We watched a video of a presentation made by psychologist Dan Gilbert titled The Surprising Science of Happiness in which he describes several experiments he and his colleagues ran, the data they collected, the statistics they derived, and the conclusions they drew. We also watched a video of a talk by Simon Sinek titled Why Good Leaders Make You Feel Safe in which he talks about research into the biological foundations of leadership. This included data and statistics of brain chemicals such as seratonin, dopamine, epinephrin, oxytocin, and cortisol.
We looked at and discussed several articles/research papers to see how statistics is put to good use in science including Bees Prefer Flowers That Proffer Nicotine, Anxiety Mounts at National Labs Over Future of Climate Research, Climate Change is Turning Antarctica Green, Trees in Eastern US Head West as Climate Changes, Does the Brain Use More Energy During Particular Activities?
We finished a problem set including pythagorean theorem, area of a trapezium, trig functions SOH-CAH-TOA, volume of a prism, volume and curved surface area of a cylinder, circumference and area of a circle, using the order of operations (PEMDAS in the US, BIDMAS in the UK), arithmetic series, congruency of two polygons, obtuse angles, lines of symmetry, area of a parallelogram, vertical angles, reflex angles, isosceles triangle relationships, range, median, mode, exponentials, prime numbers, cube roots, solving linear equations, unit conversions (used unit analysis), simplifying algebraic expressions, probability, calculating percentages and percent increase, projections and rotations, solving simultaneous equations, calculating the modal class of a frequency distribution and the total amount, solving a compound inequality and graphing it, etc.
We did the problems in his statistics problem package including interpreting correlation coefficients, calculating average annual prices, calculating the chain base index, calculating the percentage increase, calculating the geometric mean, interpreting data for unemployment rates for several years, creating a cumulative frequency step polygon, determining the differences between random, simple random, stratified, and cluster sampling, etc.
We worked through several of the problems including completing a scatter plot and drawing a line of best fit, calculating the mean, using the best fit line to extrapolate predicted values and giving the reasons why this method could be unreliable, using and interpreting a choropleth map, formulating hypothesis, formulating survey questions from the hypothesis, determining whether data is quantitative or qualitative or primary or secondary, discussing the advantages and disadvantages of the different kinds of data, given data calculating the mean, median, quartiles, variance, and standard deviation, comparing means and standard deviations from two data sets.
We read and discussed an article titled The Curse of the Cluster about population research flaws caused by clustering of data and learned that the way to compensate for this possibility is to increase the sample size significantly, e.g. Democrats and Republicans tend to cluster in communities and states so a political poll needs to have a sample size of thousands to compensate. We also read and discussed an article on some data from the Trump administration performance.
