164 Experimental Zoology 
stamens and pistils are supposed to have varied much in length, 
and to be still varying, it might well happen that they could be 
reduced much more easily through natural selection into two sets 
of different lengths in different individuals than all to the same 
length and level in all individuals.” 
Darwin points out that the mutual sterility of these plants could 
not have resulted from natural selection, and although he thinks 
that the difference in the length of the stamens and pistils has 
resulted from a process of natural selection, yet he admits that 
one of the most striking facts in the case is that the individuals 
have in consequence become partly sterile to half the other indi- 
viduals in one case and to three fourths in the other. This con- 
clusion in itself shows, it seems to me, how futile it is to apply the 
theory of selection of fluctuating variations to the process of 
evolution of these forms. . 
Bateson and Gregory have examined the inheritance of hetero- 
stylism in Primula and have found that the Mendelian rule is 
followed. In the case of P. sinensis, the short-styled is dominant 
over the long-styled form. When long-styled was crossed with 
long-styled —pure forms being used —all the offspring (F,) were 
long-styled. When these were inbred again, only long-styled 
forms (F,) were produced. 
The short-styled plants that were obtained for experimental 
work proved to be heterozygous (DR). When these short-styled 
were crossed with short-styled forms, there were produced 
26 short- and ro long-styled — the Mendelian expectation being 
3:1. Of these 26 short-styled forms some were pure dominants 
(DD) and others dominant-recessives (DR). The latter (DR) 
inbred gave short (24) and long (4). It was found that other 
combinations also conformed to the Mendelian expectation. 
Bateson and Gregory also examined the inheritance of a 
peculiar form of Primula sinensis known as equal-styled. The 
anthers are at the same level as in long-styled flowers, but the 
style is short and does not reach above the level of the anthers. 
The corolla has a central yellow flush extending over half of each 
* A few departures difficult to explain were also met with. 
