"Taking this alpha level (a=0.1) into account, we perform a treatment comparison test (also referred as contrast test) for each measure. Table 8 shows the treatment means, standard error and replications for duration measure whereas Table 9 shows the same information for effort. There are several tests for performing treatment comparisons. These tests help us to analyze pairs of means to assess possible differences between means. Using Scheffé test [21] for treatment comparisons, Table 10 shows the treatment comparison with respect to duration."
"As shown in Table 10, there is a significant difference (at a=0.1) of 36 minutes in favor of pair programming (28% decrease in time). At a confidence interval of 95% this difference ranges between 6 and 66 minutes (4% to 51% decrease in time)."
"Table 11 shows the treatment comparison with respect to effort. As we see, there is a significant difference (at a=0.1) of 56 minutes in favor of solo programming (30% decrease in effort). At a confidence interval of 95% this difference ranges between 8 and 104 minutes (4% to 55% decrease in effort)."
An experiment used an alpha level of 0.1 to perform treatment (contrast) comparisons for duration and effort measures. Treatment means, standard errors, and replications were reported for duration (Table 8) and effort (Table 9). Multiple comparison methods were considered and the Scheffé test was used to compare pairs of means. Results indicate a significant 36-minute (28%) reduction in time for pair programming with a 95% confidence interval of 6 to 66 minutes (4% to 51%). Results also indicate a significant 56-minute (30%) reduction in effort for solo programming with a 95% confidence interval of 8 to 104 minutes (4% to 55%).
Read at Hackernoon
Unable to calculate read time
Collection
[
|
...
]