Advance Data – Pricing of Players in the Indian Premier League
Essay Preview: Advance Data – Pricing of Players in the Indian Premier League
Report this essay
Advance Data AnalysisASSIGNMENT: PRICING OF PLAYERS IN THE INDIAN PREMIER LEAGUE[pic 1] Submitted to – Submitted by- Dr. Shailja Rego Vikas Garg D023, Group 1ObjectiveTo recognise selling price of a cricket player in IPL depends upon which variables. Find out the relationship between selling price and these identified variables and review the effectiveness of the above relationship through multiple coefficient of determination.ProcedureMultiple Regression Analysis (MRA) was used to attain the relationship and measure its effectiveness. The following steps were taken for thisStep1: To modify the data and identify the dependent variable and the independent variables in the data. Dependent variable: SQRT(S-B) where S = Sold price and Base Price = Base PriceIndependent variables: Auction year, MTS, B25-35, BOW*SR-BL, AUSTRALIA, BAT, CAPTAINCY EXP, TEAM, BOW*T-WKTS, L25, BOW*ODI-SR-BL, INDIA, BAT*SIXERS T20, BAT*T-RUNS, BOW*WICKETS, BOW*ODI-WKTS, BAT*ODI-SR-B, BOW*ECO, BAT*HS T20, BAT*ODI-RUNS-S, BOW, BAT*AVE T20, BAT*SR -B T20, BOW*RUNS-C, BAT*RUN T20, BOW*AVE-BL Step 2:As Regression can be done when both dependent and independent variables are quantitative. So, all the variables which were qualitative are converted to quantitative variables by using dummy. Auction_year was also converted to quantitative by assuming year 2008 as 1, 2009 as 2 and 2011 as 3. Step 3:Perform regression on the dataThe output of Regression is as follows-Model SummarybModelRR SquareAdjusted R SquareStd. Error of the EstimateChange StatisticsDurbin-WatsonR Square ChangeF Changedf1df2Sig. F Change1.723a.523.402266.40448.5234.33626103.0001.873Interpretation: R square is 0.402 which is low for the model, cannot use this model Durbin Watson statistics is 1.873 which is in the range of 1.5 to 2.5. Therefore we can say that there is no autocorrelation.
ANOVAaModelSum of SquaresdfMean SquareFSig.1Regression8000823.29126307723.9734.336.000bResidual7310048.47810370971.344 Total15310871.769129 a. Dependent Variable: SQRT(S-B)b. Predictors: (Constant), Auction_year, MTS, B25-35, BOW*SR-BL, AUSTRALIA, BAT, CAPTAINCY EXP, TEAM, BOW*T-WKTS, L25, BOW*ODI-SR-BL, INDIA, BAT*SIXERS T20, BAT*T-RUNS, BOW*WICKETS, BOW*ODI-WKTS, BAT*ODI-SR-B, BOW*ECO, BAT*HS T20, BAT*ODI-RUNS-S, BOW, BAT*AVE T20, BAT*SR -B T20, BOW*RUNS-C, BAT*RUN T20, BOW*AVE-BLInterpretation:We can use above ANOVA table for checking whether the model is significant or not. As we can see the of sig. is .000 which is less than 0.05. Hence, the overall model is significant..000 < 0.05Step 4:One-Way ANOVA was used to check the significance of every dummy variable with the dependant variable. Post hoc analysis is also been done to check significance difference between samples. AGEANOVASQRT(S-B) Sum of SquaresdfMean SquareFSig.Between Groups970108.3702485054.1854.296.016Within Groups14340763.399127112919.397Total15310871.769129Multiple ComparisonsDependent Variable: SQRT(S-B) LSD (I) AGE(J) AGEMean Difference (I-J)Std. ErrorSig.95% Confidence IntervalLower BoundUpper Bound1.02.0249.496410881896850*91.490319404594350.00768.453579607923020430.5392421558707003.0287.391895046364370*105.310483352013210.00779.001453380448200495.7823367122805402.01.0-249.496410881896850*91.490319404594350.007-430.539242155870700-68.4535796079230203.037.89548416446752073.115332480327820.605-106.786564033866430182.5775323628014603.01.0-287.391895046364370*105.310483352013210.007-495.782336712280540-79.0014533804482002.0-37.89548416446752073.115332480327820.605-182.577532362801460106.786564033866430*. The mean difference is significant at the 0.05 level.