Other topics may include logistic regression, survival analysis, survey sampling and nonparametric methods. Topics include experimentation, measurement, descriptive statistics, summary graphs, correlation, probability, confidence intervals, tests of hypotheses, 2-way tables, power and sample size calculations, diagnostic tests, chi-square distribution and linear regression. This course serves as an introduction to the collection, summarization, analysis and presentation of data. Tell me about the course content of BIOS 600.īIOS 600 is an introductory course in probability and statistical inference in public health. More linear relationship of log y versus x.1. Here, we took a logarithm of the y's and that helped us see a So the big takeaway here is that the tools of linear regression can be useful even when the underlying relationship between x and y are non-linear and the way that we do that Mathematically unwind from your linear modelīack to an exponential one. And what's neat is once youįit a linear regression, it's not difficult to And the reason why you might wanna do this versus trying to fit an exponential is because we've alreadyĭeveloped so many tools around linear regressionĪnd hypothesis testing around the slope and confidence intervals and so, this might be theĭirection you wanna go at. Looks something like this, it would fit the data quite well. Way, is now we can use our tools of linear regressionīecause this data set, you could actually fitĪ linear regression line to this quite well. Taking the log of y, and thinking about that
It looks like some type ofĪn exponential relationship, but the value of transforming the data, and there's different ways you can do it. Plotting x versus the log of y, or the log of y versus x, all And if you were to plot all of these, something neat happens. Of these data points, I did it on a spreadsheet. But for the y values, I just took the log base 10 of all of these. Of plotting x versus y, we can think about x We can apply our tools of linear regression to this dataset. So maybe we could fitĪn exponential to it. And some of you might be saying, well, this looks more like Of the square distances from the points to the line. Linear regression model to try to minimize the sum
I'm just eyeballing it, obviously you can input it into a computer to try to develop a Regression or regression lines is can we fit a regression line to this? Well, if we try to, we might get something that looks like this, or maybe something that looks like this, Given that we've been talking a lot about lines of So we have some data here that we can plot on a scatter plot that looks something like that.
0 kommentar(er)
