Organizing the Data
GLSS <- subset(game, game$original == 1) #original data
aksoy <- subset(game, game$original == 0) #paper data
#splitting data
GLSS.p0 <- subset(GLSS, GLSS$first_mover==1)#first
GLSS.p1 <- subset(GLSS, GLSS$first_mover==0)#second
aksoy.p0 <- subset(aksoy, aksoy$first_mover == 1)#first
aksoy.p1 <- subset(aksoy, aksoy$first_mover == 0)#secondFor this table I am creating subsets than calculating the mean
First_mover_GLSS <- t.test(GLSS$amountsent_percentage)
First_mover_Aksoy <- t.test(aksoy$amountsent_percentage)
Return_Ratio_GLSS <- t.test(GLSS$returnratio)
Return_Ratio_Aksoy <- t.test(aksoy$returnratio)
First_mover_GLSS##
## One Sample t-test
##
## data: GLSS$amountsent_percentage
## t = 38.394, df = 185, p-value < 2.2e-16
## alternative hypothesis: true mean is not equal to 0
## 95 percent confidence interval:
## 0.7908526 0.8765309
## sample estimates:
## mean of x
## 0.8336918First_mover_Aksoy##
## One Sample t-test
##
## data: aksoy$amountsent_percentage
## t = 18.51, df = 65, p-value < 2.2e-16
## alternative hypothesis: true mean is not equal to 0
## 95 percent confidence interval:
## 0.6406938 0.7956698
## sample estimates:
## mean of x
## 0.7181818Return_Ratio_GLSS##
## One Sample t-test
##
## data: GLSS$returnratio
## t = 23.651, df = 178, p-value < 2.2e-16
## alternative hypothesis: true mean is not equal to 0
## 95 percent confidence interval:
## 0.4154105 0.4910443
## sample estimates:
## mean of x
## 0.4532274Return_Ratio_Aksoy##
## One Sample t-test
##
## data: aksoy$returnratio
## t = 21.991, df = 65, p-value < 2.2e-16
## alternative hypothesis: true mean is not equal to 0
## 95 percent confidence interval:
## 0.500270 0.600211
## sample estimates:
## mean of x
## 0.5502405(cbind(rbind("%Sent (Firstr Mover)", GLSS=First_mover_GLSS[5],Aksoy=First_mover_Aksoy[5]), rbind("Return Ratio", Return_Ratio_GLSS[5],Return_Ratio_Aksoy[5])))## estimate estimate
## "%Sent (Firstr Mover)" "Return Ratio"
## GLSS 0.8336918 0.4532274
## Aksoy 0.7181818 0.5502405GLSS First Mover
fit.1 <- lm(amount_sent~different_sex+promise+male+white+freshmen+only_child+gss_trust, data = GLSS.p0) # First mover
summary(fit.1)##
## Call:
## lm(formula = amount_sent ~ different_sex + promise + male + white +
## freshmen + only_child + gss_trust, data = GLSS.p0)
##
## Residuals:
## Min 1Q Median 3Q Max
## -12.742 -1.781 2.087 2.607 4.500
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 13.26580 1.27780 10.382 <2e-16 ***
## different_sex -0.77710 1.10188 -0.705 0.483
## promise 0.02709 1.00677 0.027 0.979
## male -0.07384 1.16649 -0.063 0.950
## white -0.45161 0.99957 -0.452 0.653
## freshmen -0.21787 1.10534 -0.197 0.844
## only_child -1.72370 1.50539 -1.145 0.255
## gss_trust 0.14608 1.00309 0.146 0.885
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 4.705 on 87 degrees of freedom
## (2 observations deleted due to missingness)
## Multiple R-squared: 0.02511, Adjusted R-squared: -0.05333
## F-statistic: 0.3201 on 7 and 87 DF, p-value: 0.9431GLSS First Mover
fit.2 <- lm(amount_sent~different_sex+promise+male+white+freshmen+only_child+trust_index,GLSS.p0)
summary(fit.2)##
## Call:
## lm(formula = amount_sent ~ different_sex + promise + male + white +
## freshmen + only_child + trust_index, data = GLSS.p0)
##
## Residuals:
## Min 1Q Median 3Q Max
## -12.451 -1.848 2.027 2.665 4.697
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 13.7911 1.2556 10.983 <2e-16 ***
