The effect of marketing expenditures on ABC Company's performance could be endogenous due to

Dependent Variable (Y) - Income

Endogenous Variable (X1) - Marketing Expenditures
Instrumental Variable (Z) - Advertising spend
Exogenous Variable (W) - Firm Size

DATA SET
Income (Y) Marketing Expediture (X1)
1 50000 7000
2 55000 7500
3 52000 7200
4 60000 8000
5 63000 8200
6 66000 8500
7 64000 8300
8 68000 8700
9 70000 8800
10 73000 9000

FIRST STAGE
SUMMARY OUTPUT

Regression Statistics
Multiple R 0.995993659036028
R Square 0.992003368839976
Adjusted R Square 0.989718617079969
Standard Error 69.727697117392
Observations 10

ANOVA (Degrees of Freedom)

df
Regression (# of predictors) 2
Residual (total # - # of predictors - 1) 7
Total (total observation - 1) 9

Coefficients
Intercept 2452.52466627975
Advertising Spend (Z) 0.0235055136389997
Firm Size (W) 45.0957632037145

Predicted Value 4486.15307771441

SECOND STAGE
Income (Y)
1 50000
2 55000
 3 52000
4 60000
5 63000
6 66000
7 64000
8 68000
9 70000
10 73000

SUMMARY OUTPUT

Regression Statistics
Multiple R 0.999448478906366
R Square 0.998897261988249
Adjusted R Square 0.998582193984892
Standard Error 291.367591719905
Observations 10

ANOVA
df
Regression 2
Residual 7
Total 9

Coefficients
Intercept -11079.7329143755
Marketing Expediture (X1) 3.77847604084839
Firm Size (W) 343.283582089552
uld be endogenous due to its correlation with other unobserved variables, such as market conditions.

Advertising Spend (Z) Firm Size (W)

3000 100
3200 110
3100 105
3500 120
3600 125
3800 130
3700 128
3900 135
4000 140
4200 145

very strong linear relationship between the observed and predicted values of dependent variables
approximately 99.2% variability in income can be explained by the model (Advertising and Firm)
very high
measures the ave distance that the observed fall from the regression line
number of data points

SS MS F Significance F<0.05 indicates that the

4221966.33778294 2110983.16889147 434.184311050478 4.573E-08 regression model is sta
34033.6622170633 4861.95174529475
4256000

Standard Error t Stat P-value Lower 95%Upper 95%

319.993537693539 7.66429436030847 0.00011972321638763 1695.8602 3209.1891
0.84401539998674 0.0278496264871103 0.978559431222303 -1.972274 2.0192848
22.5371469219838 2.00095262101371 0.0854991237674896 -8.196121 98.387647

Marketing Expediture (X1) Firm Size (W)

7000 100
7500 110
 7200 105
8000 120
8200 125
8500 130
8300 128
8700 135
8800 140
9000 145

SS MS F Significance F
538305734.485467 269152867.242734 3170.41797752809 4.453E-11
594265.514532601 84895.0735046573
538900000

Standard Error t Stat P-value Lower 95%Upper 95%

3967.60113411784 -2.79255210890521 0.0268097565298887 -20461.62 -1697.847
1.57929348435321 2.39251037143096 0.0479914200267822 0.0440404 7.5129117
72.498825718256 4.73502265296843 0.00212011764369252 171.8511 514.71606
 <0.05 indicates that the overall
regression model is statitically
significant

Upper 95%
Upper 95%
FIRST STAGE
Models' Explanatory

The model explains a very high proportion of the variance in Income, as indicated by the R Square
means that 99.2% of the variability in Income is explained by the Advertising Spend and Firm Size
The adjusted R Square (0.990) supports this high explanatory power even after adjusting for the n
Overall Significance of the Model

Advertising Spend (Z): The coefficient for Advertising Spend is 0.0235, but its p-value is 0.978, whi
the conventional significance level of 0.05. This suggests that Advertising Spend is not a significant
this model. The confidence interval also spans zero (-1.972 to 2.019), further indicating non
Significance of Individual Predictors

