Large data set momento mistaki

Explain how the data will need to be cleaned before the statistics such as the mean and standard deviation can be calculated. [there are trace values writted as tr and it is grouped data]

Need to replace tr with a numerical value

Value of tr is between 0 and 0.05 suggest using e.g 0.025 , 0 or value less than or equal to 0.05

Using your knowledge of the large data set give a reason why these data would not be suitable for estimating the annual mean daily total rainfall in a location for a year

Only covers May~Oct (so not a suitable sample)

State, giving a reason how you would expect the estimate (for mean daily total rainfall from large data set) to differ from the actual annual mean daily total rainfall for the location for the year

Winter months are missing when we’d expect more rain

so expect estimate in (b)(i) to be an underestimate

Refinement to a discrete uniform distribution for cloud cover

reason (varies with location and month) so non-uniform

what does mean temperature of 27.2 suggest in july

Overseas not perth

what does windspeed mean of 3.5 suggest

not coastal

Correlation between windspeed and temperature in winter? guessing from MS comment

Might expect weakly positive?

{using your knowledge of the large data set and wind is blows clockwise if high pressure and anticlockwise if low and pressure is around 1029. put these wind directions with heathrow hurn and leuchars. } Give a reason for your answer

Wind direction is direction wind blows from

high pressure so clockwise

locations are (from north to sound) Leuchars, heathrow, hurn

so: answer

Mean air temperature is 19.4 and standard deviation is 2.83 in perth suggest giving a reason a month these data may have come from

Mean is higher than average OR a summer/spring month

If they say winter/autumn they must explain that these are hotter

months for Perth.

[Perth is southern hemisphere or Australia so latest available]

month is Oct

For perth in 2015 mean is 5.3 and standard deviation is 12.4 using your knowledge of the large data set suggest which variable [This is]

Rain[fall] (allow [Mean] Windspeed)

Assuming each location is typical of the hemisphere it is in, suggest what

these means and standard deviations imply about the relative daily mean air

temperature in June 2015 in each hemisphere [mean for perth is 14.8 and SD for perth is 2.37 and mean for jacksonville is 26.6 and SD for jacksonville is 2.09]

Mean for Perth is lower than mean for Jacksonville which

suggests the daily mean air temperature is higher in the

northern hemisphere (in June)

Standard deviations are similar which suggests similar levels of

variation of the daily mean air temperature in each hemisphere

(in June).

OR

Sizes of standard deviations are small compared with the

difference in mean temperatures making it more likely that the

difference in means is significant.

comment on the validity of an assumption which was based on two locations to make generalisations about the two hemispheres

This is based on one location in each hemisphere and therefore

is not valid as temperatures are likely to vary across each

hemisphere

Sam decides to investigate the daily mean wind direction throughout the year.
“state a limitation of using the data for Hurn from the large data set as a sampling frame”

Large data set only gives data for months May to October

or large data set only gives data for 2 specific years

Explain how to use simple random sampling to select 36 days from a year

Any two from eg

Create numbered list or sampling frame of days of the year

Use random number generator/table to select 36 numbers

In the range 001 to 365 (or 366)

ignoring others/repeats

explain what affect this action [setting tr to 0] is likely to have on an estimate of the mean Daily Total Rainfall

Would underestimate mean value as 0 < tr < 0.05