1

A Research Study on Formula One:

Determining the Effectiveness of Drivers Based on Their Experience

Ignacio Felix-Padilla
 2

INTRODUCTION

As of August 2020, there were eight Formula One drivers without a firm contract to race in

the 2020-2021 season, out of only twenty driver seats in what is the highest circuit of car racing

worldwide. Every year, teams have to decide to sign a driver that is already racing in, or that was

recently racing in Formula One, or bring up a new driver either out of Formula Two (the racing

league directly one level below Formula One) or from another racing league (Balfour, 2020). Teams

had to make a decision: go for the experience or gamble for young potential.

Despite being a sport with hundreds of millions of followers globally, and with billions

of dollars in revenue and media spend, only twenty drivers compete at the Formula One level

annually, with many dreaming of becoming one of the selected few (Gough, 2020; Lange, 2020).

In 70 years of history, there have been less than 800 Formula One drivers, with less than 120

drivers having raced over the last 20 years. Of these 800 drivers, only 33 have ever won a

championship, and only 76 drivers (less than 10% of the total) have won 2 races or more in the

1,035 races since its inception (Davies, 2020). Being a good driver is not enough. These drivers

want to be the best. Over the past few years, there has been a surge of younger drivers in

Formula One. Many of these young drivers have had some very good results. For example,

Lewis Hamilton, the current champion, started in Formula One at 22 years of age and is now the

driver with most races won ever (Donaldson, 2020). Teams are constantly evaluating whether to

sign a new driver with the promise to be the next big thing or to sign an older, more experienced

and proven driver, even if that person may not win a championship. Along with that decision,

comes an economic decision as well, which is how much to pay that driver.

The null hypothesis to be proven or disproven through this research is that a rookie

driver is a more efficient decision for teams versus hiring an experienced veteran.
 3

Literature Review

There are only a handful of research studies about Formula One, with studies focused on

why certain drivers or teams are successful but have not focused on how signing a driver might

affect the results of the team. For example, there have been multiple studies about who the

greatest driver of all time is (Smedley, et al., 2020), how a driver and car perform in certain

conditions (Marino, Aversa, Mesquita, & Anand, 2015), and if the performance of a team is

affected by the transactions a team makes with its competitors (Aversa, Furnari, & Haefliger,

2015). This study fills an important gap in the research field by estimating the expected

effectiveness (total points at the end of a season along with the salary earned that year) of a

rookie driver compared to older and more experienced drivers based on historical and statistical

analysis from contracts of prior young and experienced drivers, and their results on the races they

competed in, for which there were no studies or white papers found.

This research analyzed the historical results of Formula One teams when they changed

drivers to determine whether a rookie driver or a more experienced driver had greater

effectiveness. This study aimed to figure out whether teams would be better suited for the future

if they signed a rookie driver or if they signed an older driver based on statistical analysis of

historical results over the past 15 years, and estimate mathematically the effectiveness of a

given driver based on their experience.

As the sport and popularity of Formula One has evolved and grown, the regulations for the

points system have changed drastically. From the year chosen as the starting point (2005), the points

system awarded the first eight finishers, with the point distribution going from ten points for the

number one driver, to one point for number eight, (Diepraam, 2019). The point system
 4

then changed in 2010, with the first ten finishers awarded points, and the distribution ranging

from twenty-five points for the race champion, to one point for the tenth position driver, and

no points for drivers in places 11 to 20 on each race (Diepraam, 2019).

METHODS

Design

This study explores the effectiveness of a rookie driver when compared to more

experienced drivers. The goal of the research is to figure out what a team’s expected results

would be if they hired a rookie driver compared to a more experienced driver. This is important

because the results that a driver achieves may be worth millions of dollars for a team. For the

purpose of this study, a rookie driver is considered a driver that is in his first five years in

Formula One. An experienced driver has been racing in Formula One for at least six years with

a maximum of 13 years. A veteran driver has been racing in Formula One for at least 14 years.

A single method study was conducted through a quantitative analysis of data using

statistical tools across points won per season and salary earned by the drivers each year. The

method used to gather data and conduct the research was the causal-comparative method

(Salkind, 2010), and that same method was used to identify a causative relationship between

the grouping variable (selected driver) of the study and the dependent variable (expected

effectiveness) of the study (Mahehwari, 2018).

The data gathered for this research included initially the last twenty years of results (from

2000 to 2019), however, it had to be adjusted to the years 2005 to 2019, since the data for

salaries per driver is practically non-existent before 2005, as teams traditionally do not disclose

the terms of a contract.

