Creates a regresion table in APA style
apa.reg.table(..., filename = NA, table.number = NA, prop.var.conf.level = 0.95)
| ... | Regression (i.e., lm) result objects. Typically, one for each block in the regression. |
|---|---|
| filename | (optional) Output filename document filename (must end in .rtf or .doc only) |
| table.number | Integer to use in table number output line |
| prop.var.conf.level | Level of confidence (.90 or .95, default .95) for interval around sr2, R2, and Delta R2. Use of .90 confidence level helps to create consistency between the CI overlapping with zero and conclusions based on the p-value for that block (or block difference). |
APA table object
sr2 and delta R2 confidence intervals calculated via:
Alf Jr, E. F., & Graf, R. G. (1999). Asymptotic confidence limits for the difference between two squared multiple correlations: A simplified approach. Psychological Methods, 4(1), 70.
Note that Algina, Keselman, & Penfield (2008) found this approach can under some circumstances lead to inaccurate CIs on proportion of variance values. You might consider using the Algina, Keselman, & Penfield (2008) approach via the apa.reg.boot.table function
# View top few rows of goggles data set # from Discovering Statistics Using R head(album)#> adverts sales airplay attract #> 1 10.256 330 43 10 #> 2 985.685 120 28 7 #> 3 1445.563 360 35 7 #> 4 1188.193 270 33 7 #> 5 574.513 220 44 5 #> 6 568.954 170 19 5# Single block example blk1 <- lm(sales ~ adverts + airplay, data=album) apa.reg.table(blk1)#> #> #> Regression results using sales as the criterion #> #> #> Predictor b b_95%_CI beta beta_95%_CI sr2 sr2_95%_CI r #> (Intercept) 41.12** [22.72, 59.53] #> adverts 0.09** [0.07, 0.10] 0.52 [0.44, 0.61] .27 [.18, .36] .58** #> airplay 3.59** [3.02, 4.15] 0.55 [0.46, 0.63] .29 [.20, .38] .60** #> #> #> #> Fit #> #> #> #> R2 = .629** #> 95% CI[.55,.69] #> #> #> Note. A significant b-weight indicates the beta-weight and semi-partial correlation are also significant. #> b represents unstandardized regression weights. beta indicates the standardized regression weights. #> sr2 represents the semi-partial correlation squared. r represents the zero-order correlation. #> Square brackets are used to enclose the lower and upper limits of a confidence interval. #> * indicates p < .05. ** indicates p < .01. #> #>apa.reg.table(blk1,filename="exRegTable.doc")#> #> #> Regression results using sales as the criterion #> #> #> Predictor b b_95%_CI beta beta_95%_CI sr2 sr2_95%_CI r #> (Intercept) 41.12** [22.72, 59.53] #> adverts 0.09** [0.07, 0.10] 0.52 [0.44, 0.61] .27 [.18, .36] .58** #> airplay 3.59** [3.02, 4.15] 0.55 [0.46, 0.63] .29 [.20, .38] .60** #> #> #> #> Fit #> #> #> #> R2 = .629** #> 95% CI[.55,.69] #> #> #> Note. A significant b-weight indicates the beta-weight and semi-partial correlation are also significant. #> b represents unstandardized regression weights. beta indicates the standardized regression weights. #> sr2 represents the semi-partial correlation squared. r represents the zero-order correlation. #> Square brackets are used to enclose the lower and upper limits of a confidence interval. #> * indicates p < .05. ** indicates p < .01. #> #># Two block example, more than two blocks can be used blk1 <- lm(sales ~ adverts, data=album) blk2 <- lm(sales ~ adverts + airplay + attract, data=album) apa.reg.table(blk1,blk2,filename="exRegBlocksTable.doc")#> #> #> Regression results using sales as the criterion #> #> #> Predictor b b_95%_CI beta beta_95%_CI sr2 sr2_95%_CI r #> (Intercept) 134.14** [119.28, 149.00] #> adverts 0.10** [0.08, 0.12] 0.58 [0.46, 0.69] .33 [.23, .43] .58** #> #> #> #> (Intercept) -26.61 [-60.83, 7.60] #> adverts 0.08** [0.07, 0.10] 0.51 [0.43, 0.59] .26 [.17, .34] .58** #> airplay 3.37** [2.82, 3.92] 0.51 [0.43, 0.60] .25 [.17, .33] .60** #> attract 11.09** [6.28, 15.89] 0.19 [0.11, 0.27] .04 [.00, .07] .33** #> #> #> #> Fit Difference #> #> #> R2 = .335** #> 95% CI[.23,.43] #> #> #> #> #> #> R2 = .665** Delta R2 = .330** #> 95% CI[.59,.72] 95% CI[.24, .42] #> #> #> Note. A significant b-weight indicates the beta-weight and semi-partial correlation are also significant. #> b represents unstandardized regression weights. beta indicates the standardized regression weights. #> sr2 represents the semi-partial correlation squared. r represents the zero-order correlation. #> Square brackets are used to enclose the lower and upper limits of a confidence interval. #> * indicates p < .05. ** indicates p < .01. #> #># Interaction product-term test with blocks blk1 <- lm(sales ~ adverts + airplay, data=album) blk2 <- lm(sales ~ adverts + airplay + I(adverts * airplay), data=album) apa.reg.table(blk1,blk2,filename="exInteraction1.doc")#> #> #> Regression results using sales as the criterion #> #> #> Predictor b b_95%_CI beta beta_95%_CI sr2 #> (Intercept) 41.12** [22.72, 59.53] #> adverts 0.09** [0.07, 0.10] 0.52 [0.44, 0.61] .27 #> airplay 3.59** [3.02, 4.15] 0.55 [0.46, 0.63] .29 #> #> #> #> (Intercept) 28.30* [1.09, 55.50] #> adverts 0.11** [0.07, 0.16] 0.69 [0.42, 0.96] .05 #> airplay 4.02** [3.14, 4.91] 0.61 [0.48, 0.75] .15 #> I(adverts * airplay) -0.00 [-0.00, 0.00] -0.19 [-0.49, 0.11] .00 #> #> #> #> sr2_95%_CI r Fit Difference #> #> [.18, .36] .58** #> [.20, .38] .60** #> R2 = .629** #> 95% CI[.55,.69] #> #> #> [.01, .08] .58** #> [.08, .22] .60** #> [-.01, .01] #> R2 = .632** Delta R2 = .003 #> 95% CI[.55,.69] 95% CI[-.01, .01] #> #> #> Note. A significant b-weight indicates the beta-weight and semi-partial correlation are also significant. #> b represents unstandardized regression weights. beta indicates the standardized regression weights. #> sr2 represents the semi-partial correlation squared. r represents the zero-order correlation. #> Square brackets are used to enclose the lower and upper limits of a confidence interval. #> * indicates p < .05. ** indicates p < .01. #> #># Interaction product-term test with blocks and additional product terms blk1<-lm(sales ~ adverts + airplay, data=album) blk2<-lm(sales ~ adverts + airplay + I(adverts*adverts) + I(airplay*airplay), data=album) blk3<-lm(sales~adverts+airplay+I(adverts*adverts)+I(airplay*airplay)+I(adverts*airplay),data=album) apa.reg.table(blk1,blk2,blk3,filename="exInteraction2.doc")#> #> #> Regression results using sales as the criterion #> #> #> Predictor b b_95%_CI beta beta_95%_CI sr2 #> (Intercept) 41.12** [22.72, 59.53] #> adverts 0.09** [0.07, 0.10] 0.52 [0.44, 0.61] .27 #> airplay 3.59** [3.02, 4.15] 0.55 [0.46, 0.63] .29 #> #> #> #> (Intercept) 48.77** [19.73, 77.82] #> adverts 0.10** [0.05, 0.14] 0.58 [0.33, 0.83] .04 #> airplay 2.65** [0.67, 4.63] 0.40 [0.10, 0.70] .01 #> I(adverts * adverts) -0.00 [-0.00, 0.00] -0.05 [-0.31, 0.20] .00 #> I(airplay * airplay) 0.02 [-0.02, 0.05] 0.15 [-0.15, 0.45] .00 #> #> #> #> (Intercept) 37.30* [2.84, 71.77] #> adverts 0.12** [0.06, 0.18] 0.72 [0.38, 1.06] .03 #> airplay 3.07** [0.98, 5.15] 0.47 [0.15, 0.78] .02 #> I(adverts * adverts) -0.00 [-0.00, 0.00] -0.03 [-0.29, 0.23] .00 #> I(airplay * airplay) 0.02 [-0.02, 0.05] 0.15 [-0.15, 0.45] .00 #> I(adverts * airplay) -0.00 [-0.00, 0.00] -0.19 [-0.49, 0.12] .00 #> #> #> #> sr2_95%_CI r Fit Difference #> #> [.18, .36] .58** #> [.20, .38] .60** #> R2 = .629** #> 95% CI[.55,.69] #> #> #> [.01, .07] .58** #> [-.01, .03] .60** #> [-.00, .00] #> [-.01, .01] #> R2 = .631** Delta R2 = .002 #> 95% CI[.55,.69] 95% CI[-.01, .01] #> #> #> [.00, .06] .58** #> [-.01, .04] .60** #> [-.00, .00] #> [-.01, .01] #> [-.01, .01] #> R2 = .634** Delta R2 = .003 #> 95% CI[.55,.69] 95% CI[-.01, .01] #> #> #> Note. A significant b-weight indicates the beta-weight and semi-partial correlation are also significant. #> b represents unstandardized regression weights. beta indicates the standardized regression weights. #> sr2 represents the semi-partial correlation squared. r represents the zero-order correlation. #> Square brackets are used to enclose the lower and upper limits of a confidence interval. #> * indicates p < .05. ** indicates p < .01. #> #>#Interaction product-term test with single regression (i.e., semi-partial correlation focus) blk1 <- lm(sales ~ adverts + airplay + I(adverts * airplay), data=album) apa.reg.table(blk1,filename="exInteraction3.doc")#> #> #> Regression results using sales as the criterion #> #> #> Predictor b b_95%_CI beta beta_95%_CI sr2 sr2_95%_CI #> (Intercept) 28.30* [1.09, 55.50] #> adverts 0.11** [0.07, 0.16] 0.69 [0.42, 0.96] .05 [.01, .08] #> airplay 4.02** [3.14, 4.91] 0.61 [0.48, 0.75] .15 [.08, .22] #> I(adverts * airplay) -0.00 [-0.00, 0.00] -0.19 [-0.49, 0.11] .00 [-.01, .01] #> #> #> #> r Fit #> #> .58** #> .60** #> #> R2 = .632** #> 95% CI[.55,.69] #> #> #> Note. A significant b-weight indicates the beta-weight and semi-partial correlation are also significant. #> b represents unstandardized regression weights. beta indicates the standardized regression weights. #> sr2 represents the semi-partial correlation squared. r represents the zero-order correlation. #> Square brackets are used to enclose the lower and upper limits of a confidence interval. #> * indicates p < .05. ** indicates p < .01. #> #>