Question

*More than 2 dependent samples*

Andrzejewski, Spencer, Kelley, and Berridge trained 8 rats in a signal detection procedure. That is, the rats had to respond on two levers (left or right) signifying whether they had just seen a tiny green light or not. Prior to test sessions, each of the rats was given a drug injection. The dependent variable was the percentage of trials in which they responded correctly.

	Drug
Rat	Saline	mg/kg Amphetamine	0.25 mg/kg Amphetamine	0.5 mg/kg Ritalin	1.0mg/kg Ritalin
1	84%	84%	84%	88%	88%
2	90%	90%	90%	88%	91%
3	84%	83%	94%	89%	89%
4	92%	92%	87%	94%	90%
5	92%	93%	97%	96%	92%
6	88%	78%	88%	90%	93%
7	88%	88%	94%	94%	94%
8	80%	82%	87%	83%	82%

            The researchers hypothesized that since amphetamine and Ritalin are used therapeutically to improve attention in humans, it might improve signal detection in rats. What would you conclude?

Answer 1

We can answer this using a paired t test as the same rats were used in a below and after setup

We enter the data in excel and then goto data > data analysis tab and select t test paired

lets perform the analysis for one variable and the same procedure can be applied to the remaining 3 variables as well

Hypothesis

H0 : signal detection is not improved due to 0.25mg/kp amphetamine
H1 : signal detection is significantly improved due to 0.25mg/kp amphetamine

we set the signficance level = 0.05

so we reject the null hypothesis if the p value of the 1 tail test is less than 0.05

as the p value is 0.07 , which is not less than 0.05 , hence we fail to reject the null hypothesis