## different_sex -0.2306 1.0812 -0.213 0.832
## promise -0.1068 0.9966 -0.107 0.915
## male -0.5412 1.1424 -0.474 0.637
## white -0.7418 0.9956 -0.745 0.458
## freshmen -0.4785 1.0929 -0.438 0.663
## only_child -1.8019 1.4501 -1.243 0.217
## trust_index -0.1020 0.2178 -0.468 0.641
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 4.554 on 84 degrees of freedom
## (5 observations deleted due to missingness)
## Multiple R-squared: 0.03699, Adjusted R-squared: -0.04326
## F-statistic: 0.4609 on 7 and 84 DF, p-value: 0.8601Aksoy First Mover
fit.3 <- lm(amount_sent~different_sex+promise+male+white+freshmen+only_child+gss_trust, data = aksoy.p0) # First mover
summary(fit.3)##
## Call:
## lm(formula = amount_sent ~ different_sex + promise + male + white +
## freshmen + only_child + gss_trust, data = aksoy.p0)
##
## Residuals:
## Min 1Q Median 3Q Max
## -5.4417 -2.2264 0.5389 1.7906 4.0093
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 4.46109 1.38253 3.227 0.00348 **
## different_sex 3.49516 1.02726 3.402 0.00225 **
## promise -0.02852 1.03888 -0.027 0.97832
## male 0.51395 0.96854 0.531 0.60035
## white -0.72014 1.06244 -0.678 0.50411
## freshmen -2.04101 1.55877 -1.309 0.20231
## only_child 0.28164 1.03102 0.273 0.78697
## gss_trust 2.71114 1.10432 2.455 0.02139 *
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 2.693 on 25 degrees of freedom
## Multiple R-squared: 0.4386, Adjusted R-squared: 0.2814
## F-statistic: 2.79 on 7 and 25 DF, p-value: 0.02732Aksoy Second Mover
fit.4 <- lm(amount_sent~different_sex+promise+male+white+freshmen+only_child+trust_index, data= aksoy.p0)
summary(fit.4)##
## Call:
## lm(formula = amount_sent ~ different_sex + promise + male + white +
## freshmen + only_child + trust_index, data = aksoy.p0)
##
## Residuals:
## Min 1Q Median 3Q Max
## -5.8125 -1.8468 0.5269 2.0264 4.3967
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 5.9032 1.2884 4.582 0.00011 ***
## different_sex 3.1710 1.0501 3.020 0.00576 **
## promise -0.4530 1.0615 -0.427 0.67318
## male 0.3912 1.0079 0.388 0.70122
## white -0.3580 1.0823 -0.331 0.74359
## freshmen -2.1396 1.6255 -1.316 0.20002
## only_child -0.2638 1.0691 -0.247 0.80708
## trust_index -0.4497 0.2404 -1.870 0.07323 .
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 2.81 on 25 degrees of freedom
## Multiple R-squared: 0.3888, Adjusted R-squared: 0.2176
## F-statistic: 2.272 on 7 and 25 DF, p-value: 0.06179Show the results
stargazer(fit.1, fit.2,fit.3,fit.4, title="Regression Results: GLSS and Aksoy", type="text", df=FALSE, digits=4, column.labels = c("fit1", "fit2","fit3", "fit4"))##
## Regression Results: GLSS and Aksoy
## =============================================================
## Dependent variable:
## -----------------------------------------
## amount_sent
## fit1 fit2 fit3 fit4
## (1) (2) (3) (4)
## -------------------------------------------------------------
## different_sex -0.7771 -0.2306 3.4952*** 3.1710***
## (1.1019) (1.0812) (1.0273) (1.0501)
##
## promise 0.0271 -0.1068 -0.0285 -0.4530
## (1.0068) (0.9966) (1.0389) (1.0615)
##
## male -0.0738 -0.5412 0.5140 0.3912
## (1.1665) (1.1424) (0.9685) (1.0079)
##
## white -0.4516 -0.7418 -0.7201 -0.3580
## (0.9996) (0.9956) (1.0624) (1.0823)
##
## freshmen -0.2179 -0.4785 -2.0410 -2.1396
