Statistical Analysis and Data Interpretation Assignment, Fall 2024

This assignment solution presents a comprehensive data analysis, encompassing various statistical techniques. Section 1 focuses on scatter plots and the computation of annual contributions and z-scores. Section 2 delves into numerical summary statistics, proportions, and hypothesis testing related to investment risk. The analysis includes z-score calculations and p-value interpretations to assess the significance of findings. Section 3 examines box and whisker plots, estimates, and z-score computations, emphasizing the relationship between risk and return in investments. Section 4 provides numerical summary statistics, sample size calculations, and the determination of a 95% confidence interval. The solution demonstrates a strong understanding of statistical concepts, data interpretation, and the application of these techniques to real-world scenarios, such as investment analysis and evaluating proposed changes.

COMPUTING ASSIGNMENT
Paras Bhandari
Student Number: 11600712
Allocated Sample: 148
26-Sep-17
1

SECTION 1
Relevant data
a) Scatter plot
Comment: Considering the positive slope of the best fit line with not much deviation of points, it
would be fair to conclude that there appears to be a moderate to strong position association
between the variables of interest.
2

b) Computation of annual contribution
Thus, for the income $20,000 the annual contribution is $24,686.2.
c) Computation of z score
d) Computation of P (Z<Z score)
P ( Z <−1.1018 ) =0.1353
3

e) Computation of estimated rank
4

SECTION 2
a) Numerical summary statistics for the sample is in the pivot table
Sample size for each investment type and proportion of investment that would make a loss is
shown below:
b) Graphical representation
5

c) Based on the respective proportions computed in part (a), it is apparent that a directly
proportional relation is observed in the underlying investment risk level and the chances of
making loss.
d) (i) Computation of estimate value of proportion difference
(ii) Computation of z score
6

(iii) Computation of P (Z<Z score)
P ( Z <0.2334 )=0.5922
7

(iv) Computation of estimated rank
8

e) Given significance level = 0.05 or 5%
(i) Hypotheses
(ii) The p value = 0.1838
(iii) No null hypothesis rejection is caused as p value obtained tends to be greater than the
level of significance (5%).
(iv) There is a 95% chance that likelihood of making loss does not depend on the
underlying risk involved in the concerned investment.
9

SECTION 3
a) Numerical summary statistics for the sample is in the pivot table
b) Box and whisker plot
10

c) It is estimated on basis of the represented data that risk and return are proportionally related.
Thus, for selecting the better investment instead of relying on either risk or return to make
the choice, it becomes pivotal to combine the two and then take a decision based on the
investment having lowest risk per unit return derived.
d) (i) Computation of estimate for μ1−μ2
(ii) Computation of z score
11

(iii) Computation of P (Z<Z score)
P ( Z <−0.943 )=0.1728
12