 5

Other variables besides the salary per driver per year included the number of years the

driver had been racing in Formula One, the ending position of the driver each season, and the

calculated variable was the points the driver accumulated in each race.

The study also captured the data of what team the driver had worked with each year, to

identify when new contracts occurred during their career, and thus compare how effective the

hiring practices of the teams had been over time.

Procedure

In order to determine the effectiveness of a driver, the study analyzed the number of

points per year achieved for each driver. As mentioned previously, Formula One has changed

the point system several times during its history. To account for the changes in regulation during

the period of the study, this research adopted the point system used since 2010, which required

to re-calculate the points awarded to drivers during the years 2005-2010, and from 2010 to 2019.

One additional clarification is that in 2019, the Formula One organizers started awarding one

extra point per race to the driver with the fastest lap in each race. This research does not

incorporate these additional potential points, since the data for the fastest lap of each race is only

available after 2010, when the new methodology was implemented.

The results from 2005-2019 were obtained from a freely available online database (Vopani,

2020). This database is public domain, so the data has been used liberally. This database included the

results for every race and every driver since Formula One races started and catalogs them under a

unique id. Each race from every year has its own id; for example, the Australian Grand Prix of the

2007 season is given the race id of 36. The database was then filtered to only include the data

necessary to conduct the study, and its information was used to determine additional pieces of

information required for the analysis. In the excel database created to

 6

analyze the results, each column contained a different data category while each row contained

the specific data that corresponded to that column. The main database included seven columns

of data, with each column having a different category, some of these were raw data from the

online database, while others were calculated fields. These categories were as follows:

A. Name of the driver – used as an identifier to track the effectiveness of a driver over time

B. Number of years racing in Formula One – used to determine whether the driver is a rookie, an

experienced driver, or a veteran, with the categorization for a driver changing over time as

they gained experience

C. Number of years racing with their team – to determine if the driver was in a new contract and

how effective their performance was concerning the salary earned

D. Year – to track the results for each year and be able to define the point system

conversion required for each race

E. Total points scored in that year for each driver– used to measure effectiveness for the

driver (most points at a “reasonable” salary is most effective)

F. Salary – used to calculate the effectiveness of the driver (measured as dollars per point won,

or points achieved per season per dollar paid)

G. Cost of a point per dollar (how much did each singular point won during a season for a driver

‘cost’ to their employing teams)

Each cell in the database included the data corresponding to the driver. The database was

aggregated from individual races to a yearly total, as the data itself was provided at the race level,

which meant aggregating twenty races per year for each driver. While most of the data was
 7

already included on the online database, some information, such as years racing by driver,

the number of years with each team, and the cost of a point per dollar had to be calculated.

The average number of points per year for each of the three categories (rookie,

experienced, and veteran) of driver experience was calculated in aggregate for each group.

These values gave an idea as to, on average, whether a rookie driver outscored an experienced

driver, a veteran driver, or none of the above. The annual salary was not included on the Vopani

online database and was gathered as reported by news outlets (Renken, 2020). The average of

the salaries for the three different groups of driver experience was calculated. With this

information, the column labeled as cost per point was quantified by dividing the total number of

points a driver accumulated during a singular season and dividing that number by the salary the

driver earned during that season. By calculating this data at the driver level first, and then

aggregating for each of the three tenure groups, the cost per point metric allowed for a direct

comparison between the three distinct categories of drivers: rookie, experienced, and veteran.

The variance of the points between the three groups was determined in order to compare

the averages of the three categories of driver experience and determine how “scattered” the

results were over time. This helped to look for consistency in the number of points scored by

rookie drivers, experienced drivers, or veteran drivers.

The study then compared the variances between each group using a one-way analysis of

variance test (ANOVA), which allowed for a statistical examination of the points scored by each

individual driver sorted by the number of years they had been racing in Formula One.

In order to explore if a correlation existed between the number of points scored by drivers

and their years of experience driving (which seemed plausible given that the average points

increased based on the average years racing), a regression analysis was performed. This
 8

statistical analysis compared the number of points of each driver with the number of years they

have been racing to determine if a direct correlation existed, testing for both linear and binomial

correlations.

Materials

An Apple MacBook Air was used to acquire research and find the database used in

the study. Microsoft Excel was used to filter and sort the data used in terms of the years from

2005-2019. The historical database from Kaggle was used as the data source used in the study

(Vopani, 2020). A calculator was manually used to double-check calculations done in

Microsoft Excel, given complex databases and formulae were utilized.

