This is the first time I have requested info from a user group and I must thank contributors for their very speedy response. The language of the kindergarten (or even simpler)suits me fine as I have no experience in the subject matter. To give more background info I am teaching a group of general office staff various elements of Microsoft Office. They are studying for a UK standard that is more or less eqivelent to the Microsoft MOUS qualification. One of the criteria they have to meet is to be able to create Excel pie, column, mixed line/column and scatter charts. In theory all they need to do is create the graphs from supplied data but I would like to at least explain in what situation you might use a scatter graph, the pupose of the trend line and how to interpret the trendline equation. I have given up on my original target of 30 words and propose to add this to the handout:
"A scatter graph is a statistical diagram drawn to compare two sets of data. It can be used to look for connections or a correlation between the two sets of data e.g. temperature and sales of ice cream, hours watching TV and Exam results etc. A scatter chart has two value axes instead of one value axis and one category axis like most chart types. Data used as x values should always be in the first row or column. Data for y values should always be placed in the row or column following the x values. Example A supermarket wants to know the effect temperature had on the sales of ice cream. The available data was as follows: Temp (oC) -10 -5 0 5 10 15 20 25 30 35 Sales (�000) 2 3 4 5 8 12 25 40 50 75 The equation resulting from this data is y = 1.4909x + 3.763 The equation is displayed in the form y = mx+ c where m is the slope of the line and c is the Y-axis interception. The equation for the above trend line is: y = 1.4909x + 3.7636 Assuming you accept the trend line, this equation allows you to calculate any Y axis value i.e. sales of ice cream, without looking at the graph. For example what are ice cream sales liable to be when the temperature is 20oC? Using the equation Y = 1.4909X + 3.7636: Y (i.e. ice cream sales) = (1.4909*20) + 3.7636 Y (i.e. ice cream sales) = 29.818 + 3.7636 Y (i.e. ice cream sales) = �33,586 Hopefuuly with your hepl I have managed to come up with a simplistic explanation but any comments would be most welcome. Thanks Jacob T [EMAIL PROTECTED] (Donald Burrill) wrote in message news:<[EMAIL PROTECTED]>... > In the absence of any context, it is nearly impossible to offer useful > advice. E.g.: > "I have to produce..": Why? At whose behest? In some institutional > context, perhaps? > "intermediate Excel ... users": high school? college? graduate > school? psychologists? accountants? sci-fi authors? middle > management? And "intermediate" with respect to what? > > Further comments embedded below... > > On Fri, 27 Feb 2004, Jacob Thomas wrote (edited): > > > I have to produce a simple handout for intermediate Excel Chart/Graphs > > users, which unfortunately for me has to include Scatter Graphs. I can > > follow the logic behind the trend line but am not sure how to > > interpret the trend line equation. For instance on the chart I have > > produced the trend line equation is y = 1.4909x + 3.7636. > > What variable is "y"? What is "x"? In what units are they measured? > Note, please, that "y = f(x)" does not really (as it may seem to) say > that the observed values of y are equal to this function of x; "y" in > this equation should be interpreted as "the predicted value of y" (using > the function of x that in some sense best predicts it). Commonly in > textbooks one imposes a circumflex (^) over the "y", and reads the > result "y-hat", as a way of distinguishing between some observed value y > and the corresponding predicted value y-hat. (If this sounds to you > like kindergarten, so much the better; if it distresses you to be > addressed in kindergarten language, recall that you provided no > information about your own level of understanding.) > > All that one can say, from the information available, is that "y" can be > predicted from "x" by starting with 3.76 and adding 1.49 times the > value of x. This will be defensible only over a limited range of values > of x, but you have supplied no information as to what that range might > be. You also have failed to supply information (presumably available > from the "trend line" routine; I am unfamiliar with Excel and would > never use it for this purpose) that would help one to tell whether > either of the constants reported (3.76 or 1.49) differ significantly > from zero (or any other value, for that matter). Whether it is useful, > or reasonable, or good, or bad, that the fitted function predicting y > increases by 1.5 units every time x increases by 1 unit, I cannot tell. > > > Is this good or bad, ... > > Impossible to tell, out of context. In fact, without context, one > cannot even tell what "good" and "bad" might mean. > > > and at what point does it become of no use? > > On what continuum are you perceiving "points" (in which this question > makes sense)? "Of no use" with respect to what intended utility? > As it stands, I find the question meaningless, therefore unanswerable. > (This is not to imply that your idea(s) be meaningless, only that I do > not perceive them clearly enough to make sense of them.) > > > I am looking for a simple explanation/definition for non > > mathmaticians, and in less than 30 words!! Thanks . . > > There may be such an explanation suitable for your context; but if > there is, I rather suspect you must generate it yourself (one cannot > explain what one does not understand), and it will take far more than 30 > words for anyone to help you come to an understanding adequate to the > task. > > More might be written, but perhaps this is enough for a start. > ------------------------------------------------------------ > Donald F. Burrill [EMAIL PROTECTED] > 56 Sebbins Pond Drive, Bedford, NH 03110 (603) 626-0816 > . > . > ================================================================= > Instructions for joining and leaving this list, remarks about the > problem of INAPPROPRIATE MESSAGES, and archives are available at: > . http://jse.stat.ncsu.edu/ . > ================================================================= . . ================================================================= Instructions for joining and leaving this list, remarks about the problem of INAPPROPRIATE MESSAGES, and archives are available at: . http://jse.stat.ncsu.edu/ . =================================================================
