You are on page 1of 3

MISM 6210

Information Visuals and Dashboards for Business


Analysis Homework #1

For this assignment, you will be conducting analysis based on the Indian Premier League case
(W25529). R code to run some of the analyses is posted on Canvas, as well, though you will
need to adapt it as you work through the questions.

1. What is the fundamental business question that the case proposes? What hypothesis
would you construct to answer this question?

Ans: The case focuses on examining if the salaries of IPL players correspond to their
performances on the field. The hypothesis formulated for this investigation is: Players'
salaries in the IPL is not directly related to their performance.

2. Conduct a descriptive analysis of the performance measures included in the data set using
the R code posted on Canvas. What do you observe about the various metrics for player
performance recorded here?

Ans:
1. Runs: Scores range widely from a low of 12 to a high of 692, with players
averaging 249.3 runs.
2. Batting Average: The range of averages is from 3.60 to 83.20, with a mean value
of 28.58, indicating a variety in batting reliability.
3. Strike Rate: Players' strike rates extend from 63.15 to 204.81, with an overall
mean of 133.12, showcasing different paces in scoring.
4. Hundreds: Achieving hundreds is uncommon, with players averaging only
0.08571, highlighting its rarity.
5. Fifties: Players hit up to 8 fifties, more typical than hundreds, with an average
occurrence of 1.486.
6. Fours: The frequency of fours hit ranges from 1 to 64, with an average of 22.40.
7. Sixes: The count of sixes hit varies from 0 to 52, with an average of 10.51.

In short, the data shows various levels of player performance, important for determining
how their pay compares to their on-field performance.
3. Conceptually, how do each of the performance indicators potentially relate to the overall
objective in the game?

Ans:
1. Runs: This is the most direct measure of a player's contribution to the team's score.
High run-scorers are crucial for building a competitive total or chasing down a
target.
2. Batting Average: Reflects a player's consistency in scoring runs. A higher average
suggests reliability and the ability to contribute valuable runs regularly, which is key
for team stability.
3. Strike Rate: In T20 cricket, where each over is critical, the strike rate is vital. A
higher strike rate indicates the ability to score runs quickly, a crucial aspect in this
fast-paced format.
4. Hundreds: Although rare in T20 cricket, scoring a hundred is a significant
achievement. It indicates the player's capacity for playing a match-defining innings,
contributing massively to the team's total.
5. Fifties: More common than hundreds, a fifty is also a substantial contribution in a
T20 match. It signifies the player's ability to build a solid innings, which can be
crucial in setting a challenging total or anchoring a chase.
6. Fours and Sixes: These are key indicators of a player's aggressive batting and
ability to accelerate the scoring rate. In T20 cricket, hitting boundaries is essential to
boost the team's total quickly.

4. Given your hypothesis, what performance indicators do you would be most appropriate to
test it out? Create a General Batting Performance Index, as Mitra suggests, adapting the
included R code.
Ans: For my hypothesis, the indicators which would be the most appropriate to test
would be:
1. Batting Average (Avg): It measures consistency and reliability in scoring.
2. Strike Rate (SR): It's crucial in T20 cricket to indicate how quickly a player scores
runs.
3. Runs Scored: Total runs give a direct indication of the player's scoring contribution.
4. Hundreds and Fifties: High scores like hundreds and fifties show the player's ability
to play match-defining innings.
5. Fours and Sixes: The number of boundaries indicates aggressive batting, which can
change the course of a match quickly in T20 cricket.
5. Given your index, which players rank most highly? You can sort the data using the
arrange () command, as shown in the included R code.
Ans: After arranging the players in descending order of their GBPI, the highest-ranking
players are:
Andre Russel with GBPI of 4.73
MS Dhoni with GBPI of 3.73
Hardik Pandya with GBPI of 3.40
David Warner with GBPI of 3.15
Jonny Bairstow with GBPI of 2.77

6. How does your index compare to the salaries paid to the players? Try running a
regression using the lm () command. What do these results suggest? Given your
analysis, who is most underpaid? Who is the most overpaid?
Ans: Upon sorting the players based on their GBPI from highest to lowest, it appears that
there is a general trend where higher GBPI scores tend to correspond with higher salaries.
However, it's important to note that salaries are probably affected by more than just
GBPI. Other aspects like a player's popularity, seniority, and specific position or duties
within the team might also play a significant role in how much they're paid. From the
analysis, it seems that Virat Kohli has a salary that's less justified by his GBPI, indicating
he may be overvalued, whereas Stuart Binny's performance suggests he could be
undervalued, given his lower salary in comparison to his GBPI.

You might also like