Advertising Spend (Z): The coefficient for Advertising Spend is 0.0235, but its p-value is 0.978, whi
the conventional significance level of 0.05. This suggests that Advertising Spend is not a significant
this model. The confidence interval also spans zero (-1.972 to 2.019), further indicating non

Firm Size (W): The coefficient for Firm Size is 45.10, with a p-value of 0.085. This p-value is slig
threshold but indicates marginal significance at the 10% level. This suggests that Firm Size has a n
strongly significant, positive effect on Income. For each additional unit increase in Firm Size, In
approximately 45.10 units, holding Advertising Spend constant.
Practical Implications
The high explanatory power of the model suggests that the included variables (Advertising Spend
relevant for explaining Income. However, the non-significance of Advertising Spend implies that oth
in this model might be driving Income. Therefore, relying solely on Advertising Spend to predict or
not be effective.

Firm Size, showing some significance, might be a more reliable indicator for predicting Income. La
higher income, which could be due to economies of scale, better market reach, or more diversifie

Other Considerations

Given that Advertising Spend is not a significant predictor, it might be beneficial to investigate othe
variables that could influence Income. Additionally, checking for multicollinearity, adding interactio
modeling techniques might improve the model.

Considering the marginal significance of Firm Size, further data collection and analysis with a larger
clarify its role and potentially strengthen its significance in predicting Income

SECOND STAGE
Models' Explanatory
 R Square (0.999) and Adjusted R Square (0.999) indicate that approximately 99.89% of the variab
variable (likely Income) can be explained by the model. This suggests that Marketing Expenditure an
effective predictors of the dependent variable in this dataset.
Overall Significance of the Model

F-statistic (3170.42) and Significance F (4.45E-11) demonstrate that the overall model is highly sign
the combination of predictors (Marketing Expenditure and Firm Size) significantly explains the varia
variable.
Significance of Individual Predictors

The negative intercept is statistically significant (p-value: 0.027). It implies that when both Marketin
Size are zero, the dependent variable would be -11079.73. This might not be practically meaningf
significant.

Statistically significant (p-value: 0.048). For each additional unit of Marketing Expenditure, the d
expected to increase by 3.78 units, holding Firm Size constant.
Statistically significant (p-value: 0.002). For each additional unit of Firm Size, the dependent variable
by 343.28 units, holding Marketing Expenditure constant.
Practical Implications

Model Validity: The extremely high R Square and F-statistic values indicate that the model is robu
chosen (Marketing Expenditure and Firm Size) are highly relevant to predicting the depend

Effect of Marketing Expenditure: Marketing Expenditure has a positive and statistically significant im
variable. However, its effect is relatively smaller compared to Firm Size.

Effect of Firm Size: Firm Size has a much larger positive impact on the dependent variable com
Expenditure. This suggests that larger firms tend to have higher values for the dependent variable (
could be due to economies of scale, better market reach, or other advantages associated with

Other Considerations

Data Size and Robustness: Given the small sample size (10 observations), the results should be inte
More data would help validate these findings and ensure they are not due to overfi

Additional Variables: Considering other potential variables that might influence the dependent var
more comprehensive model and potentially increase its explanatory power furth

SUMMARY
The regression analysis highlights that the model has a very high explanatory power overall, but the individual p
Advertising Spend is not statistically significant, while Firm Size shows marginal significance. This suggests t
other than Advertising Spend might be more crucial for predicting Income, and additional variables should be co
improve the model's robustness and predictive capability.

The regression analysis indicates that both Marketing Expenditure and Firm Size are significant predictors of th
variable, with Firm Size having a much larger impact. The model has an extremely high explanatory power an
significance, suggesting it is robust and the chosen predictors are relevant. However, given the small sample si
validation with more data is recommended.
ome, as indicated by the R Square value of 0.992. This
Advertising Spend and Firm Size variables in the model.
wer even after adjusting for the number of predictors.

