DSO 510 Project 1 Presentation Report

Data Cleaning and Processesing

raw_data = raw_data %>% filter(is.na(minutes) == FALSE)
raw_data %>% select(minutes) %>% summary()

##     minutes     
##  Min.   : 18.0  
##  1st Qu.: 80.0  
##  Median :104.0  
##  Mean   :110.8  
##  3rd Qu.:133.0  
##  Max.   :309.0

raw_data = raw_data %>% filter(is.na(winner_rank) == FALSE & is.na(winner_rank_points) == FALSE & is.na(loser_rank) == FALSE & is.na(loser_rank_points) == FALSE) 
raw_data %>% select(contains('rank')) %>% summary()

##   winner_rank     winner_rank_points   loser_rank      loser_rank_points
##  Min.   :  1.00   Min.   :   17      Min.   :   1.00   Min.   :    2.0  
##  1st Qu.: 19.00   1st Qu.:  716      1st Qu.:  34.00   1st Qu.:  591.2  
##  Median : 45.00   Median : 1023      Median :  61.00   Median :  871.5  
##  Mean   : 57.45   Mean   : 1779      Mean   :  79.48   Mean   : 1137.3  
##  3rd Qu.: 76.00   3rd Qu.: 1820      3rd Qu.:  96.75   3rd Qu.: 1243.0  
##  Max.   :503.00   Max.   :12415      Max.   :1491.00   Max.   :12355.0

## Parsing the score column into multiple columns ## 
raw_data %>% select(score) %>% head()

## # A tibble: 6 × 1
##   score         
##   <chr>         
## 1 6-4 3-6 6-2   
## 2 7-6(6) 6-2    
## 3 6-2 6-2       
## 4 6-4 7-6(2)    
## 5 6-7(2) 6-3 6-4
## 6 6-4 3-6 7-6(4)

raw_data %>% separate(score, into = c('first_set', 'second_set', 'third_set', 'fourth_set', 'fifth_set'),
                      sep = " ") %>% select(contains('set')) %>% head()

## # A tibble: 6 × 5
##   first_set second_set third_set fourth_set fifth_set
##   <chr>     <chr>      <chr>     <chr>      <chr>    
## 1 6-4       3-6        6-2       <NA>       <NA>     
## 2 7-6(6)    6-2        <NA>      <NA>       <NA>     
## 3 6-2       6-2        <NA>      <NA>       <NA>     
## 4 6-4       7-6(2)     <NA>      <NA>       <NA>     
## 5 6-7(2)    6-3        6-4       <NA>       <NA>     
## 6 6-4       3-6        7-6(4)    <NA>       <NA>

raw_data = raw_data %>% separate(score, into = c('first_set', 'second_set', 'third_set', 'fourth_set', 'fifth_set'),
                                 sep = " ")

#### Extracting Games from Sets #### 

# First Set
raw_data$first_sg1 = rep(NA,length(raw_data$first_set))
for (i in 1:length(raw_data$first_set)){
  raw_data$first_sg1[i] = str_split_fixed(raw_data$first_set, "-", n = 2)[i,1]
}

raw_data %>% select(first_sg1) %>% head()

## # A tibble: 6 × 1
##   first_sg1
##   <chr>    
## 1 6        
## 2 7        
## 3 6        
## 4 6        
## 5 6        
## 6 6

Data Analysis

Question 1: How does a match’s surface impact the average set length?

\(H_0\) = Match surface has no impact on the average set length

\(H_A\) = Match surface does have an impact on the average set length

M1 = lm(average_set_length ~ surface, data = data)

Regression Summary where Adj R-Squared Equals .01165
	Estimate	Std. Error	t value	Pr(>\|t\|)
(Intercept)	43.71895	0.30599	142.87511	0e+00
surfaceGrass	-3.06884	0.56502	-5.43144	0e+00
surfaceHard	-1.46960	0.37782	-3.88970	1e-04

M2 = aov(average_set_length ~ surface, data = data)

One-way ANOVA Summary
	Df	Sum Sq	Mean Sq	F value	Pr(>F)
surface	2	2296.459	1148.22969	16.157	1.1e-07
Residuals	2518	178946.745	71.06702	NA	NA

Tukey HSD Report for One-Way ANOVA
Term	Comparison	Estimate	Lower Bound	Upper Bound	Adj P-Value
surface	Grass-Clay	-3.068845	-4.3938557	-1.7438334	0.00000018
surface	Hard-Clay	-1.469595	-2.3556106	-0.5835802	0.00030317
surface	Hard-Grass	1.599249	0.3700932	2.8284051	0.00651235

Question 2: Does the hand combination between opponents impact match duration?