RESULTS

Over the last 15 years, there have been 84 drivers in Formula One. On average, over that

period a driver has achieved 86 points per season, with the top 25% of drivers achieving 136

points, compared with only 10 points for the bottom 25% of drivers.

The means and variances for the three groups of driver experience were calculated. Both

the variance and the mean compared the points between each group. Rounded to the nearest

tenth, rookie drivers had a mean of 52.4 points, experienced drivers had a mean of 145.1, and the

veteran drivers had a mean of 58.2.

Rookie drivers scored a variance of 5782.9, experienced drivers scored 13,532.1,

and veteran drivers scored 6074.7.

 9

Table 1

Mean and Variance of Points Scored

Group Mean Variance

1-5 years racing 52.4 5,782.9

7-13 years racing 145.1 13,532.1

14+ years racing 58.1 6,074.7

The analysis by groups proved insufficient to accept or reject the null hypothesis, which

created the need to analyze results more exhaustively. Additional analyses were completed to

understand the relevance of these groups, and the dispersion of the results: ANOVA,

correlation, and segmented analysis within each group.

In order to compare the variances between the three groups, a one-way analysis of

variance (ANOVA) was used to find the f-value, which measures the distance between a certain

data point (points scored by one driver in a specific season) and the mean of the three groups.

Rounded to the nearest hundredth, the f-value was calculated to be 34.79. Using this the p-

value was computed. The p-value was then assessed to be 2.2E-14.

Table 2

Analysis of Variance

ANOVA: One-Way

Source of Variation F-value P-value

Between Groups 34.78576 2.2E-14

 10

A regression analysis was conducted to find the level of correlation between the number

of points scored by a driver and the number of years that a driver has been racing. The scatterplot

below (Figure 1) shows the results of that statistical analysis. In a regression analysis, a value

known as the coefficient of determination (R2) is given. Rounded to the nearest hundredth, the

coefficient of determination for this analysis was 0.21.

Figure 1 – Points earned per season for each driver based on their years of experience from
2005 to 2019

The final analysis conducted consisted of comparing the results for segments of drivers

within each group (rookie, experienced, veterans), to identify whether pockets of opportunity

existed within the groups that would support a modified null hypothesis. This analysis showed

that in 30% of the cases, a rookie driver would be more efficient than an experienced driver.

The results were twice as large in the case of veterans, where 62% of these drivers over the last

15 years performed the same or worse than an average rookie driver.

 11

DISCUSSION

On average, Formula One drivers achieve more points based on the number of years they

have been racing (Figure 2), with the average increasing each year for their first 10 years in their

career, averaging 180 points by their 10th year. Past their 12th year, the average points for

experienced drivers begin to decrease, with averages dropping significantly in years 14 and 15 to

levels even below drivers in their 4th year. There are only a handful of drivers that remain racing

past their 15th year, those that do achieve, on average, more points per season in their 16th and

17th years. The points of these drivers then decrease again past that point. Although drivers with

these large sums of years racing in Formula One are not necessarily old, of course, their

regression is to be expected as it has been proven that at a certain age, the reaction time of

people will slow down (Tun & Lachman, 2008).

Figure 2 – Average points earned per season based on driver’s years of experience

Average salary per year also increases with driver experience, as shown in Figure 3. The

salary past a driver’s 12th year, however, does not decline at the same rate that the average points
 12

decline, with drivers in their 15th and 16th years averaging a salary as large as drivers in their

13th year which is the year that, on average, follows the year with the greatest number of points

achieved. The increase in salary in the 15th and 16th years can be attributed to the fact that the

majority of these drivers have experienced success throughout their lengthy careers and are

likely previous Formula One world champions (Balfour, 2014). For example, Fernando Alonso,

a two-time Formula One world champion in his 19th year racing in Formula One, recently

signed a one-year contract worth 20 million dollars, the third-highest salary for the 2021 season.

Figure 3 – Average points earned per season and average salary by driver’s years of experience

After understanding the extent to which points and salary increase with driver’s

experience over time, the results were grouped by category of experience, as rookies,

experienced, and veterans drivers. In Figure 4, the orange bars represent the average salary for

each group of drivers in millions of dollars and the blue line represents the average points scored

by that group of drivers over the fifteen years.

