Maths Portfolio Comparison Investigation PDF

Math's investigation I wonder if male students Y4-10 at Wellington Campus tend to be taller in height (meters) than Females Y 4-10 at Wellington Campus for all students at OSG – NZ My Numerical variable is the height. I measured this in meters. I measured this by finding a blank wall and putting a...

Math's investigation I wonder if male students Y4-10 at Wellington Campus tend to be taller in height (meters) than Females Y 4-10 at Wellington Campus for all students at OSG – NZ My Numerical variable is the height. I measured this in meters. I measured this by finding a blank wall and putting a metal tape measure against it for height measurement. Each student took their shoes off and stood flat against the wall with heels touching the base of the wall and head held straight. Using a flat object such as book I took the measurement from the bottom of the book and logged them in my data table. My Categorical variable is gender. I am measuring in meters. I collected gender data by obtaining a student sheet from the office. I then found each student we had measured in height and found their gender. I then logged the data into my data table. I am interested in this relationship because it is a common stereotype that boys are taller than girls., so I am interested if this is is just a stereotype or if this is factual Someone might find this information useful is a sports coach making their decisions about what training or strategies to train their players in. This could help them create strategies for both taller and shorter players to utilize in games. Hypothesis I expect my results to show that boys tend to be taller than girls. This is due to the gender stereotypes and the evidence we see in everyday height. I also know that the tallest man was taller than the tallest women although these would technically be outliers. Judged on this I think I should be able to make the call and I expect boys tend to be taller. Plan I Managed variation for my data in many ways. This means that the data will be reliable. For height measurements I made everyone take off their shoes meaning people wearing bigger shoes had no advantage, I also didn’t count hair meaning people with bigger hair also had no advantage. Finally, I gathered all data at the same time with the same people at the same place with the same tape measure and units (meters) meaning that variation is controlled. If this had not been controlled this could’ve meant that different people taking different heights such as from the top of the book or including the hair or using a different tape measure meaning the data could become unreliable. For gender data collection I went off an official school document so this would be correct. My data is primary source this is because I collected it myself Plan continued For this Investigation I chose a random sample size of 30 although this is still reliable, I would have preferred to do more. This was not achievable due wellington having a smaller campus. Having a sample size of 30 means that I can safely provide a reliable conclusion based on the sample of population. To avoid bias I will randomly take 30 students data meaning that we didn’t have a large range of older kids' vs young ones or more boys than girls. I randomly collected my data by making sure every student from year 4-10 had an equal chance of being chosen. To do this I used a random name generator in which I put in every name and had it give me 30 random names. Two sources of variation we might deal with are posture and footwear. To mitigate these, I can instruct each student to take their shoes off and stand flat foot, heels against the wall, back straight among other things whilst I take their height. If these where ignored this data would be unreliable as some shoes has thicker soles, if not flat footed this makes you taller and so on.  Gender Height (meters Male 1.54 Data Male 1.41 Male 1.47 Female 1.52 Male 1.46 Male 1.54 Male 1.52 In my data the only errors I Female 1.48 Female 1.49 found was the split of boy's vs Female Female 1.52 1.48 girls' data being recorded. I Male Male 1.59 1.61 spotted this when I first Female 1.53 randomized the names, so I Female 1.44 Female 1.37 kept randomizing until I got Female Female 1.35 1.24 another girl to keep this data Female Male 1.36 1.4 reliable. Male Female 1.27 1.37 I used NZ Grapher to draw dot Male Male 1.21 1.17 and box plots to represent the Male 1.34 data as it will help me to Female 1.35 Male 1.5 compare the variables. Male 1.57 Female 1.48 Female 1.58 Data continued Analysis With the female graph we can see a semi-regular almost bell like shape. I can see that there are two obvious groups with are around 1.35 and 1.5 meters. The IQR is 16 centimeters. There is one data point which is much smaller than the others which could be considered an outlier, but I left this in her due to the fact I can remember from my data collection that this was a young student. In the males graph we can see a lot more of a regulation bell or normal skew. The data is all very spread out and there does not appear to be any significant outliers. Compared to the Females graph the IQR is shown to be slightly bigger at 20 centimeters and males have the smallest (1.17 meters) but also biggest (1.61 meters) of the students measured This analysis means that whilst males have much more of a spread females have a much more concentrated set of data with this, we can see with the summary the median of the females is 1 cm taller than the males. Whilst the males have a bigger IQR Conclusion 1/2 / ¾ rule Conclusion – Making the call With the male's median falling inside the females IQR this concludes that I cannot make the call that if male students Y4-10 at Wellington Campus tend to be taller in height (meters) than Females Y 4-10 at Wellington Campus for all students at OSG – NZ. This is based off my NZ-Grapher box and whisker graphs made from my primary data. At the start of this investigation my hypothesis was that I expected to be able to make the call and that boys would tend to be taller but through my data collection and the making of my graphs I found out that this is not the case and that the stereotype of boys being taller is just a stereotype. Reflection If I had the chance to do this experiment again, I would improve my sample size to 75 or 100 over multiple different campuses. This would even further reduce the chances of bias data making the outcome even more reliable. Although I thought that I dealt well with biasness one thing that I failed to account for the measurer bias. This means that when I collected my data my point of view could’ve created bias when collecting the data. The only limitation I can thnk of my data I found was as stated before the data was only collected on wellington campus, and this could be very different to a different campus. And finally measurement error. When I took the measurements for my data I used a rather old tape measure that had the possibility of being slight off the exact measurements. But overall I believe that my report was reliable.