\(H_0\) = Hand combination has no impact on the match duration and/or average set length

\(H_A\) = Hand combination does impact the match duration and/or average set length

Match Duration by Hand Combination
	Best of 3 Set Matches				Best of 5 Set Matches
Hand Combination	Mean	Variance	StDev	Obs	Mean	Variance	StDev	Obs
LR	104.1327	967.3956	31.10298	226	155.2923	1775.273	42.13398	65
RR	101.4967	911.1103	30.18460	1524	157.4669	2347.862	48.45475	347
LL	101.2368	982.4018	31.34329	38	147.6667	1529.333	39.10669	3
RL	100.5369	1021.4595	31.96028	244	152.7162	2349.740	48.47412	74

One-Way ANOVA results for match duration from hand combination
	Best of 3 Set Matches					Best of 5 Set Matches
Term	DF	Sum Sq	Mean Sq	F Stat	P Value	DF	Sum Sq	Mean Sq	F Stat	P Value
hand_combo	3	1736.887	578.9623	0.6212855	0.6012237	3	1707.717	569.239	0.2508532	0.8607317
Residuals	2028	1889848.538	931.8780	NA	NA	485	1100567.522	2269.211	NA	NA

Tukey HSD Results from One-Way ANOVA for Hand Combination
	Best of 3 Set Matches					Best of 5 Set Matches
Comparison	Null Value	Estimate	Lower Bound	Upper Bound	Adj P-Value	Null Value	Estimate	Lower Bound	Upper Bound	Adj P-Value
LR-LL	0	2.8959013	-10.865576	16.657378	0.9489460	0	7.625641	-64.89319	80.14447	0.9930293
RL-LL	0	-0.6999569	-14.388176	12.988262	0.9991887	0	5.049550	-67.27446	77.37356	0.9979279
RR-LL	0	0.2598770	-12.630491	13.150246	0.9999500	0	9.800192	-61.40674	81.00713	0.9846743
RL-LR	0	-3.5958581	-10.842034	3.650318	0.5784185	0	-2.576091	-23.45215	18.29997	0.9888512
RR-LR	0	-2.6360242	-8.230784	2.958735	0.6196308	0	2.174551	-14.42288	18.77198	0.9867204
RR-RL	0	0.9598339	-4.452229	6.371897	0.9684699	0	4.750643	-10.97376	20.47504	0.8640336

Question 3: Does difference in ranking have any impact on match time?

\(H_0\) = The absolute value of player ranking distance has no negative impact on a match’s duration

\(H_A\) = The absolute value of player ranking distance negatively impacts a match’s duration

Regression for Match Duration (Minutes) from the Absolute Ranking Distance
	Best of 3-Set Matches				Best of 5-Set Matches
Term	Beta	SE	T-Stat	P-Value	Beta	SE	T-Stat	P-Value
(Intercept)	101.36111	0.86693	116.91923	0.00000	157.5944	2.75153	57.27509	0.00000
abs_ranking_distance	0.00568	0.00996	0.57018	0.56862	-0.0181	0.02599	-0.69648	0.48646

Question 4: Does the round of a tournament impact the match time?

\(H_0\) = The match round within a tournament has no impact on how long the match will take

\(H_A\) = The match round positively impacts how long the match will take

Regression for Match Duration (Minutes) against the Tournament Round
	Best of 3-Set Matches				Best of 5-Set Matches
Term	Beta	SE	T-Stat	P-Value	Beta	SE	T-Stat	P-Value
(Intercept)	103.90323	3.86056	26.91402	0.00000	150.87045	3.00017	50.28724	0.00000
roundR64	-0.45666	4.29311	-0.10637	0.91530	10.44360	5.23212	1.99606	0.04649
roundR32	-5.14452	4.00665	-1.28400	0.19929	10.08194	6.65514	1.51491	0.13045
roundR16	-1.45569	4.10885	-0.35428	0.72317	11.35536	8.98438	1.26390	0.20688
roundQF	2.35651	4.34789	0.54199	0.58789	7.99622	12.53867	0.63773	0.52396
roundSF	0.28165	4.76120	0.05915	0.95283	5.50455	16.93836	0.32498	0.74534
roundF	0.98566	5.43795	0.18126	0.85618	72.12955	23.76584	3.03501	0.00254

DSO 510 Project 1 Presentation Report

Kiran Krishnamurthi, Alice Xu, Ting Chu, Rheza Utama, Kaylee Chung

2/22/2022

Data Cleaning and Processesing

Data Analysis

Question 1: How does a match’s surface impact the average set length?

Question 2: Does the hand combination between opponents impact match duration?

Question 3: Does difference in ranking have any impact on match time?

Question 4: Does the round of a tournament impact the match time?