Example Problem

A training manager believes that a new interactive computer-based training package will help improve the production rate of order assemblers. She arranges for a production area of 21 experienced employees to complete the new training package over a 6 week period. Another group from the production area of 23 employees received no additional training. Following are the average production rates per person per hour based on a 12 week period following the training.

[Download Data]

Training Group Control Group
26 44
45 45
60 57
73 28
45 64
51 39
63 35
46 43
69 21
51 56
55 22
58 87
61 48
54 12
64 19
56 62
59 55
35 44
48 39
45 44
59 57


Recommendations: Before following these steps, screen your data for outliers and normality.

Data Editor

Two variables in dataset--productivity (dependent variable) and training variable (independent variable). Should like something like this:

Running Analysis

Move dependent variable to top box (i.e., Test Variable(s)) and independent variable to lower box (i.e., Grouping Variable).

Define Groups

Indicate which two groups you want to include in the analysis. In my example I coded the training group as 1 and the control group as 2. Yours may be different. We only have two groups in this dataset.


Descriptive statistics by group.

Independent t-test results

Writing Up Results



Table 1 presents the means and standard deviations by group. The results show that the order assemblers in the training group produced about 10 more assemblies per person per hour (M = 53.48) than the assemblers in the control group (M = 43.52). Also, the employees in the training group had more homogeneous production rates (SD = 11.01) than the employees in the control group (SD = 17.15).

Since the measurements in the training group and control group were unrelated to each other, an independent t-test was performed. The assumption of homogeneous variances was satisfied (Levene’s test, F = 2.36, p = .132). The mean score for the training group was significantly higher than the mean score for the control group, t = (.05, 42) = 2.27, p = .029. There was a large difference between the training and control groups (g=.71).

Table 1

Mean Assemblies Per Person Per Hours and Standard Deviations


Group Mean SD
Control 43.52 17.15
Training 53.48 11.01



The new computer-based training package used with the training group had a significant and positive effect on production rates. Therefore, it is appropriate for management to consider providing the new training to employees in all the assembly areas.