0235, but its p-value is 0.978, which is much higher than

ertising Spend is not a significant predictor of Income in
2 to 2.019), further indicating non-significance.

0235, but its p-value is 0.978, which is much higher than

ertising Spend is not a significant predictor of Income in
2 to 2.019), further indicating non-significance.

value of 0.085. This p-value is slightly above the 0.05

his suggests that Firm Size has a noticeable, albeit not
onal unit increase in Firm Size, Income increases by
dvertising Spend constant.

uded variables (Advertising Spend and Firm Size) are

Advertising Spend implies that other factors not included
n Advertising Spend to predict or influence Income may
ve.

dicator for predicting Income. Larger firms tend to have

r market reach, or more diversified revenue streams.

t be beneficial to investigate other potential explanatory

multicollinearity, adding interaction terms, or using other
mprove the model.

lection and analysis with a larger sample size could help

significance in predicting Income
proximately 99.89% of the variability in the dependent
sts that Marketing Expenditure and Firm Size are highly
nt variable in this dataset.

t the overall model is highly significant. This means that

ze) significantly explains the variability in the dependent

implies that when both Marketing Expenditure and Firm

might not be practically meaningful but is statistically

t of Marketing Expenditure, the dependent variable is

Firm Size, the dependent variable is expected to increase

g Expenditure constant.

ues indicate that the model is robust and the predictors

y relevant to predicting the dependent variable.

tive and statistically significant impact on the dependent

smaller compared to Firm Size.

ct on the dependent variable compared to Marketing

alues for the dependent variable (likely Income), which
other advantages associated with larger firm size.

vations), the results should be interpreted with caution.

ensure they are not due to overfitting.

might influence the dependent variable could provide a

rease its explanatory power further.
power overall, but the individual predictor of
ginal significance. This suggests that factors
d additional variables should be considered to
e capability.

ze are significant predictors of the dependent

remely high explanatory power and overall
owever, given the small sample size, further
nded.
 The effect of marketing expenditures on ABC Company's performance could be endogenous due to its correl
conditions.
Dependent Variable (Y) - Income
Endogenous Variable (X1) - Marketing Expenditures
Instrumental Variable (Z) - Advertising spend
Exogenous Variable (W) - Firm Size

DATA SET - 1ST

Income (Y) Marketing Expediture (X1) Advertising Spend (Z)
1 50000 7000 3000
2 55000 7500 3200
3 52000 7200 3100
4 60000 8000 3500
5 63000 8200 3600
6 66000 8500 3800
7 64000 8300 3700
8 68000 8700 3900
9 70000 8800 4000
10 73000 9000 4200

FIRST STAGE
SUMMARY OUTPUT

Regression Statistics
Multiple R 0.995993659036028
R Square 0.992003368839976
Adjusted R Square 0.989718617079969
Standard Error 69.727697117392
Observations 10

ANOVA
df SS
Regression 2 4221966.33778294
Residual 7 34033.6622170633
Total 9 4256000

Coefficients Standard Error

Intercept 2452.52466627975 319.993537693539
Advertising Spend (Z) 0.0235055136389997 0.84401539998674
Firm Size (W) 45.0957632037145 22.5371469219838

Predicted Value 4486.15307771441

DATA SET - 2ND

Income (Y) Marketing Expediture (X1) Firm Size (W)
1 50000 7000 100
 2 55000 7500 110
3 52000 7200 105
4 60000 8000 120
5 63000 8200 125
6 66000 8500 130
7 64000 8300 128
8 68000 8700 135
9 70000 8800 140
10 73000 9000 145

SECOND STAGE
SUMMARY OUTPUT

Regression Statistics
Multiple R 0.999448478906366
R Square 0.998897261988249
Adjusted R Square 0.998582193984892
Standard Error 291.367591719905
Observations 10

ANOVA
df SS
Regression 2 538305734.485467
Residual 7 594265.514532601
Total 9 538900000

Coefficients Standard Error

Intercept -11079.7329143755 3967.60113411784
Marketing Expediture (X1) 3.77847604084839 1.57929348435321
Firm Size (W) 343.283582089552 72.498825718256
 e endogenous due to its correlation with other unobserved variables, such as market
nditions.

