Collecting data q You will learn how to: * Select and trial data collection and sampling methods to investigate predictions for a set of related statistical questions, considering what data to collect (categorical, discrete and continuous data). + Understand the effect of sample size on data collection and analysis. Starting point Do you remember. + planning a statistical investigation? For example, planning an investigation to see if there is a connection between hand span and height. ‘* making predictions about what you think your data will show? For example, predicting that taller people wll havea larger hand span than shorter people * collecting data to see if your prediction is correct? For example, colecting data from 15 students in your clas + you learn more about the problems linked with some methods for collecting data * you learn more about presenting your data in different ways = you learn more about calculating averages from data to help analyse it. 3.0 Getting started A person's pulse rate is the number of heartbeats per minute. Pulse rates are affected by a person's age and weight, health, medication and even air temperature and body position. A normal pulse rate for a person older than 10 years old is between 60 and 100 beats per minute when they are at rest. Predict what you think might happen to your pulse rate when you exercise. Tip Let's find out! To measure your pulse rate, put your fingers on your wrist and count the beats. Jog on the spot for one minute, then measure your pulse rate again. _ Record the number of beats Record the number of beats per minute immediately after you stop _per minute. jogging Measure your pulse rate when you are sitting down, * What happened to your pulse rate? Did you know? * Compare your results to others in your class what do you aire anivouiaes : in your neck. Place your + To investigate further, what other information could index and middle fingers you collect? on your neck to the side of your windpipe. Stage 7: Student’Key terms Data types: Categorical data are data that can be put into categories. Examples of categorical data are count: of birth, favourite subject, name and eye colour. rete data are numerical values which can be recorded exactly. Discrete data usually is counted Examples of discrete data are number of brothers and sisters, number of books and number of employees The name and the colour cannot be counted or measured. aah name of the flower The number of petals can be counted ‘Conteeeeeeees and the results will be given as whole foibeimesstenriencianen numbers. rounded to a suitable degree The height and diameter are of accuracy. Examples of measurements and will be rounded to _—_continuous data are height, perhaps 1 or 2 decimal places. mass and speed. @ Fis colleting information from people about ther use of mobile phones Decide if each of the following variables is categorical, discrete or continuous data 2) the time spent using their mobile phone yesterday b) the number of text messages they sent yesterday ©) the make of their mobile phone. Sofia is measuring the height of sunflowers in her garden. Is the height of the sunflowers discret cor continuous data? © Humna is collecting data about the voluntary work that some of her friends and family do. Decide if each of the following variables is categorical, discrete or continuous data. + time spent per week doing voluntary work + age (in years) + number of volunteers in their organisation + gender (male or female) + type of voluntary work undertaken, Chapter 3: Collecting data@ 4 football coach wants to find out about the fi ess levels and performance of his players. He collects the following data from each player: + heart rate (beats per minute) + height + mass * age (in years) + time taken to run a 100 metre sprint + number of goals scored in training, Write down whether each variable is continuous data or discrete data. @ “Zotin wants to investigate the shopping habits of his classmates. List two examples of aicrete | data he could collect and two examples of continuous data he could collect. | YQ Brsita says that age is iscete data. Jordan says that age is continuous data. Explain how Brigita Foe ee pera ” Thinking and working mathematically activity Copy this table. imagine that you want to collect data from people about music. Think of examples of variables that you could collect data about. Write your examples in the correct column in the table. Try to find at least two variables for each column. 3.2 Data collection methods Key terms When you investigate a statistical question, you may need to collect your own data ‘There are several common methods for collecting data 1 Observation - This is when you collect data by observing or counting. For exemple, you could count the number of cars that pass along a road. The collected data can be recorded in a data collection sheet which is a type of table. 2 Interviews - This is when you collect data by asking people questions. For example, you could ask people about their views on how to protect the environment. A focus group is a group of people who are brought together to discuss their views on a particular subject. 26 Stage 7: Student’s Booklonger written answer. orked example 2 jender of people who use the site and ho. ey use it a ‘What is your age? | *Under18 0 * 18-30 a 931-60 o *6lorover O 3 Questionnaires — A questionnaire is a set of questions that you send out for people to complete. You can design a questionnaire for people to complete online or on paper. For example, you could prepare a questionnaire to ask people about their holidays. Questions in a questionnaire should be cleer and easy to answer. A questionnaire can include yyesino answers, tick boxes, numbered responses, word responses and questions requiring a ‘A question is said to be biased if it is worded such that a particular answer is favoured over other answers. To get reliable data from a questionnaire, the questions should be unbiased. Ste manager wants to find out about the age and gender of people who use the site and ‘often they use it. Design a short questionnaire for users to complete to collect this data, Tanager wants to find out about the age and often The manager wants to know three things: tage 2) gender 3) how often people use the site. The first question is about age so you can either ask for an exact age or provide categories. Categories are easier to analyse. Make sure that the options do not overlap and that every possible age is included. The second question is about gender, so you can ask a simple male or female question here. FE ‘What