Typhoon Hits Taiwan
Typhoon Morakot dumped heavy rain on Taiwan early Saturday and threatened to further soak the recently drought-stricken island. As of 3 a.m. local time, the storm's eye was over the northern part of the island, CNN forecaster Kevin Corriveau reported, although he noted that slow-moving Morakot is so large it encompassed the entire island.
Journalist Andrew Lee in Taipei, citing local media, said the storm had blown off roofs and washed out some bridges. Corriveau said the island has received more than 39 inches (99 centimeters) of rain from the storm, which he said was expected to dump another 39 to 47 inches (99 to 119 centimeters) of rain on Taiwan. The storm made landfall carrying winds of up to 92 mph (148 km/h), with gusts up to 115 mph (185 km/h), the Joint Typhoon Warning Center said.
More recent reports show great devastation, as in an AGI (Taipei) story on 14 August:
"The recent passage of Typhoon Morakot is having increasingly catastrophic results in Taiwan. The death toll currently stands at 117 but, according to Taiwanese President Ma Ying-jeou, the total could reach as high as 500 victims. It seems increasingly possible that around 380 people lost their lives buried under mud and detritus which wiped out the village of Hsiaolin, between the mountains in the south of the island, hit by a gigantic mudslide that was caused by torrential downpours caused by the typhoon."
Although Morakot hit several other countries including the Phillipines, and it continued on to mainland China, the greatest destruction and loss of life appears to be in Taiwan. Thus we chose this single 24 hour period to represent this long-drawn, widespread natural disaster. The formal event was set for the 24 hours of August 7th, 2009, UTC. Chisquare is 86113.006 on 86400 df, for p = 0.755 and Z = -0.690.
It is important to keep in mind that we have only a tiny statistical effect, so that it is always hard to distinguish signal from noise. This means that every "success" might be largely driven by chance, and every "null" might include a real signal overwhelmed by noise. In the long run, a real effect can be identified only by patiently accumulating replications of similar analyses.