## (1.1053) (1.0929) (1.5588) (1.6255)
##
## only_child -1.7237 -1.8019 0.2816 -0.2638
## (1.5054) (1.4501) (1.0310) (1.0691)
##
## gss_trust 0.1461 2.7111**
## (1.0031) (1.1043)
##
## trust_index -0.1020 -0.4497*
## (0.2178) (0.2404)
##
## Constant 13.2658*** 13.7911*** 4.4611*** 5.9032***
## (1.2778) (1.2556) (1.3825) (1.2884)
##
## -------------------------------------------------------------
## Observations 95 92 33 33
## R2 0.0251 0.0370 0.4386 0.3888
## Adjusted R2 -0.0533 -0.0433 0.2814 0.2176
## Residual Std. Error 4.7054 4.5535 2.6928 2.8098
## F Statistic 0.3201 0.4609 2.7904** 2.2717*
## =============================================================
## Note: *p<0.1; **p<0.05; ***p<0.01GLSS Column 1
fit.1a <- lm(returnratio~amount_sent+different_sex+promise+male+white+freshmen+only_child+gss_trust, data = GLSS.p1) # Second mover
summary(fit.1a)##
## Call:
## lm(formula = returnratio ~ amount_sent + different_sex + promise +
## male + white + freshmen + only_child + gss_trust, data = GLSS.p1)
##
## Residuals:
## Min 1Q Median 3Q Max
## -0.51476 -0.07475 -0.00879 0.08016 0.59326
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 0.137228 0.118820 1.155 0.2517
## amount_sent 0.021603 0.006749 3.201 0.0020 **
## different_sex 0.014642 0.052468 0.279 0.7810
## promise -0.005965 0.051026 -0.117 0.9073
## male -0.002652 0.056821 -0.047 0.9629
## white 0.053476 0.052117 1.026 0.3081
## freshmen -0.038780 0.053504 -0.725 0.4708
## only_child -0.190102 0.093924 -2.024 0.0465 *
## gss_trust 0.092083 0.050394 1.827 0.0716 .
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.2238 on 76 degrees of freedom
## (7 observations deleted due to missingness)
## Multiple R-squared: 0.221, Adjusted R-squared: 0.139
## F-statistic: 2.695 on 8 and 76 DF, p-value: 0.01152GLSS Column 2
fit.1b <- lm(returnratio~amount_sent+different_sex+promise+male+white+freshmen+only_child+trust_index, data = GLSS.p1) # Second mover
summary(fit.1b)##
## Call:
## lm(formula = returnratio ~ amount_sent + different_sex + promise +
## male + white + freshmen + only_child + trust_index, data = GLSS.p1)
##
## Residuals:
## Min 1Q Median 3Q Max
## -0.44411 -0.10688 -0.01959 0.10497 0.52733
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 0.153911 0.115165 1.336 0.185502
## amount_sent 0.021462 0.006423 3.341 0.001309 **
## different_sex 0.002106 0.050357 0.042 0.966755
## promise 0.033750 0.049982 0.675 0.501619
## male -0.024521 0.054808 -0.447 0.655887
## white 0.050668 0.050120 1.011 0.315336
## freshmen -0.006235 0.052931 -0.118 0.906551
## only_child -0.218396 0.089233 -2.447 0.016758 *
## trust_index 0.044018 0.011826 3.722 0.000383 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.2123 on 74 degrees of freedom
## (9 observations deleted due to missingness)
## Multiple R-squared: 0.3098, Adjusted R-squared: 0.2352
## F-statistic: 4.152 on 8 and 74 DF, p-value: 0.000387Aksoy Column 1
fit.1c <- lm(returnratio~amount_sent+different_sex+promise+male+white+freshmen+only_child+gss_trust, data = aksoy.p1) # Second mover
summary(fit.1c)##
## Call:
## lm(formula = returnratio ~ amount_sent + different_sex + promise +
## male + white + freshmen + only_child + gss_trust, data = aksoy.p1)
##
## Residuals:
## Min 1Q Median 3Q Max
## -0.42137 -0.11860 -0.00781 0.14291 0.30424
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 0.67567 0.14639 4.616 0.00011 ***