Firm Size (W)

100
110
105
120
125
130
128
135
140
145

MS F Significance F
2110983.16889147 434.184311050478 4.573E-08
4861.95174529475

t Stat P-value Lower 95%Upper 95%Lower 95.0%Upper 95.0%

7.66429436030847 0.00011972321638763 1695.8602 3209.1891 1695.8602 3209.1891
0.0278496264871103 0.978559431222303 -1.972274 2.0192848 -1.972274 2.0192848
2.00095262101371 0.0854991237674896 -8.196121 98.387647 -8.196121 98.387647
 MS F Significance F
269152867.242734 3170.41797752809 4.453E-11
84895.0735046573

t Stat P-value Lower 95%Upper 95%Lower 95.0%Upper 95.0%

-2.79255210890521 0.0268097565298887 -20461.62 -1697.847 -20461.62 -1697.847
2.39251037143096 0.0479914200267822 0.0440404 7.5129117 0.0440404 7.5129117
4.73502265296843 0.00212011764369252 171.8511 514.71606 171.8511 514.71606
Upper 95.0%
Upper 95.0%
 An Analysis on the Decisions and Motivations of Young Adul
Marikina City on the Immunization of the COVID-19 V

Dependent Variable (Y) - Confidence

Endogenous Variable (X1) - Familiarity of the Vaccine
Instrumental Variable (Z) - Citizen's Activity
Exogenous Variable (W) - Availablity of the Vaccine

DATA SET - 1ST Confidence (Y) Familiarity (X1) Activity (Z)

1 0 1 1
2 0 1 2
3 1 1 0
4 0 3 1
5 0 3 3
6 0 1 1
7 0 1 1
8 0 2 1
9 0 3 1
10 1 2 0
11 0 3 0
12 1 1 2
13 0 3 2
14 1 3 2
15 0 3 1
16 0 2 1
17 0 1 1
18 0 1 1
19 0 1 0
20 0 2 2
21 0 1 1
22 1 0 0
23 0 3 1
24 0 2 2
25 1 0 1
26 0 3 1
27 0 2 1
28 3 2 2
29 0 1 1
30 2 3 1
31 1 2 2
32 0 2 1
33 2 2 2
34 0 1 2
 35 0 3 1
36 0 0 0

DATA SET - 2ND Confidence (Y) Familiarity (X1) Availablity (W)

1 0 1 1
2 0 1 1
3 1 1 0
4 0 3 2
5 0 3 2
6 0 1 0
7 0 1 1
8 0 2 0
9 0 3 0
10 1 2 3
11 0 3 0
12 1 1 1
13 0 3 0
14 1 3 0
15 0 3 0
16 0 2 2
17 0 1 2
18 0 1 0
19 0 1 1
20 0 2 0
21 0 1 0
22 1 0 0
23 0 3 0
24 0 2 0
25 1 0 1
26 0 3 0
27 0 2 1
28 3 2 0
29 0 1 1
30 2 3 1
31 1 2 0
32 0 2 0
33 2 2 2
34 0 1 0
35 0 3 0
36 0 0 0
s and Motivations of Young Adults Residing in
Immunization of the COVID-19 Vaccine

Availablity (W) FIRST STAGE

1 SUMMARY OUTPUT
1
0 Regression Statistics
2 Multiple R 0.285009708
2 R Square 0.0812305337
0 Adjusted R Square 0.0255475357
1 Standard Error 0.9677587978
0 Observations 36
0
3 ANOVA
0 df SS MS
1 Regression 2 2.7325048965 1.3662524483
0 Residual 33 30.906383992 0.9365570907
0 Total 35 33.638888889
0
2 Coefficients Standard Error t Stat
2 Intercept 1.3858980467 0.3262158816 4.2484076495
0 Activity (Z) 0.3777989519 0.2220455367 1.7014480793
1 Availablity (W) -0.0345402573 0.1953187635 -0.1768404461
0
0 PREDICTED VA 1.5298231241
0
0
0
1
0
1
0
1
1
0
0
2
0
0
0

