Psych 230

Spring 2006

Jury study data

Gender and Ethnicity of the Sample. Highlighted cells are the ones you need to pay attention to.

Frequency Table

**GENDER**
		Frequency	Percent	Valid Percent	Cumulative Percent
Valid	Men	133	44.6	44.6	44.6
	Women	165	55.4	55.4	100.0
	Total	298	100.0	100.0

**Ethnicity**
		Frequency	Percent	Valid Percent	Cumulative Percent
Valid	Caucasian	170	57.0	59.4	59.4
	Black	21	7.0	7.3	66.8
	Hispanic	57	19.1	19.9	86.7
	Other	38	12.8	13.3	100.0
	Total	286	96.0	100.0
Missing	System	12	4.0
Total		298	100.0

Age range and mean

**Descriptive Statistics**
	N	Minimum	Maximum	Mean	Std. Deviation
AGE	298	18	73	26.23	9.579
Valid N (listwise)	298

Oneway analysis of variance (ANOVA) testing the differences among the mean guilt ratings of our eyewitness conditions. Note that the differences between groups are stastically significant, F(2, 295) = 9.36, p < .001.

**Descriptives: These are the means and standard deviations that were compared. The highlighted fields are to go in your table and figure**
VERDICT
	N	Mean	Std. Deviation	Std. Error	95% Confidence Interval for Mean		Minimum	Maximum
	N	Mean	Std. Deviation	Std. Error	Lower Bound	Upper Bound	Minimum	Maximum
No Witness	107	4.07	1.824	.176	3.72	4.41	1	7
Eyewitness	97	4.80	1.772	.180	4.45	5.16	1	7
Discredited witness	94	3.73	1.660	.171	3.39	4.07	1	7
Total	298	4.20	1.805	.105	4.00	4.41	1	7

**Test of Homogeneity of Variances: Since the result is nonsignificant, ignore this table**
VERDICT
Levene Statistic	df1	df2	Sig.
.420	2	295	.658

**ANOVA: This is the actual test with all the info you need to report the significance of the result.**
VERDICT
	Sum of Squares	df	Mean Square	F	Sig.
Between Groups	57.748	2	28.874	9.358	.000
Within Groups	910.171	295	3.085
Total	967.919	297

Post hoc Tukey tests; The ANOVA told us that overall the differences among group means were real, and not due to chance. The post hoc tests tell us HOW they differed. There are 3 comparisons: NW to EW, NW to DW, and NW to DW. The highlighted Sig column tells you if the means are significantly different or not.

**Multiple Comparisons**
Dependent Variable: VERDICT
Tukey HSD
		Mean Difference (I-J)	Std. Error	Sig.	95% Confidence Interval
(I) GROUP	(J) GROUP	Mean Difference (I-J)	Std. Error	Sig.	Lower Bound	Upper Bound
No Witness	Eyewitness	-.74(*)	.246	.008	-1.32	-.16
No Witness	Discredited witness	.33	.248	.377	-.25	.92
Eyewitness	No Witness	.74(*)	.246	.008	.16	1.32
Eyewitness	Discredited witness	1.07(*)	.254	.000	.47	1.67
Discredited witness	No Witness	-.33	.248	.377	-.92	.25
Discredited witness	Eyewitness	-1.07(*)	.254	.000	-1.67	-.47
* The mean difference is significant at the .05 level.

Graph

Bar of mean guilt ratings by eyewitness condition