is your gender? __sfemale 0 + Male o a ‘often do you use this site per week? | *0ort times o © +2or3 times a _ +4-10times a *morethan 10times (1 Do adults sleep more than children? a) gender of person b) age of person number of hours slept last night 4) time they woke up this morning @ Wo has been asked to explore the question For the third question you can use option boxes to make the data easier to analyse. Make sure the options do not overlap and that every possible answer is included. Make sure you give a time period for people ‘to base their answer on, for example, per month or per week. He has decided to collect data from people in a local town centre. Which two of these things will it be most useful for him to collect data about? Chapter 3: Collect g data© A café owner is trying to find out which drinks are its bestsellers. She will record the drinks that customers buy one morning. Copy and complete the data collection sheet. Fill in the first column with names of possible drinks. © Valeria is researching students’ favourite subjects She completes a survey of students and asks them, ‘What is your favourite subject?" Design a table for Valeria to use to record her results. @ write 2 questionnaire question that could be used to collect data in each of these situations. Include some response boxes for each of your questions. a) Moira wants to find out how many hot drinks people have in a day. 'b) Amol wants to find out how far (in kilometres) students in his school travel to school. © A mobile phone company believes that young people use their phones more than older people. Write a questionnaire of at least three questions to help the company collect data to test their theory. Try to include response boxes for some of the questions. |@“espreet wants to collect information about how many times people play sport. Mere is the question she has written: How many times do you play sport? oto2l_] 204-2 atoel] more than 6[ | 2) Identify two problems with this question. b) Write a suitable question for Jaspreet to use. N@ Rewrite the following questions so they are not biased * a) Do you agree that the environment is important? b) The business has made a profit for the last five years. Do you think the business is successful? ©) Are you in favour of opening a new cinema to give young people more to do?DY” Thinking and working mathematically activity 1 Design 2 questionnaire for collecting data about music. Wri collect information about things like: '* age and gender * the type of music people like how people listen to music (radio, streaming, ...) + the amount of time people listened to music yesterday. Include some tick boxes for each of your questions. Give your questionnaire to a few friends to complete. Ask them to tell you how easy it was to ‘complete. Use their comments to make some improvements to your questionnaire. questions that will help you to Jana wants to know how many passengers there are in cars using a specific road. Suggest a way that Jana can collect suitable data Lucasz is opening a book shop in a town. He wants to find out whether people in the town would use his shop. Suggest a way that Lucasz can collect suitable data. A chocolate company has developed a new type of chocolate bar. The company wants to find out the opinions of people about this chocolate bar before it is sold in the shops. Suggest 2 way that the company can get this information. NG Ceraicine is investigating the average height of people in different countries around the world. Y Which would be the most sensible way for her to collect useful data? Explain your answer. a) measure her own height b) measure the height of people in her class look on the internet 4) phone up people in different cities and ask them for their height. Elliot is researching what people think about libraries. He designs a survey to complete. Y Which would be the best group of people for him to survey? Explain your answer, a) people in his local library b) children at a school ) people in a town centre d) people in a local bookshop. Belen mired Key terms The set of all people or things you want to find out about is called the population. ‘You may not want (or be able) to collect information from everybody in the population. instead, youcan collect information from a sample. A sample isa selection of people from the population from which data is obtained. The sample should be representative of the population - this means that the sample should be as similar as possible to the whole population. Asample is called a random sample if every member of the population has an equal chance of being picked. An easy way to get a random sample is to pick names from a hat. Another way is to number everyone in the population and then pick the sample using a random number generator. The sample size is the number of people you decide to survey from the total population Chapter 3: Collecting data 29Worked example 3 A school has 1000 students. The head teacher wants to investigate the average time that students at her school spend travelling to school. a) Write down the population for the head teacher's investigation. b) She decides to ask a sample of ten students in Year 7 for their journey time to school. Write down two comments about her sample. ©) Explain how the head teacher could choose the students who will be in her sample. a) The population is all students in the school. b) Selecting ten students is too small a sample size to gain a variety of results The head teacher's sample will not be representative of all students in the school as __ she is only asking students from Year 7. ©) She could put the names of all the students into @ hat and pick out names without looking. @ A sym has 500 members. The manager wants to select a sample ‘of gym members to ask them what they think about the gym. 2) Explain why asking a sample of five gym members may not give reliable results. b) Suggest a more suitable sample size. The population is all of the people that she wants to find out information about. The more students you survey, the more reliable your results will be. In this instance it may be more appropriate to ask about 100 students. selection of students from all year groups should be used, not just students from one year group. z She should choose her sample randomly. This will help to make sure the students in her sample are representative of those in the whole school. Discuss Why in Worked example 3 why might the journey times to school for Year 7 students be different to the journey times for older students? @ Pippa wants to select a sample of people who work at her office. She has a list of all 100 people who work at the office. She selects Did you know? the first person on the list and then every fifth person. How many people does Pippa select? © Decide whether each statement below is true or fase population. ‘A sample that is chosen by selecting people at regular intervals is called a systematic sample. a) A very small sample is likely to be representative of the whole b) Data from a large sample takes longer to analyse than data from a small sample. ©) Results from a large sample are likely to be more reliable than results from a small sample. 