higher debt ratios tend to have lower short interest ratios

Question 22

The dependent variable in Anh Liu’s regression is:

  • A. the intercept
  • B. the debt ratio
  • C. the short interest ratio

Question 23

The degrees of freedom for the -test of the slope coefficient are:

  • A. 48
  • B. 49
  • C. 50

Question 24

Which conclusion is most supported by Anh Liu’s results?

  • A. The average short interest ratio in the sample is 5.4975
  • B. The slope coefficient is different from zero at the 0.05 significance level
  • C. The debt ratio explains 30.54% of the variation in the short interest ratio

Question 25

MQD Corp has a debt ratio of 0.40. The predicted short interest ratio is closest to:

  • A. 3.8339
  • B. 5.4975
  • C. 6.2462

Question 26

The F-statistic for testing the overall significance of the regression is closest to:

  • A. −2.2219
  • B. 3.5036
  • C. 4.9367

Questions 27–29: US CPI Regression (Forecasting Bias)

Olabudo regresses actual CPI () on forecast CPI () using observations. An unbiased forecast model should have intercept = 0 and slope = 1.

CoefficientStd. Error-statistic
[[quantitative-methods/glossary/m10-simple-linear-regression#interceptIntercept]]0.00010.0002
Slope0.98300.015563.4194

[[quantitative-methods/glossary/m10-simple-linear-regression#r|]] = 0.9859, [[quantitative-methods/glossary/m10-simple-linear-regression#see|]] = 0.0009, -critical (two-tailed, 5%) , CPI forecast for next period:


Question 27

Based on the regression results, Olabudo should:

  • A. conclude that the CPI forecasts are unbiased
  • B. reject that the slope coefficient equals 1
  • C. reject that the intercept is equal to 0

Question 28

The 99% prediction interval for the actual CPI when the forecast is 2.8 is closest to:

  • A. 2.7506 to 2.7544
  • B. 2.7521 to 2.7529
  • C. 2.7981 to 2.8019

Question 29

Which observation about forecasting from this regression is correct?

  • A. Only Observation 1
  • B. Only Observation 2
  • C. Both observations

Observation 1: The width of a prediction interval is the same regardless of how far the forecast value is from the sample mean. Observation 2: A larger SEE leads to a wider confidence interval for the predicted value.


Questions 30–34: Amtex and Crude Oil Returns

Regression of Amtex monthly returns () on crude oil monthly returns () using observations.

CoefficientStd. Error
Intercept0.00950.0078
Oil return0.23540.0760

Critical values at 1%: one-tailed ; two-tailed Expected oil return for month 37: ;


Question 30

Which of the following regression assumptions is incorrectly stated?


Question 31

The standard error of estimate (SEE) is closest to:

  • A. 0.04456
  • B. 0.04585
  • C. 0.05018

Question 32

Vasileva should reject the null hypothesis that:

  • A. the slope coefficient is less than or equal to 0.15
  • B. the intercept is less than or equal to 0
  • C. crude oil returns do not explain Amtex returns

Question 33

The predicted Amtex return for month 37, when the expected crude oil return is −1%, is closest to:

  • A. −0.0024
  • B. 0.0071
  • C. 0.0119

Question 34

The 99% prediction interval for the Amtex return in month 37 is closest to:

  • A.
  • B.
  • C.

Questions 35–38: NPM vs. Fixed Asset Turnover (Log-Lin Model)

Tremblay estimates the log-linear regression:

ANOVA Table:

SourceSSdf-value
Regression102.915211486.70790.0000
Error2.215232
Total105.130333
CoefficientStd. Error-statistic-value
Intercept0.59870.056110.67490.0000
FATO0.29510.007738.55790.0000

Question 35

The coefficient of determination () is closest to:

  • A. 0.0211
  • B. 0.9789
  • C. 0.9894

Question 36

The standard error of estimate (SEE) is closest to:

  • A. 0.2631
  • B. 1.7849
  • C. 38.5579

Question 37

At the 0.01 significance level, Jones should conclude that:

  • A. the mean NPM is 0.5987%
  • B. variation in FATO explains variation in
  • C. a change in FATO from 3 to 4 leads to a change in NPM of 0.5987%

Question 38

The predicted NPM for a company with is closest to:

  • A. 1.1889%
  • B. 1.8043%
  • C. 3.2835%