 13

The fact that the average points for experienced drivers is over three times as large as the

average points for rookies, would reject the null hypothesis for this research. The result is not as

clear, however, for veteran drivers. In addition, it can be seen that there is a significant difference

in the average salaries for rookie drivers versus those with more experience. For example, the

annual salary of veteran drivers is ~10 times that of rookie drivers per year ($15.5M vs $1.6M),

and these drivers’ average points is merely 25% higher than those of rookie drivers (58 vs 45

average points per year), raising the question whether those veterans are worth the salary they are

perceiving when compared to a rookie driver.

By analyzing results beyond simply averages, and looking at individual driver

performance, an even more scattered picture is present, with a significant variation on

points achieved for drivers with the same level of experience. Figure 5 shows that there is a

large variation in points for drivers at different years of experience. For example, rookies in

their second year of experience achieve anything from zero to over 250 points per season.
 14

Experienced drivers show an even larger spread, as evidenced by the almost twice as large

variance observed before for this group. As an example, drivers in their 9th year achieved from

zero points to over 350 over the past 15 years. The variation for veterans decreases somewhat

and as suggested by the variance calculation, it is somewhat similar to that of the rookies. In

the case of drivers with 15 years of experience, their range goes from zero to almost 200 points.

All three groups of driver experience (rookie, experienced, and veterans) have drivers that

score more points and also drivers that don’t score any point at all during an entire season.

Figure 5 – Points earned per season by individual drivers based on their years of experience
driving

As seen in the top right corner of the chart, the coefficient of determination is given, with a

rounded value of R2 = 0.21. In this scenario, the coefficient of determination analyzes the

predictability of estimating the number of points that a driver with a certain number of years racing

will have. With a value of 0.21, the coefficient of determination allows the conclusion that
 15

there is a little to no chance of predicting how many points a driver will have based only on

their years of experience, which supports the null hypothesis for this research.

The analysis of variance (ANOVA) shown previously in Table 2 provided two crucial

values, relevant to study the three groups in comparison with each other: the f-value and the p-

value. The f-value was found by performing an f-test on the three groups. Ideally, a smaller f-

value (close to a ratio of 1.0) would prove the null hypothesis true. Thus, the f-value of 34.79

proves that the variance between the three groups is much larger than the expected value. When

dealing with the p-value, the same principle applies. However, even though the p-value in this

study is 2.2E-14, this is only calculating the probability of accurately being able to estimate how

many points a driver will have in their next season. This means that it is very hard for teams to

predict how well a driver will do based only on the group of experience it belongs to, also

supporting the null hypothesis.

Figure 6 shows that there are opportunities for teams to make more efficient decisions in

terms of their drivers. The green box illustrates a positive opportunity, as these drivers are being

paid a rookie salary and are scoring well above the average for a rookie driver. The data shows

that over the last 15 years, there is a significantly large amount of experienced and veteran

drivers that have achieved results that are the same or worse (illustrated by the red boxes on the

chart) than the results of rookie drivers. These experienced and veteran drivers are being paid

significantly more than rookie drivers, but are also scoring either well below the average for

their group for experienced drivers, or not better than rookies in the case of veterans, partially

supporting the null hypothesis that a rookie driver can be more effective than an experienced

driver, but only in some cases.

 16

To calculate the extent of this opportunity, and measure the potential salary savings from

making a more efficient decision, results were analyzed further within each group of drivers, to test

a modified null hypothesis, expressed as “rookie drivers are a more efficient decision for Formula

One teams versus a meaningful portion of experienced drivers and versus a large portion of veteran

drivers”. In Figure 7, there are several measures of evaluation comparing experienced and veteran

drivers to rookies. There are two columns with data for both the experienced and veteran drivers;

the one on the left represents salary and the one on the right shows points earned. There are four

color-coded differentiators within each group: significantly better than rookies, a bit better than

rookies, approximately the same as rookies, and less than

 17

rookies. Since the average points scored for rookie drivers is 48, when comparing experienced

drivers, significantly better translates to 100 points or more scored (more than twice better

performance), a bit better than rookies translates to 61-99 points scored, approximately the same

translates to 50-60 points scored, and less than rookies translates to below 50 points scored. The

same distinction is used when comparing veteran drivers.

Starting with the salary column for experienced drivers, it can be seen that 79% of the

total salary paid to that group of drivers over the 15 years of analysis was given to the

experienced drivers that performed significantly better than rookie drivers, which supports the

notion that these drivers are earning their keep. 7% of the total salary was given to

experienced drivers that performed slightly better than rookie drivers, and 14% was given to

experienced drivers that performed the same or worse than rookie drivers. The same logic is

applied to the veteran drivers when comparing the distribution of their salaries.

