Daily asthma attack diaries of 16 panels of asthmatics residing in the Los Angeles area were collected by the Environmental Protection Agency for 34-week periods during the years 1972-1975. There data are examined here for the relationship between daily attack occurrence and daily levels of photochemical oxidant, total suspended particulates, minimum temperature, relative humidity, and average wind speed. A separate multiple logistic regression is used for each panelist's attack data. Variables representing the presence or absence of attack on the preceding day, as well as day of week and time since the start of the study, are included in the regressions. The most significant predictor of attacks was the presence of an attack on the preceding day. On the average, the panelists tended to have increased attacks on days with high oxidant and particulate pollution, on cool days, and during the first two months of the study. Panelists' attack propensity also differed by day of week; in particular they had more attacks on Saturdays (the last day of the weekly reporting period) than on Sundays. Each panelist's regression coefficients are classified according to age, sex, hay fever status, and self-assessed attack precursors; this classification is used to examine subgroups among the panelists with high coefficients corresponding to the above factors.