## amount_sent 0.01581 0.01412 1.119 0.27409
## different_sex -0.13798 0.08284 -1.666 0.10879
## promise -0.01791 0.07229 -0.248 0.80643
## male -0.05925 0.07578 -0.782 0.44194
## white -0.06306 0.08048 -0.784 0.44100
## freshmen 0.03174 0.11280 0.281 0.78086
## only_child -0.12011 0.07699 -1.560 0.13184
## gss_trust -0.10001 0.07555 -1.324 0.19806
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.1986 on 24 degrees of freedom
## Multiple R-squared: 0.2953, Adjusted R-squared: 0.06037
## F-statistic: 1.257 on 8 and 24 DF, p-value: 0.3108Aksoy Column 2
fit.1d <- lm(returnratio~amount_sent+different_sex+promise+male+white+freshmen+only_child+trust_index, data = aksoy.p1) # Second mover
summary(fit.1d)##
## Call:
## lm(formula = returnratio ~ amount_sent + different_sex + promise +
## male + white + freshmen + only_child + trust_index, data = aksoy.p1)
##
## Residuals:
## Min 1Q Median 3Q Max
## -0.3696 -0.1020 0.0012 0.1378 0.3511
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 0.5948919 0.1401147 4.246 0.000283 ***
## amount_sent 0.0193898 0.0144708 1.340 0.192818
## different_sex -0.1464638 0.0855152 -1.713 0.099656 .
## promise -0.0008651 0.0760808 -0.011 0.991021
## male -0.0414877 0.0773400 -0.536 0.596597
## white -0.0677037 0.0841920 -0.804 0.429199
## freshmen 0.0300685 0.1178582 0.255 0.800801
## only_child -0.1092021 0.0794215 -1.375 0.181842
## trust_index 0.0026872 0.0177068 0.152 0.880644
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.2056 on 24 degrees of freedom
## Multiple R-squared: 0.2445, Adjusted R-squared: -0.007274
## F-statistic: 0.9711 on 8 and 24 DF, p-value: 0.4811stargazer(fit.1a, fit.1b,fit.1c,fit.1d, title="Regression Results: GLSS and Aksoy", type="text", df=FALSE, digits=5, column.labels = c("fit1", "fit2","fit3", "fit4"))##
## Regression Results: GLSS and Aksoy
## ===============================================================
## Dependent variable:
## -------------------------------------------
## returnratio
## fit1 fit2 fit3 fit4
## (1) (2) (3) (4)
## ---------------------------------------------------------------
## amount_sent 0.02160*** 0.02146*** 0.01581 0.01939
## (0.00675) (0.00642) (0.01412) (0.01447)
##
## different_sex 0.01464 0.00211 -0.13798 -0.14646*
## (0.05247) (0.05036) (0.08284) (0.08552)
##
## promise -0.00596 0.03375 -0.01791 -0.00087
## (0.05103) (0.04998) (0.07229) (0.07608)
##
## male -0.00265 -0.02452 -0.05925 -0.04149
## (0.05682) (0.05481) (0.07578) (0.07734)
##
## white 0.05348 0.05067 -0.06306 -0.06770
## (0.05212) (0.05012) (0.08048) (0.08419)
##
## freshmen -0.03878 -0.00623 0.03174 0.03007
## (0.05350) (0.05293) (0.11280) (0.11786)
##
## only_child -0.19010** -0.21840** -0.12011 -0.10920
## (0.09392) (0.08923) (0.07699) (0.07942)
##
## gss_trust 0.09208* -0.10001
## (0.05039) (0.07555)
##
## trust_index 0.04402*** 0.00269
## (0.01183) (0.01771)
##
## Constant 0.13723 0.15391 0.67567*** 0.59489***
## (0.11882) (0.11517) (0.14639) (0.14011)
##
## ---------------------------------------------------------------
## Observations 85 83 33 33
## R2 0.22097 0.30982 0.29527 0.24454
## Adjusted R2 0.13897 0.23521 0.06037 -0.00727
## Residual Std. Error 0.22380 0.21226 0.19857 0.20560
## F Statistic 2.69470** 4.15237*** 1.25697 0.97111
## ===============================================================
## Note: *p<0.1; **p<0.05; ***p<0.01