SECOND STAGE
SUMMARY OUTPUT

Regression Statistics
Multiple R 0.1148128677
R Square 0.0131819946
Adjusted R Square -0.0466251573
Standard Error 0.7449009762
Observations 36

ANOVA
df SS MS
Regression 2 0.2445992328 0.1222996164
Residual 33 18.310956323 0.5548774643
Total 35 18.555555556

Coefficients Standard Error t Stat

Intercept 0.3392220203 0.280601866 1.2089086405
Familiarity (X1) -0.0061242345 0.1284738937 -0.0476690968
Availablity (W) 0.0993673868 0.1503698705 0.6608197933
 F Significance F
1.4588031652 0.2471201375

P-value Lower 95% Upper 95% Lower 95.0% Upper 95.0%

0.0001653682 0.7222068453 2.049589248 0.7222068453 2.049589248
0.0982643495 -0.0739560892 0.829553993 -0.0739560892 0.829553993
0.8607146166 -0.4319192694 0.3628387549 -0.4319192694 0.3628387549
 F Significance F
0.220408332 0.8033625314

P-value Lower 95% Upper 95% Lower 95.0% Upper 95.0%

0.235288762 -0.2316667685 0.9101108092 -0.2316667685 0.9101108092
0.9622672945 -0.2675063366 0.2552578677 -0.2675063366 0.2552578677
0.5133150607 -0.2065624151 0.4052971886 -0.2065624151 0.4052971886
FIRST STAGE
Models' Explanatory
The model explains only 3.28% of the variation in the dependent variable (x1), which is very low.
Overall Significance of the Model
The model is not statistically significant overall (p-value = 0.5769), suggesting that the independen
Significance of Individual Predictors
Intercept: The coefficient is 0.1675 with a p-value of 0.5052, indicating that it is not statistically s
Activity (Z): The coefficient is 0.1386 with a p-value of 0.4185, indicating that it is not a significa
Availability (W): The coefficient is 0.0977 with a p-value of 0.5163, indicating that it is also not a
Practical Implications
Given the low explanatory power and lack of significant predictors, this model is not useful for pre

Other Considerations
Sample Size: The relatively small sample size (36 observations) may limit the ability to detect sig
Multicollinearity: Check for multicollinearity between Activity and Availability, which could infl
PREDICTED VALUE

the predicted value of 0.196219598 means that, given the specific values of the independent variab
variable in the second stage) would be approximately 0.1962.

This predicted value will be used in the second stage of the 2SLS regression to replace the endoge
endogenous variable on the dependent variable in the second stage.

SECOND STAGE
Models' Explanatory
The model explains only 1.32% of the variation in the dependent variable, which is very low. This
Overall Significance of the Model
The model is not statistically significant overall (p-value = 0.8034), suggesting that the independen
Significance of Individual Predictors
Familiarity (X1): The coefficient is -0.0061 with a p-value of 0.9623, indicating that it is not a sig
Availability (W): The coefficient is 0.0994 with a p-value of 0.5133, indicating that it is also not a
Practical Implications
Given the low explanatory power and lack of significant predictors, this model is not useful for pre
Other Considerations
Sample Size: The relatively small sample size (36 observations) may limit the ability to detect sig
Multicollinearity: Check for multicollinearity between Familiarity and Availability, which could i

SUMMARY
First Stage

The first-stage regression model does not effectively predict the dependent variable. The low R-sq
Availability) are not strong predictors.

Second Stage

The second-stage regression analysis indicates that the model, which includes Familiarity and Ava
statistically significant overall (p-value = 0.8034). Neither Familiarity nor Availability significantl
Therefore, this model is not useful for prediction, suggesting that other variables not included in th
specification is recommended.
riable (x1), which is very low. This indicates that Activity and Availability are not good predictors of x1.

suggesting that the independent variables collectively do not explain the variability in the dependent variable.

ting that it is not statistically significant.

icating that it is not a significant predictor of the dependent variable.
, indicating that it is also not a significant predictor.

this model is not useful for predicting the dependent variable. It suggests that other variables not included in this model might be better pre

y limit the ability to detect significant effects.

