I'm working on a spreadsheet to calculate the size of a holding tank for condensate water. The goal is to size the tank so that on the worst day (sometime in February) we have 50 or 100 gallons in the tank.
I've got a data set of average monthly condensate water from 18 ac units.
Here's the monthly average, Jan to Dec (in gallons):
310
134
996
2298
3801
3289
3110
3350
3046
1454
1430
307
To make the simulation more accurate and eliminate the sudden changes that occur after the first of each month (Where Feb is 134 gallons and Mar is 966) I'd like to be able to calculate 365 data points that are along the mathematical curve created by the 12 average points so that the accumulation is more realistic. For simulation purposes I can assume that the average monthly is at the mid month of each month.
How would one go about such a calculation?
Related
Date Open High Low Close Volume
1993-01-29 27.14 27.14 27.00 27.12 1625280
1993-02-01 27.14 27.31 27.14 27.31 778338
1993-02-02 27.29 27.39 27.23 27.37 325941
Hi,
I have this timeseries from the S&P500 index (daily data) starting on 1993 all the way to 2018.
I was trying to build seasonal charts, like the January movement from day 1 to 31 since 1993 in one chart or the evolution of prices from January to December to see the sell in May effect.
Forgot to say that I'm only using the close column.
Thanks...
Steve
I have an excel sheet with one column named (population of 2018).
lets suppose that the pop of 2018 is 25 million.
I want to add one more column which represent the population of the year 2028; which is ten years later from now.
If the increase percentage of the population is 3% every year, how to calculate the population for 2028?
Thank you.
You should have to find out the population of last 50 to 100 year and then see how much population is increasing from last 10 year.
for example if the population in 1988 is 10 million and in 1998 it will become 13 million and then in 2008 become 18 million and in 2018 it will become 28 million.
in 1998, population is increased by 30 percent.
in 2008, population is increased by 38 percent.
in 2018, population is increased by 55 percent.
so from the above data we can say that in 2028 population will increase approximately 82 to 85 percent that will be 51 million.
If cell A1 holds data then your formula should be:
=A1*(1+0.03)^10
To compute the travel time (across two points) over a period of time, I was logging the time at which I crossed the sub-points between the two main points. My ultimate aim was to prepare a line chart which would show the trend of the journeys, and then find out where I have lost time and where I have gained.
My time entries are in the below format
Day 1|Day 2
09:55|09:35
10:01|09:37
10:06|09:42
10:09|09:45
10:12|09:49
10:15|09:51
10:22|09:58
10:28|10:08
10:35|10:18
10:38|10:21
10:48|10:31
I drew the chart with the time series appearing on the y axis (with journey points on the x axis). But Excel has some logic to determine which time values should be shown in the y axis. How can I force excel to only show the time values which I want to be seen? For example in the above case I actually need time stamps like ;
09:00
09:15
09:30
09:45
10:00
10:15
10:30
10:45
11:00
How can this be done? Thanks in advance.
Found the answer. On the Axis there is a provision to set the Min, Max values, and Major and Minor points on the axis.
For the Min and Max values, divide the hours you wish to see by 24. Example, if the starting time should be 9AM, then 9/24 = 0.375 should be given as the Min value. If 12 noon should be the max value then 12/24 = 0.500 should be given as the Max value. For the Major point, in case the intervals have to be of 15 mins the formula to be used is (15/60)/24 = 0.01041.
EDIT: To clarify, I'm specifically attempting to project the number of points that will be scored by a particular player in the NBA on any given night. So the groups below display the points scored by Player A, Player B, and Player C. Then, when all three players are on my team their combined averages are 73.25. What I'm trying to calculate is the Standard Deviation from the combined points that all three players have scored. In other words, if I put all three players on my team, and the would combime to score an average of 73.25 points, what would the STDEV on that average be based on the number sets that I have?
I'm trying to figure out what the Standard Devation of a group of multiple subsets would be once they are combined.
I have 3 sets of numbers, as follows:
Group A:
9
18
27
26
Avg: 20
STDEV: 7.25
Group B:
15
27
32
18
Avg:23
STDEV: 6.82
Group C:
19
48
34
20
Avg: 30.25
STDEV: 11.84
So I have the Standard Deviation for each individual group, but if I were to combine the three groups, for example, the average would be 73.25 (the sum of all of the averages). How would I calculate the Standard Deviation for the total I would get for all of these sets combined?
If I take the STDEV of every number I get 9.91, but the average of 73.25 and STDEV of 9.91 doesn't seem right to me. Is there another way to do it?
If I am understanding this correctly groups A,B and C are actually players A,B and C. Given that I would think that it would be significant to say something like player B averages 23 points per game with a standard deviation of 6.8 so that we could project he scores in the 16 to 30 point per game range.
I am further assuming that the four numbers given are for four games and that the 73.25 average is the average number of combined points scored by the three players in the four games. So my thinking is that to get the average standard deviation of the three players combined you would get the standard deviation of the game totals. This would give you a resulting standard deviation of 21 pts. meaning that you could project that the combined points of the three players would be anywhere from 52 to 94 points in a game. (Notice that the first game turns out to be an outlier game for the three players combined and for players A and B individually.)
I would like to compute some descriptive statistics about the following table of information. The main thing that I like to describe is the Price component.
Price Qty
493 5
4500 8
2107 14
269 1
The weighted average is straight forward with =sumproduct(Price,Qty)/sum(Qty). However it gets more challenging when I want to calculate the =skew() and =kurt(). In an ideal situation I would have data that isn't aggregated, but unfortunately I only have aggregated data.
Does anybody have a smart idea about how to get the skewness and kurtosis in Excel using the above data?
There are two ways to do this, but I don't think you're going to like the answer, since Excel functions don't work with aggregate data.
First way would be to unroll the data.
Price
493
493
493
493
493
4500
4500 (x 7 more times, one per row)
2107
2107 (x 13 more times, one per row)
269
Skew, kurtosis, and standard deviation will all work great with data unrolled.
Here's another way.
Extending your example:
Price Qty AggPrice
493 5 2465
4500 8 36000
2107 14 29498
269 1 269
AggPrSum =sum(c2:c5)
mean =sum(c2:c5)/sum(b2:b5)
You may then calculate the skew by applying the equation. When you calculate the mean, the rest should become clear. (You can start by adding a new column D which is price minus the mean, the difference cubed.)