The implication is that teams have overpaid some of these drivers significantly, leading

to more efficient decision-making opportunities. By calculating the salaries paid to these

experienced and veteran drivers during those years, and comparing them to the salaries paid to

rookie drivers that are achieving the same or better results, the study shows that teams have

overpaid experienced and veteran drivers by around 360 million dollars, as a rookie would have

achieved similar results, which will be detailed as follows. Over the last 15 years, for

experienced drivers with 6 to 13 years, 25% of their seasons were worse than an average rookie

driver, and an additional 5% of seasons their results were the same, for a total of 30% of the

times that experienced drivers performed the same or worse than an average rookie. For veteran

drivers, the differences are even more glaring, with their results being worse than that of an

average rookie driver 55% of the time, and an additional 7% of the time where their results are
 18

approximately the same, for a total of 62% of the time that a veteran driver performed the same

or worse than an average rookie.

By adding up the salaries that these experienced and veteran drivers earned during those

seasons, and comparing the total of those salaries versus the amount that average rookies would

have earned during those same seasons, it is estimated that teams spent an incremental 360

million dollars during those seasons by hiring an underperforming experienced or veteran driver

instead of a rookie.

Figure 7 – Comparison of points and salary earned for subgroups of experienced and veteran
drivers versus rookie drivers

In summary, when comparing the cost per point for drivers, we can see that there is an

opportunity to replace 25% of experienced drivers in years 6-13, and over 60% of drivers with

14+ years of experience with rookies, as they would be expected to perform at similar point levels

at much lower cost, providing teams the opportunity to create more competition for the
 19

coveted Formula One driver position, and saving in aggregate 360 million dollars, an equivalent

of 24 million dollars per year.

In conclusion, this research study has proven that while on average, experienced drivers

are more effective performers (more points despite higher salaries) than rookie drivers, there is

a significant opportunity where rookies outperform 30% of experienced drivers, and 62% of

veteran drivers, creating room for more competition in the Formula One circuit.

Limitations

As with all research studies, there are limitations, enumerated below:

One possible limitation may be the relatively small sample size when comparing the past

15 years to the entire 71 year-long history of Formula One. The reduced sample size was due to

the salary of drivers not available before 2005, as this was closely guarded confidential

information. This obstacle occurred mainly because there was less media around the sport of

Formula One, so no one kept track of the salaries. This potential limitation, however, is

relatively minor, as the salaries of Formula One drivers have skyrocketed only during the last 15

years. This increase in salary makes these latest years of Formula One the most valuable, as the

cost per point for each driver shows a better reflection of their performance. In addition, a side

analysis was conducted to analyze rookie versus experienced performance in prior years, with

similar results as observed in this analysis (higher performance for more experienced drivers in

the average, with significant variation in performance across tenure groups). One interesting fact

is that prior to 2005, drivers had longer tenures driving, highlighting the fact that Formula One

teams have been acting in the lines of this study, by hiring more rookie drivers and limiting the

tenure for veterans.

 20

Some drivers have gap years in between their Formula One racing careers, either due to a

short retirement or being replaced by another driver. This study accounted for this by not

counting the years they were missing from Formula One as part of their Formula One careers

(years racing). Hence, a driver that competed in Formula One for three seasons, left for two

years to race elsewhere, and then came back, would count in the analysis for his fourth season,

which is believed to be a fair representation, as competition outside of Formula One is generally

accepted as of less caliber.

Historically, some team owners have hired their relatives as their driver. This may have

influenced the driver to feel safe about not having to perform on the race track since they have a

relative (or even themselves in some cases) as their employer. For this study, this particular effect is

relevant only for rookie drivers, as most of these familial drivers only compete for one or two

seasons, bringing down the rookie driver average performance (this handful of drivers scored none or

very few points) which would highlight a higher potential performance for deserving rookies and

increased their true efficiency as compared to experienced or veteran ones.

Another limitation of this study is that there was no measure from any emotional or

personal aspect on a driver’s performance. For example, in 2009, Lewis Hamilton, the most

accomplished driver in Formula One history, broke up with his four-year girlfriend. This

year was the statistically worst year of Hamilton’s career.