30 Stage 7: Student’s Book@ Mathias wants to find out how often people from his town go to the cinema. He decides to interview people for his survey. a) What is the population for his survey? b) Give a reason why Mathias is unlikely to want to collect information from everyone in the population. ©) Mathias decides to interview 50 people from the town. He plans to conduct interviews by asking people in the street. Suggest a suitable time and place where Mathias could conduct the survey. © 427 wants to investigate how happy residents living in an apartment block are with their apartments, She decides to select a sample of residents. a) Write down the population for her investigation. b) Amy decides to ask all the residents living on the first floor. Explain why her sample is not a random sample of residents living in the block ©) Explain how Amy could obtain a random sample of residents, “Andrei wants to know how many hours per week people spend exercising. He asks 30 people 7 this local running club. Give one disadvantage of this approach. “ierey has been asked to investigate the ages of people who use the library. He stands in the 7 library between 10 a.m. and 11 a.m. on a Wednesday and he tallies the number of people who come in during that period. Give two disadvantages of this method, © 4 college has 2000 students and 100 staff. The college wants to find out what students and staff think about anew timetable. TIP Write down a plan for data collection. Ensure that you include all of the details In question 8, include information like: + how many students and how many staff the Y 7 Thinking and working mathematically activity 1 Use the questionnaire that you designed in section 3.2 to college should question collect some data about music from students in your school Think about: ‘+ how these students and staff could be selected * What do you expect to find out? (These are your conjectures.) |. how the college could = Who do you want to collect data from? Who is your target collect information from Population? ‘these students. + How many people will you give your questionnaire to? + How will you select the people you will ask to complete your questionnaire? Explain why your choices will lead to reliable data being collected. After you have collected your data, make some conclusions. Were your conjectures shown to be true? Chapter 3: Collecting data. 31Consolidation exercise Y Copy this table onto a piece of paper. Write these statements in the correct place in the table: + number of pets is continuous data * area is continuous data * favourite TV program is categorical data * speed is discrete data. (@ There are 500 nurses who work at a hospital. Jill wants to find out what they think about a new Y work rota. She decides to ask five nurses for their opinion. Comment on Jill's sample size | © George owns a fruit shop. He wants to find out what type of fruit his customers like best. 2) What is the population for his investigation? b) George decides to interview 30 of his customers. Suggest one way he can select these customers. YQ Emily designs a questionnaire to find out about Mathematics homework. Here is her questionnire: @ 00 you agree that Mathematics homework is very useful? + Yes + No @ How long do you spend doing your Mathematics homework per week? + 0-30 minutes + 30-60 minutes + 60-90 minutes © Where do you usually complete your homework? ‘© In the library * Athome | @ what do you think of your homework? tip + Always interestin: easter ae Try answering the questionnaire yourself to * Always boring see what the issues are. + Sometimes interesting Give feedback on Emily's questionnaire and make suggestions about how she could improve it. 32 Stage 7: Student's BookEnd of chapter reflection You should know that. Rr Sees There are different types of Identify data that is categorical, | Which of the following data. continuous and discrete. variables are continuous? ‘There are different ways Identify which information James is going to investigate ie sample? Gophie wants to find out what people think about government spending on roads. Y Which of these questions is the best? Explain your answer. ‘A: Doyou think you pay too much tax? B: Do you think our roads are good? ‘G Would you be prepared to pay more tax if the money raised was spent on improving roads? D:Doyou think the government spends too much money on themselves and not enough con roads? Vocabulary question Copy and compete the sentences below and fill in the blanks using the list ‘of words in the box. [categorical exact sample size discrete measurements survey continuous _ results When conducting a it is important that your is large enough to give reliable Sometimes the data you collect will be , such as eye colour or favourite sport. Other data is numerical. data is counted data and is values, such as the number of students in a class. data (for example height or mass) are and cannot be written down exactly. height, number of siblings, mass, number of press ups of collecting data such as needs to be collected, whether adults eat more or less. ‘questionnaires, face-to-face chocolate than teenagers. interviews or by observation, | Decide which method of data collection is appropriate. ) What information should he collect? b) How could James collect the information he needs? ‘Questions in a questionnaire Design a questionnaire to find | Design a questionnaire to find shouldbe clear and simple to _out relevant data. ‘out how much money people answer. spend on chocolate Itis usually simpler to collect | Decide ona suitable way to _ Serena wants to choose 2 data from a sample rather choose a sample, sample of 20 houses from the than from everyone in the 200 houses on a road. population. How could Serena choose her Alerger sample size gives more | Choose an appropriate sample Explain why a sample of 10 reliable results. size for the population you are from a population of 1000 may investigating. be an inappropriate size. Chapter 3: Collecting data 33