I'm a bit puzzled which role programmer ability has in this experiment. What strikes me is the enormous spread in programmer quality within each group. Varying from 0.7 to 15 hours for the scanner assignment and 50% to 100% of succeeded test cases. The spread occurs over both groups.
That programmer quality shows way stronger effects than the measured effect of a typing system would suggest to me that
- the measurement was flawed?
- programmer ability beats language choice by orders of magnitude?
That programmer ability beats language choice by orders of magnitude, is already a familiar fact, so that would seem a satisfactory explanation for the observed variance.
That programmer quality shows way stronger effects than the measured effect of a typing system would suggest to me that
- the measurement was flawed?
- programmer ability beats language choice by orders of magnitude?
Or do I make a category error here?