Many studies have focused on the quality of the car as one of the most important criteria

for a team's performance in Formula One. This study excludes the car quality / relative

performance from its analysis. When analyzing driver careers for the duration of the study, it is

seen that drivers change teams a significant amount of times during their careers. For example,

the current champion (and seven-time champion during his career), Hamilton, has driven for four
 21

different teams, winning championships with three of them. A similar situation is observed with

the majority of drivers in the current championship season (as stated at the beginning of this

white paper, eight of the current drivers changed teams for the 2021 season), making this point

about the car quality less relevant for this study, and strengthens the hypothesis that focusing a

significant level of attention on the driver is one of the most important decisions a team can

make, in parallel with improving the car quality.

Finally, the rationale for teams to choose a certain driver may have to do with factors

outside of earning points, for example hiring a charismatic driver to bring popularity to their

brand, or as an image icon. This is a limitation from this analysis, which given recent hiring

decisions, may impact more for veteran drivers, who are former champions at the sunset of their

careers, and may represent for their teams a way to gather followers not based on winning but

on their driver image.

CONCLUSION

This research set out to prove or disprove the null hypothesis that a rookie driver is a

more efficient decision for teams versus hiring an experienced veteran. Initial analyses showed

that points earned by drivers do increase with experience, with the highest average in years of

experience in between years 10 to 12 of experience. While in most cases, an experienced driver

(6-13 years racing) will statistically be the most effective driver out of the three groups, there are

many instances where those drivers underperform.

A more thorough analysis demonstrated that a partially modified null hypothesis can be

accepted, as some rookie drivers are a more efficient decision versus 30% of the experienced

drivers, and versus 62% of the veteran drivers. Over the last 15 years, these decisions represented
 22

an excess in cost for teams adding up to 360 million dollars, or 24 million dollars per year, over

what teams would have spent on rookie drivers during that period. By comparing results at the

driver level, and proactively identifying promising rookies, Formula One teams can make more

efficient decisions when selecting their next driver.

 23

REFERENCES

Aversa, P., Furnari, S., & Haefliger, S. (2015, May 12). Business model configurations and

performance: A qualitative comparative analysis in Formula One Racing, 2005-

2013. Industrial and Corporate Change, 1-22.

Balfour, A. (2014, October 22). Age and the F1 driver - from teenage stars to fast 50-year-olds.

Formula 1® - The Official F1® Website.

Balfour, A. (2020, August 26). Who goes where? The 2021 Formula 1 driver market explained.

Retrieved from F1 Experiences.

Davies, J. (2020). Drivers. Retrieved from Chicane F1.

Diepraam, M. (2019, January 18). World Championship points systems. Retrieved from 6th

Gear Donaldson, G. (2020). Lewis Hamilton. Retrieved from Formula.

Gough, C. (2020, June 25). Number of TV viewers of Formula One (F1) racing worldwide from

2008-2019. Retrieved from Statista.

Jindal, S. (2020, August 16). F1 Car Cost: How much does an F1 Car Cost in 2020, Which

Formula 1 Team Spends Most? Retrieved from The SportsRush.

Lange, D. (2020, November 25). Revenue generated by the Formula One Group worldwide

from 2017 to 2019. Retrieved from Statista.

Mahehwari, D. V. (2018, January 23). Causal-comparative Research. Retrieved from Dr. V.K.

Maheshwari, Ph.D.

Marino, A., Aversa, P., Mesquita, L., & Anand, J. (2015). Driving Performance via Exploration

in Changing Environments: Evidence from Formula One Racing. Organization Science,

26(4), 1079-1100.
 24

Renken, Dieter. “Every F1 Salary Over The Past 20 Years.” RaceFans: Independent

Motorsport Coverage, 30 Mar. 2020.

Salkind, N. J. (2010). Causal-comparative design. In Encyclopedia of research design (Vol. 1, pp.

125-131). SAGE Publications, Inc.

Singh, Gurchetan. “Analysis Of Variance (ANOVA): Introduction, Types &

Techniques.” Analytics Vidhya, 15 Jan. 2018.

Smedley, R., Wise, C., Enkhbayar, D., Price, G., Cheng, R., & Yang, G. (2020, August 20).

The fastest driver in Formula 1. Retrieved from Amazon Web Services.

Tun, P. A., & Lachman, M. E. (2008). Age differences in reaction time and attention in a

national telephone sample of adults: Education, sex, and task complexity matter.

Developmental Psychology, 44(5), 1421-1429.

Vopani. (2020, December 14). Formula 1 World Championship (1950 - 2020): F1 race data

from 1950 to 2020. Retrieved from Kaggle.