Availability, which could inflate standard errors and affect the significance of the predictors.

alues of the independent variables (Activity and Availability), the model predicts that the dependent variable (e.g., an instrumental variable

gression to replace the endogenous variable with its predicted value from the first stage, thus allowing for a more accurate estimation of the

riable, which is very low. This indicates that Familiarity and Availability are not good predictors of the dependent variable.

suggesting that the independent variables collectively do not explain the variability in the dependent variable.

3, indicating that it is not a significant predictor of the dependent variable.

, indicating that it is also not a significant predictor.

this model is not useful for predicting the dependent variable. It suggests that other variables not included in this model might be better pre

y limit the ability to detect significant effects.

and Availability, which could inflate standard errors and affect the significance of the predictors.

endent variable. The low R-squared value, lack of significant predictors, and non-significant overall model suggest that the chosen instrum

h includes Familiarity and Availability as predictors, is not effective. The model explains only 1.32% of the variability in the dependent var
ty nor Availability significantly predicts the dependent variable, as evidenced by their high p-values and wide confidence intervals that incl
her variables not included in the model might be better predictors. Further research with different predictors, a larger sample size, or an imp
model might be better predictors.

an instrumental variable for the endogenous

accurate estimation of the effect of the

model might be better predictors.

t that the chosen instruments (Activity and

ility in the dependent variable and is not

fidence intervals that include zero.
ger sample size, or an improved model
 An Analysis on the Decisions and Motivations of Young Adul
Marikina City on the Immunization of the COVID-19 V

Dependent Variable (Y) - Confidence

Endogenous Variable (X1) - Familiarity of the Vaccine
Instrumental Variable (Z) - Citizen's Activity
Exogenous Variable (W) - Availablity of the Vaccine

DATA SET - 1ST Confidence (Y) Familiarity (X1) Activity (Z)

1 0 1 1
2 0 1 2
3 1 1 0
4 0 3 1
5 0 3 3
6 0 1 1
7 0 1 1
8 0 2 1
9 0 3 1
10 1 2 0
11 0 3 0
12 1 1 2
13 0 3 2
14 1 3 2
15 0 3 1
16 0 2 1
17 0 1 1
18 0 1 1
19 0 1 0
20 0 2 2
21 0 1 1
22 1 0 0
23 0 3 1
24 0 2 2
25 1 0 1
26 0 3 1
27 0 2 1
28 3 2 2
29 0 1 1
30 2 3 1
31 1 2 2
32 0 2 1
33 2 2 2
34 0 1 2
35 0 3 1
 36 0 0 0

DATA SET - 2ND Confidence (Y) Familiarity (X1) Availablity (W)

1 0 1 1
2 0 1 1
3 1 1 0
4 0 3 2
5 0 3 2
6 0 1 0
7 0 1 1
8 0 2 0
9 0 3 0
10 1 2 3
11 0 3 0
12 1 1 1
13 0 3 0
14 1 3 0
15 0 3 0
16 0 2 2
17 0 1 2
18 0 1 0
19 0 1 1
20 0 2 0
21 0 1 0
22 1 0 0
23 0 3 0
24 0 2 0
25 1 0 1
26 0 3 0
27 0 2 1
28 3 2 0
29 0 1 1
30 2 3 1
31 1 2 0
32 0 2 0
33 2 2 2
34 0 1 0
35 0 3 0
36 0 0 0
s and Motivations of Young Adults Residing in
Immunization of the COVID-19 Vaccine

Availablity (W) FIRST STAGE

1
1
0
2
2
0
1
0
0
3
0
1
0
0
0
2
2
0
1
0
0
0
0
0
1
0
1
0
1
1
0
0
2
0
0
0

SECOND STAGE