Question 1

If prediction is made from the Pearsonian regression line and linearity of regression does not hold, the predicted value of Y will be

Accepted Answer

A)  an overestimate of Y 
B)  an underestimate of Y 
C)  sometimes an overestimate and sometimes an underestimate of Y 
D)  satisfactory only if the Y distribution is homoscedastic 
A)  an overestimate of Y 
B)  an underestimate of Y 
C)  sometimes an overestimate and sometimes an underestimate of Y 
D)  satisfactory only if the Y distribution is homoscedastic

Question 2

When obtained values of Y are not normally distributed

Accepted Answer

A)    is likely to be underestimated 
B)    is likely to be overestimated 
C)  the limits of predictive error are likely to be underestimated or overestimated 
D)  the standard error of estimate is likely to be too large or too small 
A)    is likely to be underestimated 
B)    is likely to be overestimated 
C)  the limits of predictive error are likely to be underestimated or overestimated 
D)  the standard error of estimate is likely to be too large or too small

Question 3

When   
 what z score in X leads us to a predicted Y score of

Accepted Answer

A)  +.50 
B)  0 
C)  -.50 
D)  none of the above 
A)  +.50 
B)  0 
C)  -.50 
D)  none of the above

Question 4

when

Accepted Answer

A)    
B)    
C)    
D)    
A)    
B)    
C)    
D)

Question 5

The regression line for predicting Y from X is drawn so that which of the following is minimized?

Accepted Answer

A)    
B)    
C)    
D)    
A)    
B)    
C)    
D)

Question 6

The least squares line of regression for predicting Y from X minimizes

Accepted Answer

A)  SY 
B)  SY and SX 
C)  SYX 
D)  SY' 
A)  SY 
B)  SY and SX 
C)  SYX 
D)  SY'

Question 7

The following data are for freshman students at Spartan University:   
 (a) Write the raw score regression equation for predicting Y from X and simplify it.   
(b) John and Will score 485 and 710, respectively, on the aptitude test. Predict the freshman GPA for each. 
(c) Compute the standard error of prediction. 
(d) Set up the 95% confidence limits around John's and Will's predicted GPAs. 
(e) For students with aptitude scores the same as John's, what proportion would be expected to obtain a GPA better than the freshman mean? What proportion would be expected to obtain a GPA of 2.0 or below? 
(f) For students with aptitude scores the same as Will's, what proportion would be expected to obtain a GPA of 2.5 or better?

Accepted Answer

(a) @#IMG-DLM& 
(b)John: 2.46, Will: 2.9

Question 8

Depending on the value of   may take values between

Accepted Answer

A)  0 and 1.00 
B)  0 and SY 
C)  0 and SX 
D)  SX and SY 
A)  0 and 1.00 
B)  0 and SY 
C)  0 and SX 
D)  SX and SY

Question 9

when

Accepted Answer

A)    
B)    
C)    
D)    
A)    
B)    
C)    
D)

Question 10

Estimates of predictive error utilizing the regression equation and the standard error of estimate are affected by random sampling variation. When this factor is taken into account, it is found that error estimates made by the methods of this chapter are generally

Accepted Answer

A)  correct only on the average 
B)  larger than they should be 
C)  smaller than they should be 
D)  correct only for small samples 
A)  correct only on the average 
B)  larger than they should be 
C)  smaller than they should be 
D)  correct only for small samples

Question 11

Which term, if any, does not appear in the raw score regression equation?

Accepted Answer

A)    
B)    
C)    
D)  all appear in the raw score equation 
A)    
B)    
C)    
D)  all appear in the raw score equation

Question 12

In predicting Y from a particular value of X, we report 68% of obtained values of Y to fall within

Accepted Answer

A)    
B)    
C)    
D)    
A)    
B)    
C)    
D)

Question 13

and   
;   
 and   
 If   
 and X is 40, what value do we predict for Y?

Accepted Answer

A)  120 
B)  100 
C)  90 
D)  80 
A)  120 
B)  100 
C)  90 
D)  80

Question 14

Accepted Answer

A)    
B)    
C)    
D)    
A)    
B)    
C)    
D)

Question 15

The manager of an ice cream company wants a better basis for deciding how much ice cream to make each evening. He would like to be able to predict the amount of ice cream sold at his retail outlets on any day from the temperature forecast the evening before. He records both the evening temperature forecast (X) and the number of five-gallon containers of ice cream sold the next day (Y) over a considerable period in the late spring and early summer. The following results are obtained:
   
(a) Write the regression equation for predicting Y from X; simplify; and compute the standard error of prediction.
(b)Suppose the temperature forecast is for 96°. On what proportion of following days would he expect to sell over 1300 containers of ice cream?
(c)Suppose the forecast is for 50° and he plans to make 800 containers. For what proportion of the following days would this be too much ice cream?
(d)The regression equation is based on data gathered in the late spring and early summer. Will it "work" in midsummer, or in early fall?

