Stats Flashcards
How does standard deviation help us interpret data?
- Shows the spread of the data / howdata varies2. Overlap = no difference / due tochance / not significant3. Low SD means results more reliable /repeatable
The scientists collected insects at sites chosen at random. Explain the importance ofthe sites being chosen at random.
Removes bias
A student investigated the diversity of plants at several sites on a golf course. At each site she took a large number of random samples.1. Explain the importance of taking a large number of samples at each site.2. Explain the importance of taking samples at random.
- Produces a more reliable mean/average / makes sure sample was representative / reduce effect of extreme values / identify anomalies2. Removes bias
Scientists investigated the effect of drinking tea and coffee on reducing the risk of developing one type of brain cancer. The investigation involved 410 000 volunteers and was conducted in 10 European countries over a period of 8.5 years.A. Apart from age, suggest 4 factors that the scientists should have considered when selecting volunteers for this trial?B. Give two features of the design of this investigation that would ensure the reliability of the results obtained.
A.1. Sex2. Lifestyle3. Body mass4. Health5. Ethnicity6. Genetic factors / family historyB.1. Large sample/number / 410 0002. Long time period / 8.5/many years3. Different countries / more than one country
During the investigation, the volunteers were asked to estimate the volume of tea and/or coffee that they drank each day. The types of tea and coffee consumed in different countries varied. When the data from all the countries were collected there was a correlation between drinking more than 100 cm3 of tea or coffee each day and a reduced risk of developing this type of brain cancer.Tea and coffee contain caffeine. A newspaper reported the results of this investigation under the headline ‘Caffeine helps cut cancer risk’. Explain why scientists could not support this view solely on the basis of this investigation.
- Correlation does not mean causal relationship2. Tea/coffee contains other substances3. Contain different amounts of caffeine4. Estimated intake (of tea/coffee)5. No control group6. Only one type of cancer studied7. Further studies required / only one investigation/study/group
In analysing the results of this investigation, the scientists took into account the age of the volunteers. Suggest why.
Cancer rates rise with age
Another group of scientists investigated the effect of caffeine on blood flow to certain parts of the brain. Volunteers were given different concentrations of caffeine solution to drink. A control group was also set up.Describe how the control group should have been treated.
- Treated the same2. No caffeine
Volunteers who drank the same concentration of caffeine solution often had different concentrations of caffeine in their blood. Suggest one reason for the difference in concentration of caffeine in the blood of volunteers.
- Absorb different amounts2. Broken down by enzymes/digested3. Different blood volumes4. Differences in metabolism5. Caffeine from a different source
The investigation showed that caffeine reduces the blood flow to certain parts of the brain. Suggest one way in which this could lead to a reduced risk of brain cancers.
- Less oxygen/glucose to (cancer) cells2. Less carcinogens3. Reduces spread of cancer (cells)
What does the standard deviation of data tell us?
It tells you how much the values in a single sample vary, its a measure of the spread of values about the mean.A large standard deviation means the values in the sample vary a lot. A small standard deviation tells you most of the sample data is round the mean value so varries little
what does the standard deviations suggests about heritability of values - values overlap
due to the values overlapping there is not a significant difference in heritability values- not a substantial difference win results- results due to chance
