Results

Scatterplot

Descriptives, of basic variables.

Descriptives
		Choice
N		3900
Missing		0
Mean
Median
Standard deviation
Minimum
Maximum

Frequencies

Frequencies of Choice
Levels	Counts	% of Total	Cumulative %
non-purchase	3296	84.5 %	84.5 %
purchase	604	15.5 %	100.0 %

Binomial Logistic Regression

Model Fit Measures
Model	Deviance	AIC	BIC	R²_McF
1	3048	3062	3106	0.0934

Model Coefficients - Choice
						95% Confidence Interval
Predictor	Estimate	SE	Z	p	Odds ratio	Lower	Upper
Intercept	-2.36	0.114	-20.7664	< .001	0.0945	0.0757	0.118
Amount_Purchased	4.25e-4	4.96e-4	0.8575	0.391	1.0004	0.9995	1.001
P_Art:
1 – 0	1.21	0.103	11.7795	< .001	3.3653	2.7500	4.118
2 – 0	2.02	0.163	12.3499	< .001	7.5204	5.4599	10.359
3 – 0	2.62	0.296	8.8535	< .001	13.7189	7.6832	24.496
4 – 0	2.94	0.711	4.1289	< .001	18.8615	4.6781	76.048
5 – 0	14.86	324.744	0.0458	0.964	2.83e+6	1.07e-270	7.49e+282
Note. Estimates represent the log odds of "Choice = purchase" vs. "Choice = non-purchase"

Prediction

Classification Table – Choice
	Predicted
Observed	non-purchase	purchase	% Correct
non-purchase	3272	24	99.3
purchase	566	38	6.29
Note. The cut-off value is set to 0.5

Predictive Measures
Specificity	Sensitivity	AUC
0.993	0.0629	0.696
Note. The cut-off value is set to 0.5

ROC Curve

[3]

Contingency Tables

The table below indicates that purchase percentage tends to increase as P_Art increases. This is statistically significant.

mean(Amount_Purchased)

Contingency Tables
		P_Art
Choice		0	1	2	3	4	5	Total
non-purchase	% within column	90.7 %	74.1 %	55.7 %	40.4 %	33.3 %	0.0 %	84.5 %
purchase	% within column	9.3 %	25.9 %	44.3 %	59.6 %	66.7 %	100.0 %	15.5 %
Total	% within column	100.0 %	100.0 %	100.0 %	100.0 %	100.0 %	100.0 %	100.0 %

χ² Tests
	Value	df	p
χ²	377	5	< .001
N	3900

Plots

Independent Samples T-Test

Independent Samples T-Test
		Statistic	df	p		Effect Size
Amount_Purchased	Student's t	-5.71	3898	< .001	Cohen's d	-0.253
	Welch's t	-5.62	828	< .001	Cohen's d	-0.251

Assumptions

Normality Test (Shapiro-Wilk)
	W	p
Amount_Purchased	0.985	< .001
Note. A low p-value suggests a violation of the assumption of normality

Homogeneity of Variances Test (Levene's)
	F	df	df2	p
Amount_Purchased	0.0245	1	3898	0.876
Note. A low p-value suggests a violation of the assumption of equal variances

[4]

Group Descriptives
	Group	N	Mean	Median	SD	SE
Amount_Purchased	non-purchase	3296	194	195	95.0	1.66
	purchase	604	218	228	97.3	3.96

Plots

Amount_Purchased

Correlation

	Pearson's product-moment correlation

data:  x and y
t = 19, df = 3898, p-value <2e-16
alternative hypothesis: true correlation is not equal to 0
95 percent confidence interval:
 0.2639 0.3213
sample estimates:
   cor 
0.2929

R

[1] NA

Box & Violin Plots

Plots

Amount_Purchased

Robust Independent Samples T-Test

Robust Independent Samples T-Test
		t	df	p	Mean diff
Amount_Purchased	Yuen's test	5.69	521	< .001	-28.2
	Yuen's bootstrapped	-5.68		< .001

Generalized Linear Models

Model Info
Info	Value	Comment
Model Type	Logistic	Model for binary y
Call	glm	Choice ~ 1 + Gender
Link function	Logit	Log of the odd of y=1 over y=0
Direction	P(y=1)/P(y=0)	P( Choice = purchase ) / P( Choice = non-purchase )
Distribution	Binomial	Dichotomous event distribution of y
R-squared	0.0178	Proportion of reduction of error
AIC	3306.4010	Less is better
BIC	3318.9390	Less is better
Deviance	3302.4014	Less is better
Residual DF	3898
Chi-squared/DF	1.0005	Overdispersion indicator
Converged	yes	Whether the estimation found a solution

[5]

Model Results

Loglikelihood ratio tests
	X²	df	p
Gender	59.9	1	< .001

Parameter Estimates
					95% Exp(B) Confidence Interval
Names	Effect	Estimate	SE	exp(B)	Lower	Upper	z	p
(Intercept)	(Intercept)	-1.612	0.0450	0.200	0.183	0.218	-35.81	< .001
Gender1	Male - Female	-0.704	0.0900	0.495	0.415	0.590	-7.82	< .001

Post Hoc Tests

Post Hoc Comparisons - Gender
Comparison
Gender		Gender	exp(B)	SE	z	p_bonferroni
Female	-	Male	2.02	0.182	7.82	< .001

Plots

References

[1] The jamovi project (2021). jamovi. (Version 1.8) [Computer Software]. Retrieved from https://www.jamovi.org.

[2] R Core Team (2021). R: A Language and environment for statistical computing. (Version 4.0) [Computer software]. Retrieved from https://cran.r-project.org. (R packages retrieved from MRAN snapshot 2021-04-01).

[3] Sing, T., Sander, O., Beerenwinkel, N., & Lengauer, T. (2015). ROCR: Visualizing the Performance of Scoring Classifiers. [R package]. Retrieved from https://cran.r-project.org/package=ROCR.

[4] Fox, J., & Weisberg, S. (2020). car: Companion to Applied Regression. [R package]. Retrieved from https://cran.r-project.org/package=car.

[5] Gallucci, M. (2019). GAMLj: General analyses for linear models. [jamovi module]. Retrieved from https://gamlj.github.io/.