Accepted Answer

(a)
@#IMG-DLM& 
(b) @#IMG-DLM&

(c) 
@#IMG-DLM&

(d)the correlation

Question 16

Consider the situation described from above. (a) Convert to z scores the heights of the following 10-year-olds: Benny (42.5 in.), Cal (55.3 in.), Arthur (50.1 in.), (b) Use the standard score form of the regression equation to obtain their predicted z scores for height as adults. (c) Convert the predicted z scores from (b) to predicted heights in inches and compare with the results Benny: 61.8, Cal: 73.9, Arthur: 69.0.

Accepted Answer

(a) Benny: -1.87, Cal: +2.26,

Question 17

If

Accepted Answer

A)  X is of no use in predicting Y 
B)  values of Y can be predicted from values of X without error 
C)  either the X scores or the Y scores must be negative 
D)  the relationship becomes difficult to interpret 
A)  X is of no use in predicting Y 
B)  values of Y can be predicted from values of X without error 
C)  either the X scores or the Y scores must be negative 
D)  the relationship becomes difficult to interpret

Question 18

When   
 =

Accepted Answer

A)    
B)    
C)  either (a) or (b) is true 
D)  r = 0 
A)    
B)    
C)  either (a) or (b) is true 
D)  r = 0

Question 19

For what value of r does a particular z score in X lead us to predict the same z score in Y?

Accepted Answer

A)  0 
B)  -1.00 
C)  +1.00 
D)  both (b) and (c) 
A)  0 
B)  -1.00 
C)  +1.00 
D)  both (b) and (c)

Question 20

In a problem where we are predicting Y from X, which of the following can be considered a mean?

Accepted Answer

A)  predicted value 
B)  zX 
C)  error of estimate 
D)  zY 
A)  predicted value 
B)  zX 
C)  error of estimate 
D)  zY

If prediction is made from the Pearsonian regression line and linearity of regression does not hold, the predicted value of Y will be

When obtained values of Y are not normally distributed

When what z score in X leads us to a predicted Y score of

when

The regression line for predicting Y from X is drawn so that which of the following is minimized?

The least squares line of regression for predicting Y from X minimizes

Depending on the value of may take values between

when

Estimates of predictive error utilizing the regression equation and the standard error of estimate are affected by random sampling variation. When this factor is taken into account, it is found that error estimates made by the methods of this chapter are generally

Which term, if any, does not appear in the raw score regression equation?

In predicting Y from a particular value of X, we report 68% of obtained values of Y to fall within

and ; and If and X is 40, what value do we predict for Y?

If

When =

For what value of r does a particular z score in X lead us to predict the same z score in Y?

In a problem where we are predicting Y from X, which of the following can be considered a mean?

Introduction

Frequency Distributions, Percentiles,

Graphic Representation of Frequency Distributions

Central Tendency

Variability and Standard Z Scores

Standard Scores and the Normal Curve

Correlation

Interpretive Aspects of Correlation and Regression

Probability

Random Sampling and Sampling Distributions

Introduction to Statistical Inference: Testing Hypotheses About Single Means Z and T

Interpreting the Results of Hypothesis Testing: Effect Size, Type I and Type II Errors, and Power

Testing Hypotheses About the Difference Between Two Independent Groups

Testing for a Difference

Inference About Correlation Coefficients

An Alternative to Hypothesis Testing: Confidence Intervals

Testing for Differences Among Three or More Groups: One-Way Analysis of Variance and Some Alternatives

Factorial Analysis of Variance

Chi-Square and Inference About Frequencies

Some Almost Assumption-Free Tests

Filters

Exam 8: Prediction

If prediction is made from the Pearsonian regression line and linearity of regression does not hold, the predicted value of Y will be

When obtained values of Y are not normally distributed

When what z score in X leads us to a predicted Y score of

when

The regression line for predicting Y from X is drawn so that which of the following is minimized?

The least squares line of regression for predicting Y from X minimizes

Depending on the value of may take values between

when

Estimates of predictive error utilizing the regression equation and the standard error of estimate are affected by random sampling variation. When this factor is taken into account, it is found that error estimates made by the methods of this chapter are generally

Which term, if any, does not appear in the raw score regression equation?

In predicting Y from a particular value of X, we report 68% of obtained values of Y to fall within

and ; and If and X is 40, what value do we predict for Y?

If

When =

For what value of r does a particular z score in X lead us to predict the same z score in Y?

In a problem where we are predicting Y from X, which of the following can be considered a mean?

Introduction

Frequency Distributions, Percentiles,

Graphic Representation of Frequency Distributions

Central Tendency

Variability and Standard Z Scores

Standard Scores and the Normal Curve

Correlation

Interpretive Aspects of Correlation and Regression

Probability

Random Sampling and Sampling Distributions

Introduction to Statistical Inference: Testing Hypotheses About Single Means Z and T

Interpreting the Results of Hypothesis Testing: Effect Size, Type I and Type II Errors, and Power

Testing Hypotheses About the Difference Between Two Independent Groups

Testing for a Difference

Inference About Correlation Coefficients

An Alternative to Hypothesis Testing: Confidence Intervals

Testing for Differences Among Three or More Groups: One-Way Analysis of Variance and Some Alternatives

Factorial Analysis of Variance

Chi-Square and Inference About Frequencies

Some Almost Assumption-Free Tests

Filters