In: Statistics and Probability
In 1974, Loftus and Palmer conducted a classic study demonstrating how the language used to ask a question can influence eyewitness memory. In the study, college students watched a film of an automobile accident and then were asked questions about what they saw. One group was asked, “About how fast were the cars going when they smashed into each other?” Another group was asked the same question except the verb was changed to “hit” instead of “smashed into.” The “smashed into” group reported significantly higher estimates of speed than the “hit” group. You, as a researcher wonder if Loftus and Palmer’s study is reliable, and repeats this study with a sample of FIU students and obtains the following data.
Hit Group |
Smashed Into Group |
|
32 |
50 |
|
26 |
44 |
|
40 |
54 |
|
23 |
45 |
|
42 |
44 |
|
20 |
40 |
|
37 |
49 |
|
25 |
34 |
|
24 |
38 |
|
22 |
30 |
|
19 |
50 |
|
24 |
46 |
|
19 |
40 |
|
22 |
35 |
|
29 |
43 |
|
24 |
41 |
|
34 |
30 |
|
33 |
39 |
|
37 |
44 |
|
20 |
35 |
Your job is to determine if smashed into group reports higher speed than hit group. As you work on this problem, make sure to provide information for each of the eight steps we cover in Chapter 11 (Salkind) as well as the APA write-up you would see in a results section.
Claim:smashed group has higher speed than hit group
Null and alternate hypothesis
H0:
H1:
The level of risk that means level of significance we take 5%
We use t test for two independent samples
Since =0.05
Degree of freedom = 38
t critical value =
Test statistics:
N1: 20
df1 = N - 1 = 20 - 1 = 19
M1: 27.6
SS1: 1024.8
s21 = SS1/(N - 1) = 1024.8/(20-1) =
53.94
For smashed group
N2: 20
df2 = N - 1 = 20 - 1 = 19
M2: 41.55
SS2: 838.95
s22 = SS2/(N - 1) = 838.95/(20-1) =
44.16
T-value Calculation
s2p = ((df1/(df1 +
df2)) * s21) + ((df2/(df2 +
df2)) * s22) = ((19/38) * 53.94) + ((19/38) *
44.16) = 49.05
s2M1 = s2p/N1 =
49.05/20 = 2.45
s2M2 = s2p/N2 =
49.05/20 = 2.45
t = (M1 - M2)/√(s2M1 +
s2M2) = -13.95/√4.9 = -6.3
Rejection region
R= {t:t<-1.686}
Decision
Since t=-6.3 <-1.6 so we rehte the null hypothesis .
So there sufficient evidence to conclude that the smashed group has higher speed than hit group.